[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-5ca4af3d573356c8-defab-a-new-benchmark-for-defeasible-abduction-in-summary":3,"summaries-facets-categories":85,"summary-related-5ca4af3d573356c8-defab-a-new-benchmark-for-defeasible-abduction-in-summary":4964},{"id":4,"title":5,"ai":6,"body":13,"categories":46,"created_at":48,"date_modified":48,"description":40,"extension":49,"faq":48,"featured":50,"kicker_label":48,"meta":51,"navigation":67,"path":68,"published_at":69,"question":48,"scraped_at":69,"seo":70,"sitemap":71,"source_id":72,"source_name":73,"source_type":74,"source_url":75,"stem":76,"tags":77,"thumbnail_url":48,"tldr":82,"tweet":48,"unknown_tags":83,"__hash__":84},"summaries\u002Fsummaries\u002F5ca4af3d573356c8-defab-a-new-benchmark-for-defeasible-abduction-in-summary.md","DeFAb: A New Benchmark for Defeasible Abduction in LLMs",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","google\u002Fgemini-3.1-flash-lite",4208,478,2753,0.001769,{"type":14,"value":15,"toc":39},"minimark",[16,21,25,29,32,36],[17,18,20],"h2",{"id":19},"the-challenge-of-defeasible-abduction","The Challenge of Defeasible Abduction",[22,23,24],"p",{},"Defeasible abduction represents a critical gap in current foundation model capabilities. While LLMs are proficient at pattern matching and probabilistic inference, they often struggle with non-monotonic reasoning—the logical process where conclusions are tentative and subject to revision when new evidence emerges. DeFAb (Defeasible Abduction Benchmark) is introduced to quantify this specific capability, moving beyond static benchmarks that only test for fixed, correct answers.",[17,26,28],{"id":27},"benchmark-structure-and-verification","Benchmark Structure and Verification",[22,30,31],{},"The DeFAb dataset provides a structured environment for evaluating how models handle logical explanations that may be invalidated by subsequent premises. Unlike standard benchmarks that rely on subjective evaluation or simple accuracy, DeFAb is designed to be verifiable. It includes a dedicated evaluation harness that allows researchers to systematically test whether a model can correctly identify when an initial hypothesis must be abandoned or updated as the context changes.",[17,33,35],{"id":34},"implications-for-ai-reasoning","Implications for AI Reasoning",[22,37,38],{},"By focusing on defeasible reasoning, the authors highlight the necessity for models to maintain logical consistency across dynamic contexts. This is essential for real-world applications where information is incomplete or evolving. The benchmark serves as a diagnostic tool to determine if models are truly performing logical inference or merely relying on memorized associations that fail when the logical constraints are explicitly challenged.",{"title":40,"searchDepth":41,"depth":41,"links":42},"",2,[43,44,45],{"id":19,"depth":41,"text":20},{"id":27,"depth":41,"text":28},{"id":34,"depth":41,"text":35},[47],"AI & LLMs",null,"md",false,{"content_references":52,"triage":62},[53,58],{"type":54,"title":55,"url":56,"context":57},"dataset","DeFAb Dataset","https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FPatrickAllenCooper\u002FDeFAb","recommended",{"type":59,"title":60,"url":61,"context":57},"tool","blanc evaluation harness","https:\u002F\u002Fgithub.com\u002FPatrickAllenCooper\u002Fblanc",{"relevance":63,"novelty":64,"quality":64,"actionability":41,"composite":65,"reasoning":66},3,4,3.25,"Category: AI & LLMs. The article introduces a new benchmark for evaluating LLMs' capabilities in defeasible abduction, which is relevant to AI engineering. However, it lacks practical applications or frameworks that the audience can directly implement in their product development.",true,"\u002Fsummaries\u002F5ca4af3d573356c8-defab-a-new-benchmark-for-defeasible-abduction-in-summary","2026-06-18 12:56:58",{"title":5,"description":40},{"loc":68},"5ca4af3d573356c8","arXiv cs.AI","article","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.18557","summaries\u002F5ca4af3d573356c8-defab-a-new-benchmark-for-defeasible-abduction-in-summary",[78,79,80,81],"llm","machine-learning","research","logic","DeFAb is a new, verifiable benchmark designed to test how well foundation models handle defeasible abduction—the ability to form logical explanations that can be retracted or revised in light of new, contradictory information.",[81],"9YOy68oF_PgD08g2Ldl6vnKAGw5ipWAU5wbLvq4cvak",[86,89,92,94,97,100,102,104,106,108,110,112,114,116,119,121,123,125,127,129,131,133,135,137,139,141,143,145,147,149,152,155,157,159,161,163,165,168,170,172,174,177,179,181,183,185,187,189,191,193,195,197,199,201,203,206,208,210,212,214,216,218,220,222,224,226,228,230,232,234,236,238,240,242,244,246,248,250,252,254,256,258,260,262,264,266,268,270,272,274,276,278,280,282,284,286,288,290,292,294,296,298,300,302,304,306,308,310,312,314,316,318,320,322,324,326,328,330,332,334,336,338,340,342,344,346,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,516,518,520,522,524,526,528,530,532,534,536,538,540,542,544,546,548,550,552,554,556,558,560,562,564,566,568,570,572,574,576,578,580,582,584,586,588,590,592,594,596,598,600,602,604,606,608,610,612,614,616,618,620,622,624,626,628,630,632,634,636,638,640,642,644,646,648,650,652,654,656,658,660,662,664,666,668,670,672,674,676,678,680,682,684,686,688,690,692,694,696,698,700,702,704,706,708,710,712,714,716,718,720,722,724,726,728,730,732,734,736,738,740,742,744,746,748,750,752,754,756,758,760,762,764,766,768,770,772,774,776,778,780,782,784,786,788,790,792,794,796,798,800,802,804,806,808,810,812,814,816,818,820,822,824,826,828,830,832,834,836,838,840,842,844,846,848,850,852,854,856,858,860,862,864,866,868,870,872,874,876,878,880,882,884,886,888,890,892,894,896,898,900,902,904,906,908,910,912,914,916,918,920,922,924,926,928,930,932,934,936,938,940,942,944,946,948,950,952,954,956,958,960,962,964,966,968,970,972,974,976,978,980,982,984,986,988,990,992,994,996,998,1000,1002,1004,1006,1008,1010,1012,1014,1016,1018,1020,1022,1024,1026,1028,1030,1032,1034,1036,1038,1040,1042,1044,1046,1048,1050,1052,1054,1056,1058,1060,1062,1064,1066,1068,1070,1072,1074,1076,1078,1080,1082,1084,1086,1088,1090,1092,1094,1096,1098,1100,1102,1104,1106,1108,1110,1112,1114,1116,1118,1120,1122,1124,1126,1128,1130,1132,1134,1136,1138,1140,1142,1144,1146,1148,1150,1152,1154,1156,1158,1160,1162,1164,1166,1168,1170,1172,1174,1176,1178,1180,1182,1184,1186,1188,1190,1192,1194,1196,1198,1200,1202,1204,1206,1208,1210,1212,1214,1216,1218,1220,1222,1224,1226,1228,1230,1232,1234,1236,1238,1240,1242,1244,1246,1248,1250,1252,1254,1256,1258,1260,1262,1264,1266,1268,1270,1272,1274,1276,1278,1280,1282,1284,1286,1288,1290,1292,1294,1296,1298,1300,1302,1304,1306,1308,1310,1312,1314,1316,1318,1320,1322,1324,1326,1328,1330,1332,1334,1336,1338,1340,1342,1344,1346,1348,1350,1352,1354,1356,1358,1360,1362,1364,1366,1368,1370,1372,1374,1376,1378,1380,1382,1384,1386,1388,1390,1392,1394,1396,1398,1400,1402,1404,1406,1408,1410,1412,1414,1416,1418,1420,1422,1424,1426,1428,1430,1432,1434,1436,1438,1440,1442,1444,1446,1448,1450,1452,1454,1456,1458,1460,1462,1464,1466,1468,1470,1472,1474,1476,1478,1480,1482,1484,1486,1488,1490,1492,1494,1496,1498,1500,1502,1504,1506,1508,1510,1512,1514,1516,1518,1520,1522,1524,1526,1528,1530,1532,1534,1536,1538,1540,1542,1544,1546,1548,1550,1552,1554,1556,1558,1560,1562,1564,1566,1568,1570,1572,1574,1576,1578,1580,1582,1584,1586,1588,1590,1592,1594,1596,1598,1600,1602,1604,1606,1608,1610,1612,1614,1616,1618,1620,1622,1624,1626,1628,1630,1632,1634,1636,1638,1640,1642,1644,1646,1648,1650,1652,1654,1656,1658,1660,1662,1664,1666,1668,1670,1672,1674,1676,1678,1680,1682,1684,1686,1688,1690,1692,1694,1696,1698,1700,1702,1704,1706,1708,1710,1712,1714,1716,1718,1720,1722,1724,1726,1728,1730,1732,1734,1736,1738,1740,1742,1744,1746,1748,1750,1752,1754,1756,1758,1760,1762,1764,1766,1768,1770,1772,1774,1776,1778,1780,1782,1784,1786,1788,1790,1792,1794,1796,1798,1800,1802,1804,1806,1808,1810,1812,1814,1816,1818,1820,1822,1824,1826,1828,1830,1832,1834,1836,1838,1840,1842,1844,1846,1848,1850,1852,1854,1856,1858,1860,1862,1864,1866,1868,1870,1872,1874,1876,1878,1880,1882,1884,1886,1888,1890,1892,1894,1896,1898,1900,1902,1904,1906,1908,1910,1912,1914,1916,1918,1920,1922,1924,1926,1928,1930,1932,1934,1936,1938,1940,1942,1944,1946,1948,1950,1952,1954,1956,1958,1960,1962,1964,1966,1968,1970,1972,1974,1976,1978,1980,1982,1984,1986,1988,1990,1992,1994,1996,1998,2000,2002,2004,2006,2008,2010,2012,2014,2016,2018,2020,2022,2024,2026,2028,2030,2032,2034,2036,2038,2040,2042,2044,2046,2048,2050,2052,2054,2056,2058,2060,2062,2064,2066,2068,2070,2072,2074,2076,2078,2080,2082,2084,2086,2088,2090,2092,2094,2096,2098,2100,2102,2104,2106,2108,2110,2112,2114,2116,2118,2120,2122,2124,2126,2128,2130,2132,2134,2136,2138,2140,2142,2144,2146,2148,2150,2152,2154,2156,2158,2160,2162,2164,2166,2168,2170,2172,2174,2176,2178,2180,2182,2184,2186,2188,2190,2192,2194,2196,2198,2200,2202,2204,2206,2208,2210,2212,2214,2216,2218,2220,2222,2224,2226,2228,2230,2232,2234,2236,2238,2240,2242,2244,2246,2248,2250,2252,2254,2256,2258,2260,2262,2264,2266,2268,2270,2272,2274,2276,2278,2280,2282,2284,2286,2288,2290,2292,2294,2296,2298,2300,2302,2304,2306,2308,2310,2312,2314,2316,2318,2320,2322,2324,2326,2328,2330,2332,2334,2336,2338,2340,2342,2344,2346,2348,2350,2352,2354,2356,2358,2360,2362,2364,2366,2368,2370,2372,2374,2376,2378,2380,2382,2384,2386,2388,2390,2392,2394,2396,2398,2400,2402,2404,2406,2408,2410,2412,2414,2416,2418,2420,2422,2424,2426,2428,2430,2432,2434,2436,2438,2440,2442,2444,2446,2448,2450,2452,2454,2456,2458,2460,2462,2464,2466,2468,2470,2472,2474,2476,2478,2480,2482,2484,2486,2488,2490,2492,2494,2496,2498,2500,2502,2504,2506,2508,2510,2512,2514,2516,2518,2520,2522,2524,2526,2528,2530,2532,2534,2536,2538,2540,2542,2544,2546,2548,2550,2552,2554,2556,2558,2560,2562,2564,2566,2568,2570,2572,2574,2576,2578,2580,2582,2584,2586,2588,2590,2592,2594,2596,2598,2600,2602,2604,2606,2608,2610,2612,2614,2616,2618,2620,2622,2624,2626,2628,2630,2632,2634,2636,2638,2640,2642,2644,2646,2648,2650,2652,2654,2656,2658,2660,2662,2664,2666,2668,2670,2672,2674,2676,2678,2680,2682,2684,2686,2688,2690,2692,2694,2696,2698,2700,2702,2704,2706,2708,2710,2712,2714,2716,2718,2720,2722,2724,2726,2728,2730,2732,2734,2736,2738,2740,2742,2744,2746,2748,2750,2752,2754,2756,2758,2760,2762,2764,2766,2768,2770,2772,2774,2776,2778,2780,2782,2784,2786,2788,2790,2792,2794,2796,2798,2800,2802,2804,2806,2808,2810,2812,2814,2816,2818,2820,2822,2824,2826,2828,2830,2832,2834,2836,2838,2840,2842,2844,2846,2848,2850,2852,2854,2856,2858,2860,2862,2864,2866,2868,2870,2872,2874,2876,2878,2880,2882,2884,2886,2888,2890,2892,2894,2896,2898,2900,2902,2904,2906,2908,2910,2912,2914,2916,2918,2920,2922,2924,2926,2928,2930,2932,2934,2936,2938,2940,2942,2944,2946,2948,2950,2952,2954,2956,2958,2960,2962,2964,2966,2968,2970,2972,2974,2976,2978,2980,2982,2984,2986,2988,2990,2992,2994,2996,2998,3000,3002,3004,3006,3008,3010,3012,3014,3016,3018,3020,3022,3024,3026,3028,3030,3032,3034,3036,3038,3040,3042,3044,3046,3048,3050,3052,3054,3056,3058,3060,3062,3064,3066,3068,3070,3072,3074,3076,3078,3080,3082,3084,3086,3088,3090,3092,3094,3096,3098,3100,3102,3104,3106,3108,3110,3112,3114,3116,3118,3120,3122,3124,3126,3128,3130,3132,3134,3136,3138,3140,3142,3144,3146,3148,3150,3152,3154,3156,3158,3160,3162,3164,3166,3168,3170,3172,3174,3176,3178,3180,3182,3184,3186,3188,3190,3192,3194,3196,3198,3200,3202,3204,3206,3208,3210,3212,3214,3216,3218,3220,3222,3224,3226,3228,3230,3232,3234,3236,3238,3240,3242,3244,3246,3248,3250,3252,3254,3256,3258,3260,3262,3264,3266,3268,3270,3272,3274,3276,3278,3280,3282,3284,3286,3288,3290,3292,3294,3296,3298,3300,3302,3304,3306,3308,3310,3312,3314,3316,3318,3320,3322,3324,3326,3328,3330,3332,3334,3336,3338,3340,3342,3344,3346,3348,3350,3352,3354,3356,3358,3360,3362,3364,3366,3368,3370,3372,3374,3376,3378,3380,3382,3384,3386,3388,3390,3392,3394,3396,3398,3400,3402,3404,3406,3408,3410,3412,3414,3416,3418,3420,3422,3424,3426,3428,3430,3432,3434,3436,3438,3440,3442,3444,3446,3448,3450,3452,3454,3456,3458,3460,3462,3464,3466,3468,3470,3472,3474,3476,3478,3480,3482,3484,3486,3488,3490,3492,3494,3496,3498,3500,3502,3504,3506,3508,3510,3512,3514,3516,3518,3520,3522,3524,3526,3528,3530,3532,3534,3536,3538,3540,3542,3544,3546,3548,3550,3552,3554,3556,3558,3560,3562,3564,3566,3568,3570,3572,3574,3576,3578,3580,3582,3584,3586,3588,3590,3592,3594,3596,3598,3600,3602,3604,3606,3608,3610,3612,3614,3616,3618,3620,3622,3624,3626,3628,3630,3632,3634,3636,3638,3640,3642,3644,3646,3648,3650,3652,3654,3656,3658,3660,3662,3664,3666,3668,3670,3672,3674,3676,3678,3680,3682,3684,3686,3688,3690,3692,3694,3696,3698,3700,3702,3704,3706,3708,3710,3712,3714,3716,3718,3720,3722,3724,3726,3728,3730,3732,3734,3736,3738,3740,3742,3744,3746,3748,3750,3752,3754,3756,3758,3760,3762,3764,3766,3768,3770,3772,3774,3776,3778,3780,3782,3784,3786,3788,3790,3792,3794,3796,3798,3800,3802,3804,3806,3808,3810,3812,3814,3816,3818,3820,3822,3824,3826,3828,3830,3832,3834,3836,3838,3840,3842,3844,3846,3848,3850,3852,3854,3856,3858,3860,3862,3864,3866,3868,3870,3872,3874,3876,3878,3880,3882,3884,3886,3888,3890,3892,3894,3896,3898,3900,3902,3904,3906,3908,3910,3912,3914,3916,3918,3920,3922,3924,3926,3928,3930,3932,3934,3936,3938,3940,3942,3944,3946,3948,3950,3952,3954,3956,3958,3960,3962,3964,3966,3968,3970,3972,3974,3976,3978,3980,3982,3984,3986,3988,3990,3992,3994,3996,3998,4000,4002,4004,4006,4008,4010,4012,4014,4016,4018,4020,4022,4024,4026,4028,4030,4032,4034,4036,4038,4040,4042,4044,4046,4048,4050,4052,4054,4056,4058,4060,4062,4064,4066,4068,4070,4072,4074,4076,4078,4080,4082,4084,4086,4088,4090,4092,4094,4096,4098,4100,4102,4104,4106,4108,4110,4112,4114,4116,4118,4120,4122,4124,4126,4128,4130,4132,4134,4136,4138,4140,4142,4144,4146,4148,4150,4152,4154,4156,4158,4160,4162,4164,4166,4168,4170,4172,4174,4176,4178,4180,4182,4184,4186,4188,4190,4192,4194,4196,4198,4200,4202,4204,4206,4208,4210,4212,4214,4216,4218,4220,4222,4224,4226,4228,4230,4232,4234,4236,4238,4240,4242,4244,4246,4248,4250,4252,4254,4256,4258,4260,4262,4264,4266,4268,4270,4272,4274,4276,4278,4280,4282,4284,4286,4288,4290,4292,4294,4296,4298,4300,4302,4304,4306,4308,4310,4312,4314,4316,4318,4320,4322,4324,4326,4328,4330,4332,4334,4336,4338,4340,4342,4344,4346,4348,4350,4352,4354,4356,4358,4360,4362,4364,4366,4368,4370,4372,4374,4376,4378,4380,4382,4384,4386,4388,4390,4392,4394,4396,4398,4400,4402,4404,4406,4408,4410,4412,4414,4416,4418,4420,4422,4424,4426,4428,4430,4432,4434,4436,4438,4440,4442,4444,4446,4448,4450,4452,4454,4456,4458,4460,4462,4464,4466,4468,4470,4472,4474,4476,4478,4480,4482,4484,4486,4488,4490,4492,4494,4496,4498,4500,4502,4504,4506,4508,4510,4512,4514,4516,4518,4520,4522,4524,4526,4528,4530,4532,4534,4536,4538,4540,4542,4544,4546,4548,4550,4552,4554,4556,4558,4560,4562,4564,4566,4568,4570,4572,4574,4576,4578,4580,4582,4584,4586,4588,4590,4592,4594,4596,4598,4600,4602,4604,4606,4608,4610,4612,4614,4616,4618,4620,4622,4624,4626,4628,4630,4632,4634,4636,4638,4640,4642,4644,4646,4648,4650,4652,4654,4656,4658,4660,4662,4664,4666,4668,4670,4672,4674,4676,4678,4680,4682,4684,4686,4688,4690,4692,4694,4696,4698,4700,4702,4704,4706,4708,4710,4712,4714,4716,4718,4720,4722,4724,4726,4728,4730,4732,4734,4736,4738,4740,4742,4744,4746,4748,4750,4752,4754,4756,4758,4760,4762,4764,4766,4768,4770,4772,4774,4776,4778,4780,4782,4784,4786,4788,4790,4792,4794,4796,4798,4800,4802,4804,4806,4808,4810,4812,4814,4816,4818,4820,4822,4824,4826,4828,4830,4832,4834,4836,4838,4840,4842,4844,4846,4848,4850,4852,4854,4856,4858,4860,4862,4864,4866,4868,4870,4872,4874,4876,4878,4880,4882,4884,4886,4888,4890,4892,4894,4896,4898,4900,4902,4904,4906,4908,4910,4912,4914,4916,4918,4920,4922,4924,4926,4928,4930,4932,4934,4936,4938,4940,4942,4944,4946,4948,4950,4952,4954,4956,4958,4960,4962],{"categories":87},[88],"Developer Productivity",{"categories":90},[91],"Business & SaaS",{"categories":93},[47],{"categories":95},[96],"AI Automation",{"categories":98},[99],"Product Strategy",{"categories":101},[47],{"categories":103},[88],{"categories":105},[47],{"categories":107},[91],{"categories":109},[],{"categories":111},[47],{"categories":113},[96],{"categories":115},[],{"categories":117},[118],"AI News & Trends",{"categories":120},[96],{"categories":122},[47],{"categories":124},[96],{"categories":126},[118],{"categories":128},[96],{"categories":130},[96],{"categories":132},[47],{"categories":134},[96],{"categories":136},[47],{"categories":138},[47],{"categories":140},[47],{"categories":142},[118],{"categories":144},[47],{"categories":146},[47],{"categories":148},[],{"categories":150},[151],"Design & Frontend",{"categories":153},[154],"Data Science & Visualization",{"categories":156},[118],{"categories":158},[47],{"categories":160},[],{"categories":162},[47],{"categories":164},[96],{"categories":166},[167],"Software Engineering",{"categories":169},[47],{"categories":171},[96],{"categories":173},[47],{"categories":175},[176],"Marketing & Growth",{"categories":178},[151],{"categories":180},[47],{"categories":182},[96],{"categories":184},[47],{"categories":186},[],{"categories":188},[],{"categories":190},[151],{"categories":192},[96],{"categories":194},[88],{"categories":196},[167],{"categories":198},[151],{"categories":200},[47],{"categories":202},[167],{"categories":204},[205],"DevOps & Cloud",{"categories":207},[96],{"categories":209},[99],{"categories":211},[118],{"categories":213},[47],{"categories":215},[],{"categories":217},[47],{"categories":219},[],{"categories":221},[96],{"categories":223},[167],{"categories":225},[],{"categories":227},[91],{"categories":229},[],{"categories":231},[],{"categories":233},[47],{"categories":235},[96],{"categories":237},[47],{"categories":239},[47],{"categories":241},[96],{"categories":243},[47],{"categories":245},[47],{"categories":247},[47],{"categories":249},[],{"categories":251},[167],{"categories":253},[],{"categories":255},[],{"categories":257},[167],{"categories":259},[],{"categories":261},[167],{"categories":263},[47],{"categories":265},[47],{"categories":267},[176],{"categories":269},[151],{"categories":271},[151],{"categories":273},[47],{"categories":275},[167],{"categories":277},[96],{"categories":279},[167],{"categories":281},[47],{"categories":283},[47],{"categories":285},[96],{"categories":287},[96],{"categories":289},[154],{"categories":291},[118],{"categories":293},[96],{"categories":295},[96],{"categories":297},[176],{"categories":299},[96],{"categories":301},[99],{"categories":303},[167],{"categories":305},[],{"categories":307},[96],{"categories":309},[],{"categories":311},[96],{"categories":313},[47],{"categories":315},[167],{"categories":317},[205],{"categories":319},[151],{"categories":321},[47],{"categories":323},[],{"categories":325},[167],{"categories":327},[47],{"categories":329},[],{"categories":331},[96],{"categories":333},[],{"categories":335},[47],{"categories":337},[],{"categories":339},[88],{"categories":341},[167],{"categories":343},[91],{"categories":345},[47],{"categories":347},[47],{"categories":349},[118],{"categories":351},[47],{"categories":353},[],{"categories":355},[47],{"categories":357},[],{"categories":359},[167],{"categories":361},[154],{"categories":363},[],{"categories":365},[47],{"categories":367},[151],{"categories":369},[],{"categories":371},[151],{"categories":373},[96],{"categories":375},[],{"categories":377},[47],{"categories":379},[47],{"categories":381},[96],{"categories":383},[118],{"categories":385},[91],{"categories":387},[47],{"categories":389},[],{"categories":391},[167],{"categories":393},[96],{"categories":395},[47],{"categories":397},[99],{"categories":399},[],{"categories":401},[47],{"categories":403},[99],{"categories":405},[96],{"categories":407},[47],{"categories":409},[96],{"categories":411},[],{"categories":413},[154],{"categories":415},[47],{"categories":417},[],{"categories":419},[88],{"categories":421},[47],{"categories":423},[91],{"categories":425},[47],{"categories":427},[96],{"categories":429},[47],{"categories":431},[47],{"categories":433},[167],{"categories":435},[47],{"categories":437},[],{"categories":439},[],{"categories":441},[47],{"categories":443},[47],{"categories":445},[],{"categories":447},[151],{"categories":449},[],{"categories":451},[47],{"categories":453},[],{"categories":455},[96],{"categories":457},[47],{"categories":459},[151],{"categories":461},[],{"categories":463},[47],{"categories":465},[96],{"categories":467},[47],{"categories":469},[91],{"categories":471},[96],{"categories":473},[47],{"categories":475},[47],{"categories":477},[151],{"categories":479},[96],{"categories":481},[],{"categories":483},[167],{"categories":485},[96],{"categories":487},[],{"categories":489},[118],{"categories":491},[],{"categories":493},[47],{"categories":495},[47],{"categories":497},[91,176],{"categories":499},[],{"categories":501},[47],{"categories":503},[47],{"categories":505},[96],{"categories":507},[],{"categories":509},[],{"categories":511},[47],{"categories":513},[151],{"categories":515},[47],{"categories":517},[],{"categories":519},[47],{"categories":521},[205],{"categories":523},[],{"categories":525},[118],{"categories":527},[151],{"categories":529},[],{"categories":531},[118],{"categories":533},[47],{"categories":535},[96],{"categories":537},[118],{"categories":539},[47],{"categories":541},[176],{"categories":543},[],{"categories":545},[96],{"categories":547},[91],{"categories":549},[167],{"categories":551},[47],{"categories":553},[96],{"categories":555},[],{"categories":557},[47,205],{"categories":559},[47],{"categories":561},[47],{"categories":563},[47],{"categories":565},[96],{"categories":567},[47,167],{"categories":569},[154],{"categories":571},[47],{"categories":573},[47],{"categories":575},[167],{"categories":577},[96],{"categories":579},[176],{"categories":581},[96],{"categories":583},[47],{"categories":585},[47],{"categories":587},[96],{"categories":589},[],{"categories":591},[96],{"categories":593},[47],{"categories":595},[47,91],{"categories":597},[91],{"categories":599},[],{"categories":601},[151],{"categories":603},[151],{"categories":605},[47],{"categories":607},[],{"categories":609},[],{"categories":611},[118],{"categories":613},[],{"categories":615},[88],{"categories":617},[47],{"categories":619},[167],{"categories":621},[47],{"categories":623},[151],{"categories":625},[47],{"categories":627},[96],{"categories":629},[167],{"categories":631},[118],{"categories":633},[151],{"categories":635},[],{"categories":637},[47],{"categories":639},[47],{"categories":641},[47],{"categories":643},[47],{"categories":645},[47],{"categories":647},[47],{"categories":649},[118],{"categories":651},[88],{"categories":653},[47],{"categories":655},[96],{"categories":657},[205],{"categories":659},[151],{"categories":661},[47],{"categories":663},[96],{"categories":665},[],{"categories":667},[],{"categories":669},[151],{"categories":671},[118],{"categories":673},[154],{"categories":675},[],{"categories":677},[47],{"categories":679},[47],{"categories":681},[91],{"categories":683},[47],{"categories":685},[47],{"categories":687},[47],{"categories":689},[118],{"categories":691},[151],{"categories":693},[],{"categories":695},[96],{"categories":697},[167],{"categories":699},[],{"categories":701},[47],{"categories":703},[47],{"categories":705},[96],{"categories":707},[167],{"categories":709},[47],{"categories":711},[154],{"categories":713},[],{"categories":715},[],{"categories":717},[47],{"categories":719},[],{"categories":721},[99],{"categories":723},[91],{"categories":725},[96],{"categories":727},[96],{"categories":729},[],{"categories":731},[88],{"categories":733},[47],{"categories":735},[91],{"categories":737},[118],{"categories":739},[88],{"categories":741},[],{"categories":743},[47],{"categories":745},[],{"categories":747},[],{"categories":749},[118],{"categories":751},[118],{"categories":753},[],{"categories":755},[151],{"categories":757},[167],{"categories":759},[],{"categories":761},[91],{"categories":763},[],{"categories":765},[],{"categories":767},[88],{"categories":769},[154],{"categories":771},[],{"categories":773},[176],{"categories":775},[96],{"categories":777},[91],{"categories":779},[96],{"categories":781},[167],{"categories":783},[],{"categories":785},[99],{"categories":787},[47],{"categories":789},[151],{"categories":791},[167],{"categories":793},[47],{"categories":795},[96],{"categories":797},[91],{"categories":799},[47],{"categories":801},[],{"categories":803},[],{"categories":805},[167],{"categories":807},[154],{"categories":809},[99],{"categories":811},[47],{"categories":813},[96],{"categories":815},[47],{"categories":817},[],{"categories":819},[118],{"categories":821},[205],{"categories":823},[],{"categories":825},[96],{"categories":827},[],{"categories":829},[88],{"categories":831},[],{"categories":833},[47],{"categories":835},[47],{"categories":837},[151],{"categories":839},[176],{"categories":841},[167],{"categories":843},[96],{"categories":845},[],{"categories":847},[167],{"categories":849},[88],{"categories":851},[],{"categories":853},[118],{"categories":855},[47,205],{"categories":857},[47],{"categories":859},[118],{"categories":861},[47],{"categories":863},[47],{"categories":865},[91],{"categories":867},[47],{"categories":869},[],{"categories":871},[47],{"categories":873},[91],{"categories":875},[47],{"categories":877},[],{"categories":879},[96],{"categories":881},[167],{"categories":883},[151],{"categories":885},[118],{"categories":887},[154],{"categories":889},[47],{"categories":891},[88],{"categories":893},[47],{"categories":895},[96],{"categories":897},[47],{"categories":899},[167],{"categories":901},[167],{"categories":903},[],{"categories":905},[],{"categories":907},[96],{"categories":909},[99],{"categories":911},[],{"categories":913},[47],{"categories":915},[],{"categories":917},[151],{"categories":919},[96],{"categories":921},[167],{"categories":923},[151],{"categories":925},[47],{"categories":927},[151],{"categories":929},[],{"categories":931},[],{"categories":933},[118],{"categories":935},[96],{"categories":937},[96],{"categories":939},[47],{"categories":941},[47],{"categories":943},[47],{"categories":945},[91],{"categories":947},[47],{"categories":949},[47],{"categories":951},[],{"categories":953},[167],{"categories":955},[167],{"categories":957},[47],{"categories":959},[167],{"categories":961},[91],{"categories":963},[],{"categories":965},[47],{"categories":967},[47],{"categories":969},[96],{"categories":971},[88],{"categories":973},[91],{"categories":975},[118],{"categories":977},[96],{"categories":979},[176],{"categories":981},[47],{"categories":983},[96],{"categories":985},[],{"categories":987},[151],{"categories":989},[],{"categories":991},[47],{"categories":993},[47],{"categories":995},[],{"categories":997},[167],{"categories":999},[91],{"categories":1001},[96],{"categories":1003},[],{"categories":1005},[47],{"categories":1007},[47],{"categories":1009},[205],{"categories":1011},[154],{"categories":1013},[167],{"categories":1015},[176],{"categories":1017},[47],{"categories":1019},[151],{"categories":1021},[47],{"categories":1023},[167],{"categories":1025},[96],{"categories":1027},[],{"categories":1029},[],{"categories":1031},[96],{"categories":1033},[88],{"categories":1035},[96],{"categories":1037},[99],{"categories":1039},[91],{"categories":1041},[],{"categories":1043},[47],{"categories":1045},[99],{"categories":1047},[47],{"categories":1049},[47],{"categories":1051},[47],{"categories":1053},[47],{"categories":1055},[47],{"categories":1057},[176],{"categories":1059},[47],{"categories":1061},[47],{"categories":1063},[47],{"categories":1065},[47],{"categories":1067},[151],{"categories":1069},[96],{"categories":1071},[],{"categories":1073},[],{"categories":1075},[205],{"categories":1077},[167],{"categories":1079},[],{"categories":1081},[96],{"categories":1083},[47],{"categories":1085},[151,47],{"categories":1087},[88],{"categories":1089},[],{"categories":1091},[47],{"categories":1093},[88],{"categories":1095},[151],{"categories":1097},[96],{"categories":1099},[167],{"categories":1101},[],{"categories":1103},[47],{"categories":1105},[],{"categories":1107},[],{"categories":1109},[47],{"categories":1111},[88],{"categories":1113},[47],{"categories":1115},[47],{"categories":1117},[],{"categories":1119},[96],{"categories":1121},[99],{"categories":1123},[167],{"categories":1125},[47],{"categories":1127},[47],{"categories":1129},[47],{"categories":1131},[151],{"categories":1133},[96],{"categories":1135},[205],{"categories":1137},[151],{"categories":1139},[91],{"categories":1141},[96],{"categories":1143},[47],{"categories":1145},[47],{"categories":1147},[47],{"categories":1149},[96],{"categories":1151},[167],{"categories":1153},[47],{"categories":1155},[99],{"categories":1157},[],{"categories":1159},[118],{"categories":1161},[],{"categories":1163},[99],{"categories":1165},[96],{"categories":1167},[151],{"categories":1169},[47],{"categories":1171},[47],{"categories":1173},[96],{"categories":1175},[167],{"categories":1177},[151],{"categories":1179},[96],{"categories":1181},[118],{"categories":1183},[],{"categories":1185},[47],{"categories":1187},[],{"categories":1189},[47],{"categories":1191},[47],{"categories":1193},[151],{"categories":1195},[47],{"categories":1197},[88],{"categories":1199},[118],{"categories":1201},[47],{"categories":1203},[47],{"categories":1205},[176],{"categories":1207},[47],{"categories":1209},[47],{"categories":1211},[96],{"categories":1213},[96],{"categories":1215},[47],{"categories":1217},[47],{"categories":1219},[96],{"categories":1221},[96],{"categories":1223},[47],{"categories":1225},[47],{"categories":1227},[96],{"categories":1229},[151],{"categories":1231},[47],{"categories":1233},[47],{"categories":1235},[],{"categories":1237},[],{"categories":1239},[167],{"categories":1241},[],{"categories":1243},[88],{"categories":1245},[205],{"categories":1247},[47],{"categories":1249},[],{"categories":1251},[88],{"categories":1253},[91],{"categories":1255},[47],{"categories":1257},[176],{"categories":1259},[],{"categories":1261},[91],{"categories":1263},[91],{"categories":1265},[],{"categories":1267},[47],{"categories":1269},[167],{"categories":1271},[],{"categories":1273},[],{"categories":1275},[],{"categories":1277},[],{"categories":1279},[47],{"categories":1281},[96],{"categories":1283},[205],{"categories":1285},[47],{"categories":1287},[88],{"categories":1289},[167],{"categories":1291},[47],{"categories":1293},[47],{"categories":1295},[167],{"categories":1297},[99],{"categories":1299},[47],{"categories":1301},[176],{"categories":1303},[167],{"categories":1305},[91],{"categories":1307},[47],{"categories":1309},[47],{"categories":1311},[47],{"categories":1313},[47],{"categories":1315},[96],{"categories":1317},[47,88],{"categories":1319},[167],{"categories":1321},[167],{"categories":1323},[151],{"categories":1325},[96],{"categories":1327},[167],{"categories":1329},[47],{"categories":1331},[47],{"categories":1333},[],{"categories":1335},[],{"categories":1337},[47],{"categories":1339},[],{"categories":1341},[47],{"categories":1343},[167],{"categories":1345},[154],{"categories":1347},[118],{"categories":1349},[151],{"categories":1351},[47],{"categories":1353},[167],{"categories":1355},[],{"categories":1357},[96],{"categories":1359},[47],{"categories":1361},[47],{"categories":1363},[47],{"categories":1365},[47],{"categories":1367},[],{"categories":1369},[96],{"categories":1371},[47],{"categories":1373},[47],{"categories":1375},[],{"categories":1377},[96],{"categories":1379},[47],{"categories":1381},[91],{"categories":1383},[],{"categories":1385},[88],{"categories":1387},[47],{"categories":1389},[151],{"categories":1391},[47],{"categories":1393},[88],{"categories":1395},[47],{"categories":1397},[167],{"categories":1399},[176],{"categories":1401},[96],{"categories":1403},[96],{"categories":1405},[47,151],{"categories":1407},[118],{"categories":1409},[47],{"categories":1411},[151],{"categories":1413},[],{"categories":1415},[167],{"categories":1417},[205],{"categories":1419},[151],{"categories":1421},[167],{"categories":1423},[47],{"categories":1425},[99],{"categories":1427},[47],{"categories":1429},[96],{"categories":1431},[],{"categories":1433},[],{"categories":1435},[],{"categories":1437},[],{"categories":1439},[167],{"categories":1441},[47],{"categories":1443},[96],{"categories":1445},[91],{"categories":1447},[96],{"categories":1449},[205],{"categories":1451},[47],{"categories":1453},[47],{"categories":1455},[47],{"categories":1457},[96],{"categories":1459},[47],{"categories":1461},[47],{"categories":1463},[],{"categories":1465},[151],{"categories":1467},[167],{"categories":1469},[],{"categories":1471},[],{"categories":1473},[96],{"categories":1475},[],{"categories":1477},[],{"categories":1479},[176],{"categories":1481},[176],{"categories":1483},[96],{"categories":1485},[167],{"categories":1487},[],{"categories":1489},[47],{"categories":1491},[47],{"categories":1493},[167],{"categories":1495},[151],{"categories":1497},[151],{"categories":1499},[47],{"categories":1501},[96],{"categories":1503},[88],{"categories":1505},[47],{"categories":1507},[47],{"categories":1509},[151],{"categories":1511},[151],{"categories":1513},[96],{"categories":1515},[96],{"categories":1517},[47],{"categories":1519},[],{"categories":1521},[47],{"categories":1523},[],{"categories":1525},[47],{"categories":1527},[96],{"categories":1529},[118],{"categories":1531},[167],{"categories":1533},[47],{"categories":1535},[167],{"categories":1537},[88],{"categories":1539},[47],{"categories":1541},[],{"categories":1543},[96],{"categories":1545},[96],{"categories":1547},[],{"categories":1549},[47],{"categories":1551},[88],{"categories":1553},[47],{"categories":1555},[88],{"categories":1557},[88],{"categories":1559},[],{"categories":1561},[167],{"categories":1563},[],{"categories":1565},[96],{"categories":1567},[118],{"categories":1569},[47],{"categories":1571},[96],{"categories":1573},[47],{"categories":1575},[96],{"categories":1577},[47],{"categories":1579},[118],{"categories":1581},[154],{"categories":1583},[47],{"categories":1585},[99],{"categories":1587},[118],{"categories":1589},[151],{"categories":1591},[],{"categories":1593},[],{"categories":1595},[47],{"categories":1597},[47],{"categories":1599},[118],{"categories":1601},[],{"categories":1603},[],{"categories":1605},[],{"categories":1607},[96],{"categories":1609},[47],{"categories":1611},[],{"categories":1613},[167],{"categories":1615},[167],{"categories":1617},[154],{"categories":1619},[],{"categories":1621},[47],{"categories":1623},[47],{"categories":1625},[47],{"categories":1627},[154],{"categories":1629},[167],{"categories":1631},[],{"categories":1633},[],{"categories":1635},[96],{"categories":1637},[96],{"categories":1639},[167],{"categories":1641},[96],{"categories":1643},[118],{"categories":1645},[118],{"categories":1647},[96],{"categories":1649},[96],{"categories":1651},[88],{"categories":1653},[47,205],{"categories":1655},[],{"categories":1657},[151],{"categories":1659},[167],{"categories":1661},[88],{"categories":1663},[47],{"categories":1665},[96],{"categories":1667},[151],{"categories":1669},[],{"categories":1671},[96],{"categories":1673},[96],{"categories":1675},[96],{"categories":1677},[47],{"categories":1679},[176],{"categories":1681},[47],{"categories":1683},[167],{"categories":1685},[151],{"categories":1687},[47],{"categories":1689},[],{"categories":1691},[96],{"categories":1693},[151],{"categories":1695},[47],{"categories":1697},[96],{"categories":1699},[96],{"categories":1701},[96],{"categories":1703},[176],{"categories":1705},[154],{"categories":1707},[47],{"categories":1709},[96],{"categories":1711},[47],{"categories":1713},[],{"categories":1715},[176],{"categories":1717},[118],{"categories":1719},[167],{"categories":1721},[47],{"categories":1723},[96],{"categories":1725},[],{"categories":1727},[],{"categories":1729},[47],{"categories":1731},[96],{"categories":1733},[47],{"categories":1735},[96],{"categories":1737},[118],{"categories":1739},[47],{"categories":1741},[96],{"categories":1743},[96],{"categories":1745},[],{"categories":1747},[47],{"categories":1749},[],{"categories":1751},[],{"categories":1753},[47],{"categories":1755},[47],{"categories":1757},[96],{"categories":1759},[167],{"categories":1761},[],{"categories":1763},[],{"categories":1765},[154],{"categories":1767},[47],{"categories":1769},[154],{"categories":1771},[118],{"categories":1773},[47],{"categories":1775},[47],{"categories":1777},[96],{"categories":1779},[96],{"categories":1781},[47],{"categories":1783},[96],{"categories":1785},[],{"categories":1787},[],{"categories":1789},[47],{"categories":1791},[205],{"categories":1793},[47],{"categories":1795},[],{"categories":1797},[],{"categories":1799},[88],{"categories":1801},[],{"categories":1803},[],{"categories":1805},[47],{"categories":1807},[],{"categories":1809},[],{"categories":1811},[167],{"categories":1813},[118],{"categories":1815},[176],{"categories":1817},[91],{"categories":1819},[47],{"categories":1821},[47],{"categories":1823},[91],{"categories":1825},[],{"categories":1827},[151],{"categories":1829},[47],{"categories":1831},[96],{"categories":1833},[91],{"categories":1835},[47],{"categories":1837},[47],{"categories":1839},[88],{"categories":1841},[47],{"categories":1843},[],{"categories":1845},[88],{"categories":1847},[47],{"categories":1849},[176],{"categories":1851},[96],{"categories":1853},[118],{"categories":1855},[47],{"categories":1857},[91],{"categories":1859},[47],{"categories":1861},[47],{"categories":1863},[96],{"categories":1865},[],{"categories":1867},[47],{"categories":1869},[167],{"categories":1871},[88],{"categories":1873},[47],{"categories":1875},[47],{"categories":1877},[],{"categories":1879},[118],{"categories":1881},[47],{"categories":1883},[47],{"categories":1885},[],{"categories":1887},[91],{"categories":1889},[91],{"categories":1891},[47],{"categories":1893},[47],{"categories":1895},[99],{"categories":1897},[47],{"categories":1899},[47],{"categories":1901},[47],{"categories":1903},[],{"categories":1905},[167],{"categories":1907},[47],{"categories":1909},[],{"categories":1911},[],{"categories":1913},[47],{"categories":1915},[118],{"categories":1917},[],{"categories":1919},[205],{"categories":1921},[47],{"categories":1923},[47],{"categories":1925},[],{"categories":1927},[47],{"categories":1929},[167],{"categories":1931},[47],{"categories":1933},[47],{"categories":1935},[47,205],{"categories":1937},[47],{"categories":1939},[47],{"categories":1941},[151],{"categories":1943},[96],{"categories":1945},[],{"categories":1947},[96],{"categories":1949},[96],{"categories":1951},[47],{"categories":1953},[47],{"categories":1955},[47],{"categories":1957},[47],{"categories":1959},[88],{"categories":1961},[154],{"categories":1963},[88],{"categories":1965},[167],{"categories":1967},[151],{"categories":1969},[96],{"categories":1971},[47],{"categories":1973},[],{"categories":1975},[47],{"categories":1977},[118],{"categories":1979},[47],{"categories":1981},[96],{"categories":1983},[47],{"categories":1985},[47],{"categories":1987},[91],{"categories":1989},[],{"categories":1991},[205],{"categories":1993},[151],{"categories":1995},[151],{"categories":1997},[167],{"categories":1999},[96],{"categories":2001},[47],{"categories":2003},[91],{"categories":2005},[118],{"categories":2007},[151],{"categories":2009},[96],{"categories":2011},[47],{"categories":2013},[47],{"categories":2015},[],{"categories":2017},[47],{"categories":2019},[47],{"categories":2021},[47],{"categories":2023},[],{"categories":2025},[],{"categories":2027},[47],{"categories":2029},[47],{"categories":2031},[47],{"categories":2033},[167],{"categories":2035},[47],{"categories":2037},[47],{"categories":2039},[96],{"categories":2041},[47],{"categories":2043},[47],{"categories":2045},[47],{"categories":2047},[47],{"categories":2049},[],{"categories":2051},[154],{"categories":2053},[47],{"categories":2055},[96],{"categories":2057},[],{"categories":2059},[],{"categories":2061},[47],{"categories":2063},[47],{"categories":2065},[47],{"categories":2067},[118],{"categories":2069},[],{"categories":2071},[151],{"categories":2073},[47],{"categories":2075},[205],{"categories":2077},[118],{"categories":2079},[167],{"categories":2081},[167],{"categories":2083},[118],{"categories":2085},[118],{"categories":2087},[205],{"categories":2089},[],{"categories":2091},[118],{"categories":2093},[47],{"categories":2095},[88],{"categories":2097},[167],{"categories":2099},[47],{"categories":2101},[118],{"categories":2103},[],{"categories":2105},[47],{"categories":2107},[167],{"categories":2109},[154],{"categories":2111},[47],{"categories":2113},[118],{"categories":2115},[47],{"categories":2117},[167],{"categories":2119},[96],{"categories":2121},[118],{"categories":2123},[96],{"categories":2125},[205],{"categories":2127},[96],{"categories":2129},[47],{"categories":2131},[47],{"categories":2133},[167],{"categories":2135},[47],{"categories":2137},[],{"categories":2139},[91],{"categories":2141},[],{"categories":2143},[],{"categories":2145},[47],{"categories":2147},[96],{"categories":2149},[47],{"categories":2151},[47],{"categories":2153},[47],{"categories":2155},[47],{"categories":2157},[],{"categories":2159},[154],{"categories":2161},[88],{"categories":2163},[96],{"categories":2165},[151],{"categories":2167},[],{"categories":2169},[47],{"categories":2171},[167],{"categories":2173},[47],{"categories":2175},[205],{"categories":2177},[205],{"categories":2179},[],{"categories":2181},[96],{"categories":2183},[118],{"categories":2185},[118],{"categories":2187},[47],{"categories":2189},[96],{"categories":2191},[],{"categories":2193},[151],{"categories":2195},[47],{"categories":2197},[47],{"categories":2199},[],{"categories":2201},[47],{"categories":2203},[],{"categories":2205},[47],{"categories":2207},[167],{"categories":2209},[205],{"categories":2211},[47],{"categories":2213},[167],{"categories":2215},[91],{"categories":2217},[47],{"categories":2219},[],{"categories":2221},[96],{"categories":2223},[88],{"categories":2225},[88],{"categories":2227},[],{"categories":2229},[47],{"categories":2231},[47],{"categories":2233},[47],{"categories":2235},[167],{"categories":2237},[151],{"categories":2239},[47],{"categories":2241},[167],{"categories":2243},[167],{"categories":2245},[96],{"categories":2247},[],{"categories":2249},[47],{"categories":2251},[47],{"categories":2253},[96],{"categories":2255},[47],{"categories":2257},[47],{"categories":2259},[],{"categories":2261},[96],{"categories":2263},[47],{"categories":2265},[96],{"categories":2267},[96],{"categories":2269},[167],{"categories":2271},[],{"categories":2273},[47],{"categories":2275},[47],{"categories":2277},[96],{"categories":2279},[91],{"categories":2281},[47],{"categories":2283},[],{"categories":2285},[47],{"categories":2287},[],{"categories":2289},[47],{"categories":2291},[47],{"categories":2293},[],{"categories":2295},[47],{"categories":2297},[47],{"categories":2299},[118],{"categories":2301},[47],{"categories":2303},[47],{"categories":2305},[88],{"categories":2307},[47],{"categories":2309},[47],{"categories":2311},[154],{"categories":2313},[118],{"categories":2315},[96],{"categories":2317},[],{"categories":2319},[47],{"categories":2321},[151],{"categories":2323},[47],{"categories":2325},[176],{"categories":2327},[47],{"categories":2329},[96],{"categories":2331},[],{"categories":2333},[],{"categories":2335},[],{"categories":2337},[88],{"categories":2339},[118],{"categories":2341},[96],{"categories":2343},[47],{"categories":2345},[47],{"categories":2347},[47],{"categories":2349},[151],{"categories":2351},[96],{"categories":2353},[47],{"categories":2355},[],{"categories":2357},[96],{"categories":2359},[96],{"categories":2361},[],{"categories":2363},[47],{"categories":2365},[96],{"categories":2367},[47],{"categories":2369},[],{"categories":2371},[47],{"categories":2373},[47],{"categories":2375},[118],{"categories":2377},[151],{"categories":2379},[96],{"categories":2381},[151],{"categories":2383},[96],{"categories":2385},[91],{"categories":2387},[],{"categories":2389},[],{"categories":2391},[47],{"categories":2393},[88],{"categories":2395},[96],{"categories":2397},[118],{"categories":2399},[],{"categories":2401},[151],{"categories":2403},[],{"categories":2405},[167],{"categories":2407},[167],{"categories":2409},[151],{"categories":2411},[167],{"categories":2413},[47],{"categories":2415},[],{"categories":2417},[47],{"categories":2419},[47],{"categories":2421},[],{"categories":2423},[176],{"categories":2425},[47],{"categories":2427},[205],{"categories":2429},[167],{"categories":2431},[],{"categories":2433},[96],{"categories":2435},[47],{"categories":2437},[88],{"categories":2439},[96],{"categories":2441},[96],{"categories":2443},[47],{"categories":2445},[47],{"categories":2447},[],{"categories":2449},[88],{"categories":2451},[47],{"categories":2453},[91],{"categories":2455},[167],{"categories":2457},[151],{"categories":2459},[],{"categories":2461},[],{"categories":2463},[],{"categories":2465},[96],{"categories":2467},[167],{"categories":2469},[151],{"categories":2471},[118],{"categories":2473},[47],{"categories":2475},[118],{"categories":2477},[96],{"categories":2479},[151],{"categories":2481},[47],{"categories":2483},[],{"categories":2485},[47],{"categories":2487},[96],{"categories":2489},[151],{"categories":2491},[118],{"categories":2493},[91],{"categories":2495},[167],{"categories":2497},[47],{"categories":2499},[118],{"categories":2501},[176],{"categories":2503},[],{"categories":2505},[],{"categories":2507},[154],{"categories":2509},[96],{"categories":2511},[47,167],{"categories":2513},[118],{"categories":2515},[47],{"categories":2517},[47],{"categories":2519},[96],{"categories":2521},[47],{"categories":2523},[96],{"categories":2525},[47],{"categories":2527},[47],{"categories":2529},[],{"categories":2531},[167],{"categories":2533},[151],{"categories":2535},[47],{"categories":2537},[154],{"categories":2539},[96],{"categories":2541},[176],{"categories":2543},[205],{"categories":2545},[],{"categories":2547},[47],{"categories":2549},[91],{"categories":2551},[96],{"categories":2553},[88],{"categories":2555},[96],{"categories":2557},[47],{"categories":2559},[96],{"categories":2561},[99],{"categories":2563},[167],{"categories":2565},[47],{"categories":2567},[47],{"categories":2569},[],{"categories":2571},[],{"categories":2573},[],{"categories":2575},[205],{"categories":2577},[47],{"categories":2579},[118],{"categories":2581},[47],{"categories":2583},[47],{"categories":2585},[47],{"categories":2587},[],{"categories":2589},[154],{"categories":2591},[91],{"categories":2593},[96],{"categories":2595},[47],{"categories":2597},[],{"categories":2599},[47],{"categories":2601},[96],{"categories":2603},[47],{"categories":2605},[205],{"categories":2607},[],{"categories":2609},[151],{"categories":2611},[151],{"categories":2613},[],{"categories":2615},[167],{"categories":2617},[47],{"categories":2619},[151],{"categories":2621},[47],{"categories":2623},[91],{"categories":2625},[96],{"categories":2627},[47],{"categories":2629},[],{"categories":2631},[118],{"categories":2633},[47],{"categories":2635},[47],{"categories":2637},[151],{"categories":2639},[96],{"categories":2641},[118],{"categories":2643},[],{"categories":2645},[96],{"categories":2647},[96],{"categories":2649},[151],{"categories":2651},[47],{"categories":2653},[47],{"categories":2655},[],{"categories":2657},[47],{"categories":2659},[47],{"categories":2661},[205],{"categories":2663},[118],{"categories":2665},[154],{"categories":2667},[154],{"categories":2669},[],{"categories":2671},[],{"categories":2673},[],{"categories":2675},[96],{"categories":2677},[96],{"categories":2679},[167],{"categories":2681},[167],{"categories":2683},[47],{"categories":2685},[47],{"categories":2687},[47],{"categories":2689},[47],{"categories":2691},[96],{"categories":2693},[],{"categories":2695},[],{"categories":2697},[47],{"categories":2699},[],{"categories":2701},[47],{"categories":2703},[96],{"categories":2705},[151],{"categories":2707},[47],{"categories":2709},[47],{"categories":2711},[],{"categories":2713},[99],{"categories":2715},[47],{"categories":2717},[151],{"categories":2719},[47],{"categories":2721},[91],{"categories":2723},[47],{"categories":2725},[176],{"categories":2727},[96],{"categories":2729},[47],{"categories":2731},[47],{"categories":2733},[96],{"categories":2735},[47],{"categories":2737},[167],{"categories":2739},[151],{"categories":2741},[],{"categories":2743},[118],{"categories":2745},[96],{"categories":2747},[47],{"categories":2749},[],{"categories":2751},[118],{"categories":2753},[96],{"categories":2755},[96],{"categories":2757},[47],{"categories":2759},[96],{"categories":2761},[],{"categories":2763},[91],{"categories":2765},[96],{"categories":2767},[],{"categories":2769},[167],{"categories":2771},[47],{"categories":2773},[88],{"categories":2775},[118],{"categories":2777},[205],{"categories":2779},[96],{"categories":2781},[47],{"categories":2783},[96],{"categories":2785},[88],{"categories":2787},[],{"categories":2789},[47],{"categories":2791},[],{"categories":2793},[],{"categories":2795},[151],{"categories":2797},[47,91],{"categories":2799},[96],{"categories":2801},[47],{"categories":2803},[],{"categories":2805},[88],{"categories":2807},[154],{"categories":2809},[91],{"categories":2811},[47],{"categories":2813},[167],{"categories":2815},[47],{"categories":2817},[96],{"categories":2819},[47],{"categories":2821},[47],{"categories":2823},[47],{"categories":2825},[118],{"categories":2827},[96],{"categories":2829},[47],{"categories":2831},[],{"categories":2833},[],{"categories":2835},[96],{"categories":2837},[47],{"categories":2839},[205],{"categories":2841},[],{"categories":2843},[47],{"categories":2845},[96],{"categories":2847},[96],{"categories":2849},[],{"categories":2851},[96],{"categories":2853},[47],{"categories":2855},[176],{"categories":2857},[47],{"categories":2859},[154],{"categories":2861},[96],{"categories":2863},[47],{"categories":2865},[205],{"categories":2867},[],{"categories":2869},[47],{"categories":2871},[176],{"categories":2873},[151],{"categories":2875},[47],{"categories":2877},[47],{"categories":2879},[],{"categories":2881},[176],{"categories":2883},[118],{"categories":2885},[47],{"categories":2887},[47],{"categories":2889},[88],{"categories":2891},[47],{"categories":2893},[],{"categories":2895},[],{"categories":2897},[151],{"categories":2899},[47],{"categories":2901},[154],{"categories":2903},[176],{"categories":2905},[96],{"categories":2907},[176],{"categories":2909},[118],{"categories":2911},[],{"categories":2913},[47],{"categories":2915},[],{"categories":2917},[47],{"categories":2919},[96],{"categories":2921},[47],{"categories":2923},[47],{"categories":2925},[],{"categories":2927},[47,167],{"categories":2929},[118],{"categories":2931},[96],{"categories":2933},[167],{"categories":2935},[47],{"categories":2937},[88],{"categories":2939},[],{"categories":2941},[],{"categories":2943},[96],{"categories":2945},[47],{"categories":2947},[167],{"categories":2949},[88],{"categories":2951},[167],{"categories":2953},[167],{"categories":2955},[47],{"categories":2957},[176],{"categories":2959},[47],{"categories":2961},[167],{"categories":2963},[],{"categories":2965},[151,47],{"categories":2967},[205],{"categories":2969},[88],{"categories":2971},[],{"categories":2973},[47],{"categories":2975},[91],{"categories":2977},[91],{"categories":2979},[47],{"categories":2981},[47],{"categories":2983},[47],{"categories":2985},[167],{"categories":2987},[96],{"categories":2989},[47],{"categories":2991},[118],{"categories":2993},[176],{"categories":2995},[151],{"categories":2997},[47],{"categories":2999},[47],{"categories":3001},[47],{"categories":3003},[47],{"categories":3005},[88],{"categories":3007},[47],{"categories":3009},[96],{"categories":3011},[96],{"categories":3013},[167],{"categories":3015},[118],{"categories":3017},[167],{"categories":3019},[],{"categories":3021},[],{"categories":3023},[154],{"categories":3025},[47],{"categories":3027},[167],{"categories":3029},[47],{"categories":3031},[151],{"categories":3033},[47],{"categories":3035},[47],{"categories":3037},[47],{"categories":3039},[154],{"categories":3041},[47],{"categories":3043},[47],{"categories":3045},[47],{"categories":3047},[96],{"categories":3049},[96],{"categories":3051},[47,91],{"categories":3053},[],{"categories":3055},[151],{"categories":3057},[],{"categories":3059},[99],{"categories":3061},[47],{"categories":3063},[118],{"categories":3065},[88],{"categories":3067},[88],{"categories":3069},[96],{"categories":3071},[96],{"categories":3073},[96],{"categories":3075},[47],{"categories":3077},[47],{"categories":3079},[91],{"categories":3081},[167],{"categories":3083},[176],{"categories":3085},[47],{"categories":3087},[],{"categories":3089},[118],{"categories":3091},[47],{"categories":3093},[47],{"categories":3095},[47],{"categories":3097},[47],{"categories":3099},[47],{"categories":3101},[167],{"categories":3103},[118],{"categories":3105},[167],{"categories":3107},[167],{"categories":3109},[47],{"categories":3111},[47],{"categories":3113},[47],{"categories":3115},[96],{"categories":3117},[118],{"categories":3119},[47],{"categories":3121},[96],{"categories":3123},[47],{"categories":3125},[47],{"categories":3127},[47],{"categories":3129},[151],{"categories":3131},[47],{"categories":3133},[47],{"categories":3135},[47],{"categories":3137},[205],{"categories":3139},[47],{"categories":3141},[99],{"categories":3143},[96],{"categories":3145},[47],{"categories":3147},[47],{"categories":3149},[118],{"categories":3151},[47],{"categories":3153},[96],{"categories":3155},[176],{"categories":3157},[47],{"categories":3159},[47],{"categories":3161},[91],{"categories":3163},[47],{"categories":3165},[],{"categories":3167},[47],{"categories":3169},[167],{"categories":3171},[47],{"categories":3173},[],{"categories":3175},[],{"categories":3177},[],{"categories":3179},[91],{"categories":3181},[47],{"categories":3183},[96],{"categories":3185},[118],{"categories":3187},[118],{"categories":3189},[118],{"categories":3191},[118],{"categories":3193},[],{"categories":3195},[88],{"categories":3197},[96],{"categories":3199},[118],{"categories":3201},[47],{"categories":3203},[88],{"categories":3205},[96],{"categories":3207},[47],{"categories":3209},[47,96],{"categories":3211},[96],{"categories":3213},[205],{"categories":3215},[118],{"categories":3217},[96],{"categories":3219},[118],{"categories":3221},[96],{"categories":3223},[47],{"categories":3225},[],{"categories":3227},[118],{"categories":3229},[176],{"categories":3231},[88],{"categories":3233},[47],{"categories":3235},[47],{"categories":3237},[],{"categories":3239},[167],{"categories":3241},[],{"categories":3243},[88],{"categories":3245},[96],{"categories":3247},[118],{"categories":3249},[47],{"categories":3251},[118],{"categories":3253},[88],{"categories":3255},[118],{"categories":3257},[118],{"categories":3259},[],{"categories":3261},[91],{"categories":3263},[96],{"categories":3265},[118],{"categories":3267},[118],{"categories":3269},[118],{"categories":3271},[118],{"categories":3273},[118],{"categories":3275},[118],{"categories":3277},[118],{"categories":3279},[118],{"categories":3281},[118],{"categories":3283},[118],{"categories":3285},[154],{"categories":3287},[88],{"categories":3289},[47],{"categories":3291},[47],{"categories":3293},[96],{"categories":3295},[96],{"categories":3297},[],{"categories":3299},[47,88],{"categories":3301},[],{"categories":3303},[96],{"categories":3305},[118],{"categories":3307},[96],{"categories":3309},[47],{"categories":3311},[47],{"categories":3313},[47],{"categories":3315},[47],{"categories":3317},[47],{"categories":3319},[96],{"categories":3321},[91],{"categories":3323},[96],{"categories":3325},[],{"categories":3327},[151],{"categories":3329},[118],{"categories":3331},[47],{"categories":3333},[],{"categories":3335},[],{"categories":3337},[96],{"categories":3339},[151],{"categories":3341},[47],{"categories":3343},[],{"categories":3345},[47],{"categories":3347},[],{"categories":3349},[176],{"categories":3351},[47],{"categories":3353},[],{"categories":3355},[],{"categories":3357},[118],{"categories":3359},[88],{"categories":3361},[47],{"categories":3363},[91],{"categories":3365},[47],{"categories":3367},[47],{"categories":3369},[47],{"categories":3371},[91],{"categories":3373},[151],{"categories":3375},[],{"categories":3377},[47],{"categories":3379},[118],{"categories":3381},[],{"categories":3383},[151],{"categories":3385},[47],{"categories":3387},[176],{"categories":3389},[47],{"categories":3391},[205],{"categories":3393},[],{"categories":3395},[176],{"categories":3397},[167],{"categories":3399},[],{"categories":3401},[47],{"categories":3403},[],{"categories":3405},[96],{"categories":3407},[167],{"categories":3409},[],{"categories":3411},[91],{"categories":3413},[88],{"categories":3415},[154],{"categories":3417},[96],{"categories":3419},[151],{"categories":3421},[167],{"categories":3423},[],{"categories":3425},[],{"categories":3427},[47],{"categories":3429},[88],{"categories":3431},[47],{"categories":3433},[176],{"categories":3435},[],{"categories":3437},[96],{"categories":3439},[96],{"categories":3441},[96],{"categories":3443},[118],{"categories":3445},[167],{"categories":3447},[47],{"categories":3449},[96],{"categories":3451},[99],{"categories":3453},[47],{"categories":3455},[96],{"categories":3457},[47],{"categories":3459},[99],{"categories":3461},[176],{"categories":3463},[118],{"categories":3465},[],{"categories":3467},[176],{"categories":3469},[],{"categories":3471},[167],{"categories":3473},[96],{"categories":3475},[],{"categories":3477},[47],{"categories":3479},[47],{"categories":3481},[47],{"categories":3483},[47],{"categories":3485},[96],{"categories":3487},[91],{"categories":3489},[88],{"categories":3491},[47],{"categories":3493},[151],{"categories":3495},[167],{"categories":3497},[167],{"categories":3499},[47],{"categories":3501},[154],{"categories":3503},[96],{"categories":3505},[47],{"categories":3507},[96],{"categories":3509},[47],{"categories":3511},[91],{"categories":3513},[151],{"categories":3515},[167],{"categories":3517},[96],{"categories":3519},[47],{"categories":3521},[47],{"categories":3523},[96],{"categories":3525},[47],{"categories":3527},[118],{"categories":3529},[],{"categories":3531},[88],{"categories":3533},[47],{"categories":3535},[47],{"categories":3537},[47],{"categories":3539},[47],{"categories":3541},[96],{"categories":3543},[47],{"categories":3545},[47],{"categories":3547},[47],{"categories":3549},[47],{"categories":3551},[],{"categories":3553},[47],{"categories":3555},[151],{"categories":3557},[91],{"categories":3559},[118],{"categories":3561},[96],{"categories":3563},[47],{"categories":3565},[47],{"categories":3567},[151],{"categories":3569},[96],{"categories":3571},[47],{"categories":3573},[176],{"categories":3575},[47],{"categories":3577},[154],{"categories":3579},[47],{"categories":3581},[47],{"categories":3583},[118],{"categories":3585},[47],{"categories":3587},[47],{"categories":3589},[96],{"categories":3591},[205],{"categories":3593},[47],{"categories":3595},[96],{"categories":3597},[154],{"categories":3599},[],{"categories":3601},[96],{"categories":3603},[167],{"categories":3605},[47],{"categories":3607},[151],{"categories":3609},[47],{"categories":3611},[88],{"categories":3613},[167],{"categories":3615},[91],{"categories":3617},[167],{"categories":3619},[47],{"categories":3621},[],{"categories":3623},[96],{"categories":3625},[96],{"categories":3627},[47],{"categories":3629},[47],{"categories":3631},[154],{"categories":3633},[],{"categories":3635},[118],{"categories":3637},[],{"categories":3639},[118],{"categories":3641},[47],{"categories":3643},[47],{"categories":3645},[96],{"categories":3647},[96],{"categories":3649},[96],{"categories":3651},[],{"categories":3653},[118],{"categories":3655},[47],{"categories":3657},[],{"categories":3659},[47],{"categories":3661},[47],{"categories":3663},[],{"categories":3665},[151],{"categories":3667},[167],{"categories":3669},[96],{"categories":3671},[47],{"categories":3673},[47],{"categories":3675},[176],{"categories":3677},[47],{"categories":3679},[47],{"categories":3681},[88],{"categories":3683},[],{"categories":3685},[47],{"categories":3687},[],{"categories":3689},[88],{"categories":3691},[118],{"categories":3693},[167],{"categories":3695},[47],{"categories":3697},[47],{"categories":3699},[47],{"categories":3701},[167],{"categories":3703},[118],{"categories":3705},[151],{"categories":3707},[47],{"categories":3709},[47],{"categories":3711},[47],{"categories":3713},[118],{"categories":3715},[151],{"categories":3717},[47],{"categories":3719},[118],{"categories":3721},[151],{"categories":3723},[47],{"categories":3725},[118],{"categories":3727},[96],{"categories":3729},[96],{"categories":3731},[96],{"categories":3733},[167],{"categories":3735},[118],{"categories":3737},[96],{"categories":3739},[96],{"categories":3741},[47],{"categories":3743},[167],{"categories":3745},[151],{"categories":3747},[47],{"categories":3749},[],{"categories":3751},[96],{"categories":3753},[],{"categories":3755},[],{"categories":3757},[],{"categories":3759},[91],{"categories":3761},[96],{"categories":3763},[47],{"categories":3765},[96],{"categories":3767},[88],{"categories":3769},[96],{"categories":3771},[176],{"categories":3773},[96],{"categories":3775},[],{"categories":3777},[96],{"categories":3779},[],{"categories":3781},[88],{"categories":3783},[96],{"categories":3785},[],{"categories":3787},[96],{"categories":3789},[47],{"categories":3791},[47],{"categories":3793},[118],{"categories":3795},[47],{"categories":3797},[47],{"categories":3799},[96],{"categories":3801},[47],{"categories":3803},[47],{"categories":3805},[118],{"categories":3807},[96],{"categories":3809},[167],{"categories":3811},[151],{"categories":3813},[88],{"categories":3815},[47],{"categories":3817},[],{"categories":3819},[96],{"categories":3821},[151],{"categories":3823},[205],{"categories":3825},[118],{"categories":3827},[47],{"categories":3829},[151],{"categories":3831},[47],{"categories":3833},[88],{"categories":3835},[],{"categories":3837},[96],{"categories":3839},[47],{"categories":3841},[47],{"categories":3843},[96],{"categories":3845},[47],{"categories":3847},[151],{"categories":3849},[],{"categories":3851},[96],{"categories":3853},[99],{"categories":3855},[118],{"categories":3857},[96],{"categories":3859},[91],{"categories":3861},[],{"categories":3863},[47],{"categories":3865},[99],{"categories":3867},[47],{"categories":3869},[96],{"categories":3871},[118],{"categories":3873},[88],{"categories":3875},[205],{"categories":3877},[47],{"categories":3879},[47],{"categories":3881},[47],{"categories":3883},[118],{"categories":3885},[91],{"categories":3887},[47],{"categories":3889},[151],{"categories":3891},[118],{"categories":3893},[205],{"categories":3895},[47],{"categories":3897},[],{"categories":3899},[],{"categories":3901},[47],{"categories":3903},[205],{"categories":3905},[154],{"categories":3907},[96],{"categories":3909},[96],{"categories":3911},[118],{"categories":3913},[47],{"categories":3915},[88],{"categories":3917},[47],{"categories":3919},[151],{"categories":3921},[96],{"categories":3923},[96],{"categories":3925},[47],{"categories":3927},[176],{"categories":3929},[47],{"categories":3931},[96],{"categories":3933},[],{"categories":3935},[47],{"categories":3937},[47],{"categories":3939},[47],{"categories":3941},[118],{"categories":3943},[88],{"categories":3945},[],{"categories":3947},[47],{"categories":3949},[47],{"categories":3951},[167],{"categories":3953},[151],{"categories":3955},[47],{"categories":3957},[47,96],{"categories":3959},[176,91],{"categories":3961},[47],{"categories":3963},[47],{"categories":3965},[47],{"categories":3967},[],{"categories":3969},[96],{"categories":3971},[],{"categories":3973},[167],{"categories":3975},[47],{"categories":3977},[167],{"categories":3979},[],{"categories":3981},[47],{"categories":3983},[118],{"categories":3985},[47],{"categories":3987},[],{"categories":3989},[96],{"categories":3991},[47],{"categories":3993},[],{"categories":3995},[151],{"categories":3997},[47],{"categories":3999},[96],{"categories":4001},[47],{"categories":4003},[88],{"categories":4005},[96],{"categories":4007},[47],{"categories":4009},[],{"categories":4011},[205],{"categories":4013},[176],{"categories":4015},[91],{"categories":4017},[91],{"categories":4019},[47],{"categories":4021},[88],{"categories":4023},[88],{"categories":4025},[47],{"categories":4027},[96],{"categories":4029},[47],{"categories":4031},[47],{"categories":4033},[47],{"categories":4035},[167],{"categories":4037},[88],{"categories":4039},[47],{"categories":4041},[176],{"categories":4043},[118],{"categories":4045},[47],{"categories":4047},[47],{"categories":4049},[96],{"categories":4051},[47],{"categories":4053},[],{"categories":4055},[167],{"categories":4057},[],{"categories":4059},[167],{"categories":4061},[96],{"categories":4063},[88],{"categories":4065},[],{"categories":4067},[154],{"categories":4069},[205],{"categories":4071},[47],{"categories":4073},[167],{"categories":4075},[],{"categories":4077},[118],{"categories":4079},[96],{"categories":4081},[167],{"categories":4083},[151],{"categories":4085},[47],{"categories":4087},[96],{"categories":4089},[167],{"categories":4091},[96],{"categories":4093},[118],{"categories":4095},[88],{"categories":4097},[118],{"categories":4099},[167],{"categories":4101},[47],{"categories":4103},[151],{"categories":4105},[91],{"categories":4107},[47],{"categories":4109},[47],{"categories":4111},[47],{"categories":4113},[47],{"categories":4115},[47],{"categories":4117},[96],{"categories":4119},[47],{"categories":4121},[96],{"categories":4123},[47],{"categories":4125},[47],{"categories":4127},[88],{"categories":4129},[47],{"categories":4131},[96],{"categories":4133},[96],{"categories":4135},[151],{"categories":4137},[96],{"categories":4139},[96],{"categories":4141},[88],{"categories":4143},[96],{"categories":4145},[151],{"categories":4147},[],{"categories":4149},[47],{"categories":4151},[154],{"categories":4153},[47],{"categories":4155},[47],{"categories":4157},[167],{"categories":4159},[],{"categories":4161},[96],{"categories":4163},[176],{"categories":4165},[47],{"categories":4167},[118],{"categories":4169},[176],{"categories":4171},[96],{"categories":4173},[91],{"categories":4175},[91],{"categories":4177},[47],{"categories":4179},[47],{"categories":4181},[47],{"categories":4183},[88],{"categories":4185},[],{"categories":4187},[47],{"categories":4189},[96],{"categories":4191},[96],{"categories":4193},[47],{"categories":4195},[47],{"categories":4197},[167],{"categories":4199},[],{"categories":4201},[88],{"categories":4203},[47],{"categories":4205},[47],{"categories":4207},[96],{"categories":4209},[96],{"categories":4211},[],{"categories":4213},[167],{"categories":4215},[167],{"categories":4217},[176],{"categories":4219},[151],{"categories":4221},[],{"categories":4223},[47],{"categories":4225},[96],{"categories":4227},[88],{"categories":4229},[47],{"categories":4231},[167],{"categories":4233},[88],{"categories":4235},[118],{"categories":4237},[118],{"categories":4239},[],{"categories":4241},[118],{"categories":4243},[96],{"categories":4245},[151],{"categories":4247},[154],{"categories":4249},[47],{"categories":4251},[],{"categories":4253},[96],{"categories":4255},[118],{"categories":4257},[167],{"categories":4259},[47],{"categories":4261},[91],{"categories":4263},[47],{"categories":4265},[88],{"categories":4267},[205],{"categories":4269},[88],{"categories":4271},[],{"categories":4273},[],{"categories":4275},[96],{"categories":4277},[118],{"categories":4279},[],{"categories":4281},[96],{"categories":4283},[96],{"categories":4285},[96],{"categories":4287},[],{"categories":4289},[47],{"categories":4291},[],{"categories":4293},[118],{"categories":4295},[88],{"categories":4297},[151],{"categories":4299},[47],{"categories":4301},[118],{"categories":4303},[47],{"categories":4305},[118],{"categories":4307},[],{"categories":4309},[118],{"categories":4311},[88],{"categories":4313},[96],{"categories":4315},[47],{"categories":4317},[],{"categories":4319},[167],{"categories":4321},[96],{"categories":4323},[99],{"categories":4325},[96],{"categories":4327},[88],{"categories":4329},[],{"categories":4331},[],{"categories":4333},[],{"categories":4335},[151],{"categories":4337},[96],{"categories":4339},[47],{"categories":4341},[47],{"categories":4343},[],{"categories":4345},[],{"categories":4347},[],{"categories":4349},[151],{"categories":4351},[],{"categories":4353},[96],{"categories":4355},[47],{"categories":4357},[88],{"categories":4359},[],{"categories":4361},[],{"categories":4363},[151],{"categories":4365},[47],{"categories":4367},[118],{"categories":4369},[],{"categories":4371},[176],{"categories":4373},[118],{"categories":4375},[176],{"categories":4377},[154],{"categories":4379},[47],{"categories":4381},[47],{"categories":4383},[],{"categories":4385},[],{"categories":4387},[96],{"categories":4389},[],{"categories":4391},[47],{"categories":4393},[47],{"categories":4395},[],{"categories":4397},[96],{"categories":4399},[47],{"categories":4401},[47],{"categories":4403},[],{"categories":4405},[96],{"categories":4407},[47],{"categories":4409},[118],{"categories":4411},[47],{"categories":4413},[176],{"categories":4415},[91],{"categories":4417},[47],{"categories":4419},[47],{"categories":4421},[154],{"categories":4423},[96],{"categories":4425},[96],{"categories":4427},[],{"categories":4429},[],{"categories":4431},[47],{"categories":4433},[],{"categories":4435},[118],{"categories":4437},[91],{"categories":4439},[],{"categories":4441},[],{"categories":4443},[151],{"categories":4445},[88],{"categories":4447},[],{"categories":4449},[91],{"categories":4451},[176],{"categories":4453},[47],{"categories":4455},[167],{"categories":4457},[88],{"categories":4459},[154],{"categories":4461},[91],{"categories":4463},[167],{"categories":4465},[167],{"categories":4467},[],{"categories":4469},[47],{"categories":4471},[],{"categories":4473},[96],{"categories":4475},[88],{"categories":4477},[151],{"categories":4479},[88],{"categories":4481},[96],{"categories":4483},[205],{"categories":4485},[47],{"categories":4487},[47],{"categories":4489},[47],{"categories":4491},[88],{"categories":4493},[96],{"categories":4495},[],{"categories":4497},[47],{"categories":4499},[167],{"categories":4501},[118],{"categories":4503},[167],{"categories":4505},[47],{"categories":4507},[],{"categories":4509},[151],{"categories":4511},[118],{"categories":4513},[88],{"categories":4515},[96],{"categories":4517},[47],{"categories":4519},[47],{"categories":4521},[96],{"categories":4523},[47],{"categories":4525},[47],{"categories":4527},[91],{"categories":4529},[96],{"categories":4531},[96,205],{"categories":4533},[96],{"categories":4535},[167],{"categories":4537},[47],{"categories":4539},[47],{"categories":4541},[154],{"categories":4543},[96],{"categories":4545},[176],{"categories":4547},[96],{"categories":4549},[91],{"categories":4551},[],{"categories":4553},[96],{"categories":4555},[47],{"categories":4557},[91],{"categories":4559},[],{"categories":4561},[],{"categories":4563},[47],{"categories":4565},[96],{"categories":4567},[154],{"categories":4569},[176],{"categories":4571},[47],{"categories":4573},[47],{"categories":4575},[96],{"categories":4577},[],{"categories":4579},[118],{"categories":4581},[96],{"categories":4583},[],{"categories":4585},[118],{"categories":4587},[167],{"categories":4589},[88],{"categories":4591},[167],{"categories":4593},[47],{"categories":4595},[96],{"categories":4597},[47],{"categories":4599},[47],{"categories":4601},[176],{"categories":4603},[167],{"categories":4605},[],{"categories":4607},[118],{"categories":4609},[47],{"categories":4611},[],{"categories":4613},[47],{"categories":4615},[47],{"categories":4617},[47],{"categories":4619},[96],{"categories":4621},[47],{"categories":4623},[47],{"categories":4625},[99],{"categories":4627},[96],{"categories":4629},[47],{"categories":4631},[47],{"categories":4633},[47],{"categories":4635},[47],{"categories":4637},[47],{"categories":4639},[91],{"categories":4641},[],{"categories":4643},[99],{"categories":4645},[118],{"categories":4647},[96],{"categories":4649},[47],{"categories":4651},[167],{"categories":4653},[],{"categories":4655},[167],{"categories":4657},[167],{"categories":4659},[96],{"categories":4661},[167],{"categories":4663},[47],{"categories":4665},[47],{"categories":4667},[167],{"categories":4669},[47],{"categories":4671},[96],{"categories":4673},[118],{"categories":4675},[47],{"categories":4677},[47],{"categories":4679},[47],{"categories":4681},[91],{"categories":4683},[47],{"categories":4685},[96],{"categories":4687},[151],{"categories":4689},[],{"categories":4691},[47],{"categories":4693},[154],{"categories":4695},[96],{"categories":4697},[47],{"categories":4699},[],{"categories":4701},[47],{"categories":4703},[47],{"categories":4705},[118],{"categories":4707},[47],{"categories":4709},[96],{"categories":4711},[176],{"categories":4713},[],{"categories":4715},[],{"categories":4717},[118],{"categories":4719},[118],{"categories":4721},[47],{"categories":4723},[176],{"categories":4725},[47],{"categories":4727},[88],{"categories":4729},[96],{"categories":4731},[47],{"categories":4733},[96],{"categories":4735},[96],{"categories":4737},[47],{"categories":4739},[91],{"categories":4741},[],{"categories":4743},[154],{"categories":4745},[],{"categories":4747},[118],{"categories":4749},[47],{"categories":4751},[154],{"categories":4753},[47],{"categories":4755},[167],{"categories":4757},[167],{"categories":4759},[167],{"categories":4761},[96],{"categories":4763},[96],{"categories":4765},[96],{"categories":4767},[151],{"categories":4769},[154],{"categories":4771},[154],{"categories":4773},[],{"categories":4775},[118],{"categories":4777},[47],{"categories":4779},[47],{"categories":4781},[167],{"categories":4783},[],{"categories":4785},[118],{"categories":4787},[118],{"categories":4789},[118],{"categories":4791},[],{"categories":4793},[96],{"categories":4795},[47],{"categories":4797},[],{"categories":4799},[88],{"categories":4801},[91],{"categories":4803},[],{"categories":4805},[47],{"categories":4807},[47],{"categories":4809},[],{"categories":4811},[167],{"categories":4813},[],{"categories":4815},[],{"categories":4817},[],{"categories":4819},[],{"categories":4821},[47],{"categories":4823},[118],{"categories":4825},[],{"categories":4827},[],{"categories":4829},[47],{"categories":4831},[47],{"categories":4833},[47],{"categories":4835},[154],{"categories":4837},[47],{"categories":4839},[154],{"categories":4841},[],{"categories":4843},[154],{"categories":4845},[154],{"categories":4847},[205],{"categories":4849},[96],{"categories":4851},[167],{"categories":4853},[],{"categories":4855},[],{"categories":4857},[154],{"categories":4859},[167],{"categories":4861},[167],{"categories":4863},[167],{"categories":4865},[],{"categories":4867},[88],{"categories":4869},[167],{"categories":4871},[167],{"categories":4873},[88],{"categories":4875},[167],{"categories":4877},[91],{"categories":4879},[167],{"categories":4881},[167],{"categories":4883},[167],{"categories":4885},[154],{"categories":4887},[118],{"categories":4889},[118],{"categories":4891},[47],{"categories":4893},[167],{"categories":4895},[154],{"categories":4897},[205],{"categories":4899},[154],{"categories":4901},[154],{"categories":4903},[154],{"categories":4905},[],{"categories":4907},[91],{"categories":4909},[],{"categories":4911},[205],{"categories":4913},[167],{"categories":4915},[167],{"categories":4917},[167],{"categories":4919},[96],{"categories":4921},[118,91],{"categories":4923},[154],{"categories":4925},[],{"categories":4927},[],{"categories":4929},[154],{"categories":4931},[],{"categories":4933},[154],{"categories":4935},[118],{"categories":4937},[96],{"categories":4939},[],{"categories":4941},[167],{"categories":4943},[47],{"categories":4945},[151],{"categories":4947},[],{"categories":4949},[47],{"categories":4951},[],{"categories":4953},[118],{"categories":4955},[88],{"categories":4957},[154],{"categories":4959},[],{"categories":4961},[167],{"categories":4963},[118],[4965,5023,5096,5165],{"id":4966,"title":4967,"ai":4968,"body":4973,"categories":5001,"created_at":48,"date_modified":48,"description":40,"extension":49,"faq":48,"featured":50,"kicker_label":48,"meta":5002,"navigation":67,"path":5013,"published_at":5014,"question":48,"scraped_at":5014,"seo":5015,"sitemap":5016,"source_id":5017,"source_name":73,"source_type":74,"source_url":5007,"stem":5018,"tags":5019,"thumbnail_url":48,"tldr":5020,"tweet":48,"unknown_tags":5021,"__hash__":5022},"summaries\u002Fsummaries\u002F6bad914f489b1323-optimizing-llm-post-training-through-pairwise-comp-summary.md","Optimizing LLM Post-Training Through Pairwise Comparison Selection",{"provider":7,"model":8,"input_tokens":4969,"output_tokens":4970,"processing_time_ms":4971,"cost_usd":4972},4051,507,3074,0.00177325,{"type":14,"value":4974,"toc":4996},[4975,4979,4982,4986,4989,4993],[17,4976,4978],{"id":4977},"the-critical-role-of-data-selection-in-post-training","The Critical Role of Data Selection in Post-Training",[22,4980,4981],{},"Recent advancements in LLM post-training have shifted focus from purely algorithmic improvements (such as refining DPO or PPO) to the quality and composition of the preference data used. The core argument is that the model's alignment is fundamentally constrained by the quality of the 'chosen' vs. 'rejected' pairs provided during training. Rather than treating all preference data as equal, researchers must optimize which pairs are presented to the model to maximize learning efficiency and minimize noise.",[17,4983,4985],{"id":4984},"strategic-pair-selection-frameworks","Strategic Pair Selection Frameworks",[22,4987,4988],{},"The research highlights that effective post-training requires a nuanced approach to pair selection. Instead of relying on random sampling, practitioners should prioritize pairs that represent 'hard' negatives—cases where the rejected response is plausible but suboptimal. By focusing on these high-utility comparisons, the model is forced to learn more granular distinctions in reasoning, tone, and factual accuracy. The study suggests that the distribution of these pairs—balancing easy-to-distinguish examples with challenging edge cases—is a primary driver of model performance in downstream tasks.",[17,4990,4992],{"id":4991},"trade-offs-in-data-diversity-and-difficulty","Trade-offs in Data Diversity and Difficulty",[22,4994,4995],{},"There is a clear trade-off between the diversity of the training set and the difficulty of the individual pairs. While training on a massive, diverse dataset prevents overfitting, it can dilute the signal if the pairs are too easy or ambiguous. The authors advocate for a curriculum-based or filtered approach, where the selection of pairs is dynamically adjusted to match the model's current capabilities. This ensures that the model is consistently challenged without being overwhelmed by low-quality or contradictory preference signals.",{"title":40,"searchDepth":41,"depth":41,"links":4997},[4998,4999,5000],{"id":4977,"depth":41,"text":4978},{"id":4984,"depth":41,"text":4985},{"id":4991,"depth":41,"text":4992},[47],{"content_references":5003,"triage":5009},[5004],{"type":5005,"title":5006,"url":5007,"context":5008},"paper","Which Pairs to Compare for LLM Post-Training?","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.19607","reviewed",{"relevance":5010,"novelty":64,"quality":64,"actionability":63,"composite":5011,"reasoning":5012},5,4.15,"Category: AI & LLMs. The article discusses optimizing LLM post-training through strategic pair selection, which directly addresses the audience's need for practical applications in AI model training. It presents a framework for selecting effective training pairs, which is actionable but lacks detailed step-by-step guidance.","\u002Fsummaries\u002F6bad914f489b1323-optimizing-llm-post-training-through-pairwise-comp-summary","2026-06-19 12:57:04",{"title":4967,"description":40},{"loc":5013},"6bad914f489b1323","summaries\u002F6bad914f489b1323-optimizing-llm-post-training-through-pairwise-comp-summary",[78,79,80],"The paper investigates how the selection of response pairs in preference-based post-training (like DPO or PPO) impacts model performance, suggesting that strategic pair selection is as critical as the training algorithm itself.",[],"_JtCmCkkrvU2bIXtnfQ8QgHYxzEL-sRSfYEDKhYsE_g",{"id":5024,"title":5025,"ai":5026,"body":5031,"categories":5076,"created_at":48,"date_modified":48,"description":40,"extension":49,"faq":48,"featured":50,"kicker_label":48,"meta":5077,"navigation":67,"path":5086,"published_at":5087,"question":48,"scraped_at":5087,"seo":5088,"sitemap":5089,"source_id":5090,"source_name":73,"source_type":74,"source_url":5081,"stem":5091,"tags":5092,"thumbnail_url":48,"tldr":5093,"tweet":48,"unknown_tags":5094,"__hash__":5095},"summaries\u002Fsummaries\u002Ffc39f7c038b33285-detecting-llm-epistemic-blind-spots-via-cross-mode-summary.md","Detecting LLM Epistemic Blind Spots via Cross-Model Attribution",{"provider":7,"model":8,"input_tokens":5027,"output_tokens":5028,"processing_time_ms":5029,"cost_usd":5030},4131,632,4898,0.00198075,{"type":14,"value":5032,"toc":5071},[5033,5037,5040,5044,5047,5064,5068],[17,5034,5036],{"id":5035},"the-challenge-of-epistemic-uncertainty-in-clinical-ai","The Challenge of Epistemic Uncertainty in Clinical AI",[22,5038,5039],{},"Large Language Models (LLMs) frequently exhibit overconfidence even when their internal knowledge is insufficient for a specific task. In high-stakes domains like clinical decision support, this 'epistemic blind spot'—where a model lacks the necessary training data to make an accurate prediction—poses a significant safety risk. Standard confidence scores (like softmax probabilities) are often poorly calibrated, failing to signal when a model is guessing based on noise rather than learned patterns.",[17,5041,5043],{"id":5042},"detecting-blind-spots-via-cross-model-attribution-divergence-cmad","Detecting Blind Spots via Cross-Model Attribution Divergence (CMAD)",[22,5045,5046],{},"The authors propose a novel framework, Cross-Model Attribution Divergence (CMAD), to detect these blind spots. Instead of relying on the model's output probability, the method analyzes the 'reasoning' path by comparing feature attribution maps across different models.",[5048,5049,5050,5058],"ul",{},[5051,5052,5053,5057],"li",{},[5054,5055,5056],"strong",{},"Attribution Divergence:"," The core insight is that when multiple models (or a model and a baseline) disagree significantly on which input features are driving a prediction, the model is likely operating in a region of high epistemic uncertainty.",[5051,5059,5060,5063],{},[5054,5061,5062],{},"Clinical Tabular Application:"," By applying this to clinical tabular data, the researchers demonstrate that divergence in feature importance scores serves as a reliable proxy for identifying samples where the model lacks sufficient training coverage. When models rely on different, non-causal, or noise-heavy features to reach a conclusion, the system flags the prediction as potentially unreliable.",[17,5065,5067],{"id":5066},"practical-implications-for-model-deployment","Practical Implications for Model Deployment",[22,5069,5070],{},"This approach shifts the focus from 'what the model predicts' to 'why the model predicts it.' By quantifying the disagreement in feature attribution, developers can implement a 'human-in-the-loop' trigger. When CMAD scores exceed a defined threshold, the system can automatically route the query to a human clinician rather than allowing the LLM to provide an unverified, potentially hallucinated recommendation. This provides a robust mechanism for safety-critical AI, ensuring that models only operate within their known epistemic boundaries.",{"title":40,"searchDepth":41,"depth":41,"links":5072},[5073,5074,5075],{"id":5035,"depth":41,"text":5036},{"id":5042,"depth":41,"text":5043},{"id":5066,"depth":41,"text":5067},[47],{"content_references":5078,"triage":5083},[5079],{"type":5005,"title":5080,"url":5081,"context":5082},"LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.19509","cited",{"relevance":64,"novelty":64,"quality":64,"actionability":63,"composite":5084,"reasoning":5085},3.8,"Category: AI & LLMs. The article addresses a significant issue in AI deployment, particularly in clinical settings, by introducing a novel method (CMAD) for detecting epistemic uncertainty in LLMs. It provides insights into practical implications for model deployment, although it lacks detailed step-by-step guidance for implementation.","\u002Fsummaries\u002Ffc39f7c038b33285-detecting-llm-epistemic-blind-spots-via-cross-mode-summary","2026-06-19 12:57:03",{"title":5025,"description":40},{"loc":5086},"fc39f7c038b33285","summaries\u002Ffc39f7c038b33285-detecting-llm-epistemic-blind-spots-via-cross-mode-summary",[78,79,80],"LLMs often hallucinate confidence in clinical settings. This paper introduces a method using Cross-Model Attribution Divergence (CMAD) to identify when models rely on unreliable features, effectively flagging epistemic uncertainty in tabular data.",[],"V6Q8ZwiJoOBGigD2IBgZlrJku3e7AfEY21Rt9iQu4xA",{"id":5097,"title":5098,"ai":5099,"body":5104,"categories":5147,"created_at":48,"date_modified":48,"description":40,"extension":49,"faq":48,"featured":50,"kicker_label":48,"meta":5148,"navigation":67,"path":5155,"published_at":5156,"question":48,"scraped_at":5156,"seo":5157,"sitemap":5158,"source_id":5159,"source_name":73,"source_type":74,"source_url":5152,"stem":5160,"tags":5161,"thumbnail_url":48,"tldr":5162,"tweet":48,"unknown_tags":5163,"__hash__":5164},"summaries\u002Fsummaries\u002F8a65566820c4fee9-memtrace-beyond-final-accuracy-in-llm-long-term-me-summary.md","MemTrace: Beyond Final Accuracy in LLM Long-Term Memory",{"provider":7,"model":8,"input_tokens":5100,"output_tokens":5101,"processing_time_ms":5102,"cost_usd":5103},4053,441,2713,0.00167475,{"type":14,"value":5105,"toc":5143},[5106,5110,5113,5117,5120,5140],[17,5107,5109],{"id":5108},"the-limitations-of-final-accuracy","The Limitations of Final Accuracy",[22,5111,5112],{},"Standard benchmarks for long-term memory in Large Language Models (LLMs) often rely on final accuracy—measuring whether a model can retrieve a specific piece of information after a delay. However, this metric is insufficient because it obscures the 'how' and 'why' of memory failure. A model might arrive at the correct answer through lucky guessing, memorization of patterns rather than facts, or transient activations that do not reflect true long-term storage. MemTrace addresses this by probing the internal states of the model to distinguish between robust knowledge retention and superficial performance.",[17,5114,5116],{"id":5115},"probing-memory-dynamics","Probing Memory Dynamics",[22,5118,5119],{},"MemTrace shifts the focus from static evaluation to dynamic tracing. By analyzing the model's internal representations during the interval between information ingestion and retrieval, the framework identifies the specific points where memory degrades. This allows researchers to differentiate between:",[5048,5121,5122,5128,5134],{},[5051,5123,5124,5127],{},[5054,5125,5126],{},"Encoding Failures:"," Instances where the model never successfully integrated the information into its weights or context.",[5051,5129,5130,5133],{},[5054,5131,5132],{},"Retrieval Failures:"," Instances where the information is present but the model fails to access it due to interference or poor query alignment.",[5051,5135,5136,5139],{},[5054,5137,5138],{},"Decay Patterns:"," The rate at which information becomes inaccessible, providing a more granular view of memory stability than a binary pass\u002Ffail score.",[22,5141,5142],{},"By moving beyond the 'black box' approach of measuring only output, MemTrace provides a diagnostic tool for developers to understand if their RAG (Retrieval-Augmented Generation) pipelines or fine-tuning strategies are actually building durable knowledge or merely creating temporary, fragile associations.",{"title":40,"searchDepth":41,"depth":41,"links":5144},[5145,5146],{"id":5108,"depth":41,"text":5109},{"id":5115,"depth":41,"text":5116},[47],{"content_references":5149,"triage":5153},[5150],{"type":5005,"title":5151,"url":5152,"context":5082},"MemTrace: Probing What Final Accuracy Misses in Long-Term Memory","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.17328",{"relevance":5010,"novelty":64,"quality":64,"actionability":63,"composite":5011,"reasoning":5154},"Category: AI & LLMs. The article provides a detailed examination of a new framework, MemTrace, that enhances understanding of LLM memory dynamics, addressing a specific pain point for developers working with AI models. It offers insights into memory retention mechanisms, which can inform practical applications in AI product development.","\u002Fsummaries\u002F8a65566820c4fee9-memtrace-beyond-final-accuracy-in-llm-long-term-me-summary","2026-06-17 12:56:58",{"title":5098,"description":40},{"loc":5155},"8a65566820c4fee9","summaries\u002F8a65566820c4fee9-memtrace-beyond-final-accuracy-in-llm-long-term-me-summary",[78,80,79],"MemTrace is a diagnostic framework designed to evaluate LLM long-term memory beyond simple accuracy metrics, focusing on the underlying mechanisms of information retention and retrieval over time.",[],"hVKqiluVeYjtifrCBQ8WQYpKZDYl0qh3rhrwBI3SVlI",{"id":5166,"title":5167,"ai":5168,"body":5173,"categories":5212,"created_at":48,"date_modified":48,"description":40,"extension":49,"faq":48,"featured":50,"kicker_label":48,"meta":5213,"navigation":67,"path":5220,"published_at":5221,"question":48,"scraped_at":5221,"seo":5222,"sitemap":5223,"source_id":5224,"source_name":73,"source_type":74,"source_url":5225,"stem":5226,"tags":5227,"thumbnail_url":48,"tldr":5228,"tweet":48,"unknown_tags":5229,"__hash__":5230},"summaries\u002Fsummaries\u002Fc762634c1fa4a782-comparing-diff-in-means-and-inlp-for-llm-refusal-m-summary.md","Comparing Diff-in-Means and INLP for LLM Refusal Mechanisms",{"provider":7,"model":8,"input_tokens":5169,"output_tokens":5170,"processing_time_ms":5171,"cost_usd":5172},4084,526,2784,0.00181,{"type":14,"value":5174,"toc":5207},[5175,5179,5182,5186,5200,5204],[17,5176,5178],{"id":5177},"the-challenge-of-linear-refusal-representations","The Challenge of Linear Refusal Representations",[22,5180,5181],{},"Recent research into LLM safety often relies on the assumption that 'refusal'—the model's tendency to decline answering certain prompts—can be isolated as a single, linear vector within the model's activation space. This paper investigates this assumption by comparing two primary methods for identifying these directions: Difference-in-Means (Diff-in-Means) and Iterative Null-space Projection (INLP).",[17,5183,5185],{"id":5184},"diff-in-means-vs-inlp-methodological-trade-offs","Diff-in-Means vs. INLP: Methodological Trade-offs",[5048,5187,5188,5194],{},[5051,5189,5190,5193],{},[5054,5191,5192],{},"Diff-in-Means:"," This approach calculates the average activation difference between a set of refusal prompts and a set of benign prompts. While computationally efficient and straightforward, it assumes that the refusal behavior is concentrated in a single, dominant direction. The study suggests that this method may be too simplistic to capture the nuanced, multi-dimensional nature of model refusals.",[5051,5195,5196,5199],{},[5054,5197,5198],{},"INLP (Iterative Null-space Projection):"," This technique iteratively identifies and removes linear components that correlate with a specific behavior (in this case, refusal). By repeatedly projecting activations into the null-space of the identified refusal direction, INLP aims to 'scrub' the model of the behavior more thoroughly than a single vector subtraction. The authors evaluate whether this iterative process is more effective at neutralizing refusal without degrading general model performance.",[17,5201,5203],{"id":5202},"preliminary-findings-on-refusal-complexity","Preliminary Findings on Refusal Complexity",[22,5205,5206],{},"The core argument is that refusal is likely not a single direction but a complex, multi-faceted phenomenon. The study highlights that while both methods are useful for interpretability, they often fail to account for the non-linear ways in which models encode safety constraints. The authors suggest that relying on a single linear direction for intervention is insufficient for robust safety alignment, as models may have multiple, redundant pathways for triggering a refusal response.",{"title":40,"searchDepth":41,"depth":41,"links":5208},[5209,5210,5211],{"id":5177,"depth":41,"text":5178},{"id":5184,"depth":41,"text":5185},{"id":5202,"depth":41,"text":5203},[47],{"content_references":5214,"triage":5218},[5215],{"type":5005,"title":5216,"author":5217,"context":5082},"Refusal Beyond a Single Direction: A Preliminary Comparison of Diff-in-Means and INLP","Unknown",{"relevance":63,"novelty":64,"quality":64,"actionability":41,"composite":65,"reasoning":5219},"Category: AI & LLMs. The article discusses methodologies for improving LLM safety, which is relevant to AI product builders. However, it lacks direct actionable insights for implementation, focusing more on theoretical evaluation of techniques.","\u002Fsummaries\u002Fc762634c1fa4a782-comparing-diff-in-means-and-inlp-for-llm-refusal-m-summary","2026-06-15 12:57:02",{"title":5167,"description":40},{"loc":5220},"c762634c1fa4a782","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.13720","summaries\u002Fc762634c1fa4a782-comparing-diff-in-means-and-inlp-for-llm-refusal-m-summary",[78,79,80],"This paper evaluates two common techniques—Difference-in-Means and Iterative Null-space Projection (INLP)—for identifying and mitigating refusal behaviors in LLMs, highlighting the limitations of assuming refusal is a single, linear direction.",[],"LrQPOQc-3znscIAip-3DyoNqgvg6zzyYJLUmaEfcKEU"]