[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-f783931b642bec27-vibevoice-asr-60-min-asr-with-speakers-timestamps-summary":3,"summaries-facets-categories":142,"summary-related-f783931b642bec27-vibevoice-asr-60-min-asr-with-speakers-timestamps-summary":3712},{"id":4,"title":5,"ai":6,"body":13,"categories":97,"created_at":98,"date_modified":98,"description":91,"extension":99,"faq":98,"featured":100,"kicker_label":98,"meta":101,"navigation":125,"path":126,"published_at":98,"question":98,"scraped_at":127,"seo":128,"sitemap":129,"source_id":130,"source_name":131,"source_type":132,"source_url":133,"stem":134,"tags":135,"thumbnail_url":98,"tldr":139,"tweet":98,"unknown_tags":140,"__hash__":141},"summaries\u002Fsummaries\u002Ff783931b642bec27-vibevoice-asr-60-min-asr-with-speakers-timestamps--summary.md","VibeVoice-ASR: 60-Min ASR with Speakers, Timestamps, Hotwords",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","x-ai\u002Fgrok-4.1-fast",8981,1739,13836,0.00215885,{"type":14,"value":15,"toc":90},"minimark",[16,21,49,56,60,83,87],[17,18,20],"h2",{"id":19},"unified-long-form-transcription-in-single-pass","Unified Long-Form Transcription in Single Pass",[22,23,24,25,29,30,33,34,37,38,29,41,44,45,48],"p",{},"VibeVoice-ASR handles 60-minute audio within 64K tokens without chunking losses, maintaining speaker consistency and semantics. It jointly performs ASR, diarization, and timestamping, outputting JSON-like structures with Start\u002FEnd times, Speaker IDs, and Content. Load via Transformers >=5.3.0: ",[26,27,28],"code",{},"AutoProcessor"," and ",[26,31,32],{},"VibeVoiceAsrForConditionalGeneration.from_pretrained(\"microsoft\u002FVibeVoice-ASR-HF\")",". Use ",[26,35,36],{},"processor.apply_transcription_request(audio)"," for inputs, then ",[26,39,40],{},"model.generate(**inputs)",[26,42,43],{},"processor.decode(generated_ids, return_format=\"parsed\")"," for list of dicts or ",[26,46,47],{},"\"transcription_only\""," for plain text. Example on podcast audio yields segments like {\"Start\":0,\"End\":15.43,\"Speaker\":0,\"Content\":\"Hello everyone...\"}, preserving multi-speaker flow.",[22,50,51,52,55],{},"Custom hotwords via ",[26,53,54],{},"prompt"," parameter fix misrecognitions: on German-accented \"VibeVoice\" audio, without prompt it transcribes \"Revevoices\", but \"About VibeVoice\" prompt corrects to exact match, ideal for names or terms.",[17,57,59],{"id":58},"flexible-inference-and-optimization-techniques","Flexible Inference and Optimization Techniques",[22,61,62,63,66,67,70,71,74,75,78,79,82],{},"Batch process lists of audio\u002Fprompts for efficiency. Adjust ",[26,64,65],{},"tokenizer_chunk_size"," (default 1440000 samples\u002F60s at 24kHz, multiples of 3200 hop length) to fit memory, e.g., 64000 for shorter segments with cached states. Chat templates enable role-based inputs: ",[26,68,69],{},"[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"prompt\"},{\"type\":\"audio\",\"path\":\"url\"}]}]",", processed via ",[26,72,73],{},"apply_chat_template",". Torch.compile speeds up by 2x+ on benchmarks (e.g., batch-4 German audio: ~0.2s uncompiled to ~0.1s compiled). Pipeline mode works but requires custom parsing of raw JSON strings. For training, use ",[26,76,77],{},"model.train()"," with ",[26,80,81],{},"output_labels=True"," in chat templates, computing loss on JSON-like targets.",[17,84,86],{"id":85},"proven-performance-across-benchmarks","Proven Performance Across Benchmarks",[22,88,89],{},"Achieves average 7.77% WER on Open ASR Leaderboard (e.g., 2.20% LibriSpeech clean, 13.17% earnings22, RTF 51.80x real-time). Technical report shows low DER, cpWER, tcpWER on long-form datasets. Supports 50+ languages without ID specification, handling code-switching; distribution chart emphasizes English-heavy training with broad coverage. MIT-licensed, deployable on Foundry or Gradio playground.",{"title":91,"searchDepth":92,"depth":92,"links":93},"",2,[94,95,96],{"id":19,"depth":92,"text":20},{"id":58,"depth":92,"text":59},{"id":85,"depth":92,"text":86},[],null,"md",false,{"content_references":102,"triage":120},[103,108,113,117],{"type":104,"title":105,"url":106,"context":107},"paper","VibeVoice-ASR Technical Report","https:\u002F\u002Farxiv.org\u002Fpdf\u002F2601.18184","cited",{"type":109,"title":110,"url":111,"context":112},"other","GitHub Repo","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FVibeVoice","mentioned",{"type":114,"title":115,"url":116,"context":112},"tool","Live Playground","https:\u002F\u002Faka.ms\u002Fvibevoice-asr",{"type":109,"title":118,"url":119,"context":107},"Open ASR Leaderboard","https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fhf-audio\u002Fopen_asr_leaderboard",{"relevance":121,"novelty":122,"quality":122,"actionability":122,"composite":123,"reasoning":124},5,4,4.35,"Category: AI & LLMs. The article provides a detailed overview of the VibeVoice-ASR tool, which is highly relevant for developers looking to integrate advanced ASR capabilities into their AI products. It includes practical examples of how to implement the tool, making it actionable for the target audience.",true,"\u002Fsummaries\u002Ff783931b642bec27-vibevoice-asr-60-min-asr-with-speakers-timestamps-summary","2026-04-14 14:33:41",{"title":5,"description":91},{"loc":126},"f783931b642bec27","__oneoff__","article","https:\u002F\u002Fhuggingface.co\u002Fmicrosoft\u002FVibeVoice-ASR-HF","summaries\u002Ff783931b642bec27-vibevoice-asr-60-min-asr-with-speakers-timestamps--summary",[136,137,138],"ai-tools","machine-learning","python","Process up to 60 minutes of audio in one pass for structured transcripts (speaker IDs, timestamps, content) across 50+ languages, with custom hotwords boosting accuracy on proper nouns.",[],"CleYyRRaj1ZGtSxuM2ol1nsnQLLYzXcBZdiNsBG4ShM",[143,146,149,152,155,158,160,162,164,166,168,170,173,175,177,179,181,183,185,187,189,191,194,197,199,201,204,206,208,211,213,215,217,219,221,223,225,227,229,231,233,235,237,239,241,243,245,247,249,251,253,255,257,259,261,263,265,267,269,271,273,275,277,279,281,283,285,287,289,291,293,295,297,299,301,303,305,307,309,311,313,315,317,319,321,323,325,327,329,331,333,335,337,339,341,343,345,347,349,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,393,395,397,399,401,403,405,407,409,411,413,415,417,419,421,423,425,427,429,431,433,435,437,439,441,443,445,447,449,451,453,455,457,459,461,463,466,468,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,516,518,520,522,524,526,528,530,532,534,536,538,540,542,544,546,548,550,552,554,556,558,560,562,564,566,568,570,572,574,576,578,580,582,584,586,588,590,592,594,596,598,600,602,604,606,608,610,612,614,616,618,620,622,624,626,628,630,632,634,636,638,640,642,644,646,648,650,652,654,656,658,660,662,664,666,668,670,672,674,676,678,680,682,684,686,688,690,692,694,696,698,700,702,704,706,708,710,712,714,716,718,720,722,724,726,728,730,732,734,736,738,740,742,744,746,748,750,752,754,756,758,760,762,764,766,768,770,772,774,776,778,780,782,784,786,788,790,792,794,796,798,800,802,804,806,808,810,812,814,816,818,820,822,824,826,828,830,832,834,836,838,840,842,844,846,848,850,852,854,856,858,860,862,864,866,868,870,872,874,876,878,880,882,884,886,888,890,892,894,896,898,900,902,904,906,908,910,912,914,916,918,920,922,924,926,928,930,932,934,936,938,940,942,944,946,948,950,952,954,956,958,960,962,964,966,968,970,972,974,976,978,980,982,984,986,988,990,992,994,996,998,1000,1002,1004,1006,1008,1010,1012,1014,1016,1018,1020,1022,1024,1026,1028,1030,1032,1034,1036,1038,1040,1042,1044,1046,1048,1050,1052,1054,1056,1058,1060,1062,1064,1066,1068,1070,1072,1074,1076,1078,1080,1082,1084,1086,1088,1090,1092,1094,1096,1098,1100,1102,1104,1106,1108,1110,1112,1114,1116,1118,1120,1122,1124,1126,1128,1130,1132,1134,1136,1138,1140,1142,1144,1146,1148,1150,1152,1154,1156,1158,1160,1162,1164,1166,1168,1170,1172,1174,1176,1178,1180,1182,1184,1186,1188,1190,1192,1194,1196,1198,1200,1202,1204,1206,1208,1210,1212,1214,1216,1218,1220,1222,1224,1226,1228,1230,1232,1234,1236,1238,1240,1242,1244,1246,1248,1250,1252,1254,1256,1258,1260,1262,1264,1266,1268,1270,1272,1274,1276,1278,1280,1282,1284,1286,1288,1290,1292,1294,1296,1298,1300,1302,1304,1306,1308,1310,1312,1314,1316,1318,1320,1322,1324,1326,1328,1330,1332,1334,1336,1338,1340,1342,1344,1346,1348,1350,1352,1354,1356,1358,1360,1362,1364,1366,1368,1370,1372,1374,1376,1378,1380,1382,1384,1386,1388,1390,1392,1394,1396,1398,1400,1402,1404,1406,1408,1410,1412,1414,1416,1418,1420,1422,1424,1426,1428,1430,1432,1434,1436,1438,1440,1442,1444,1446,1448,1450,1452,1454,1456,1458,1460,1462,1464,1466,1468,1470,1472,1474,1476,1478,1480,1482,1484,1486,1488,1490,1492,1494,1496,1498,1500,1502,1504,1506,1508,1510,1512,1514,1516,1518,1520,1522,1524,1526,1528,1530,1532,1534,1536,1538,1540,1542,1544,1546,1548,1550,1552,1554,1556,1558,1560,1562,1564,1566,1568,1570,1572,1574,1576,1578,1580,1582,1584,1586,1588,1590,1592,1594,1596,1598,1600,1602,1604,1606,1608,1610,1612,1614,1616,1618,1620,1622,1624,1626,1628,1630,1632,1634,1636,1638,1640,1642,1644,1646,1648,1650,1652,1654,1656,1658,1660,1662,1664,1666,1668,1670,1672,1674,1676,1678,1680,1682,1684,1686,1688,1690,1692,1694,1696,1698,1700,1702,1704,1706,1708,1710,1712,1714,1716,1718,1720,1722,1724,1726,1728,1730,1732,1734,1736,1738,1740,1742,1744,1746,1748,1750,1752,1754,1756,1758,1760,1762,1764,1766,1768,1770,1772,1774,1776,1778,1780,1782,1784,1786,1788,1790,1792,1794,1796,1798,1800,1802,1804,1806,1808,1810,1812,1814,1816,1818,1820,1822,1824,1826,1828,1830,1832,1834,1836,1838,1840,1842,1844,1846,1848,1850,1852,1854,1856,1858,1860,1862,1864,1866,1868,1870,1872,1874,1876,1878,1880,1882,1884,1886,1888,1890,1892,1894,1896,1898,1900,1902,1904,1906,1908,1910,1912,1914,1916,1918,1920,1922,1924,1926,1928,1930,1932,1934,1936,1938,1940,1942,1944,1946,1948,1950,1952,1954,1956,1958,1960,1962,1964,1966,1968,1970,1972,1974,1976,1978,1980,1982,1984,1986,1988,1990,1992,1994,1996,1998,2000,2002,2004,2006,2008,2010,2012,2014,2016,2018,2020,2022,2024,2026,2028,2030,2032,2034,2036,2038,2040,2042,2044,2046,2048,2050,2052,2054,2056,2058,2060,2062,2064,2066,2068,2070,2072,2074,2076,2078,2080,2082,2084,2086,2088,2090,2092,2094,2096,2098,2100,2102,2104,2106,2108,2110,2112,2114,2116,2118,2120,2122,2124,2126,2128,2130,2132,2134,2136,2138,2140,2142,2144,2146,2148,2150,2152,2154,2156,2158,2160,2162,2164,2166,2168,2170,2172,2174,2176,2178,2180,2182,2184,2186,2188,2190,2192,2194,2196,2198,2200,2202,2204,2206,2208,2210,2212,2214,2216,2218,2220,2222,2224,2226,2228,2230,2232,2234,2236,2238,2240,2242,2244,2246,2248,2250,2252,2254,2256,2258,2260,2262,2264,2266,2268,2270,2272,2274,2276,2278,2280,2282,2284,2286,2288,2290,2292,2294,2296,2298,2300,2302,2304,2306,2308,2310,2312,2314,2316,2318,2320,2322,2324,2326,2328,2330,2332,2334,2336,2338,2340,2342,2344,2346,2348,2350,2352,2354,2356,2358,2360,2362,2364,2366,2368,2370,2372,2374,2376,2378,2380,2382,2384,2386,2388,2390,2392,2394,2396,2398,2400,2402,2404,2406,2408,2410,2412,2414,2416,2418,2420,2422,2424,2426,2428,2430,2432,2434,2436,2438,2440,2442,2444,2446,2448,2450,2452,2454,2456,2458,2460,2462,2464,2466,2468,2470,2472,2474,2476,2478,2480,2482,2484,2486,2488,2490,2492,2494,2496,2498,2500,2502,2504,2506,2508,2510,2512,2514,2516,2518,2520,2522,2524,2526,2528,2530,2532,2534,2536,2538,2540,2542,2544,2546,2548,2550,2552,2554,2556,2558,2560,2562,2564,2566,2568,2570,2572,2574,2576,2578,2580,2582,2584,2586,2588,2590,2592,2594,2596,2598,2600,2602,2604,2606,2608,2610,2612,2614,2616,2618,2620,2622,2624,2626,2628,2630,2632,2634,2636,2638,2640,2642,2644,2646,2648,2650,2652,2654,2656,2658,2660,2662,2664,2666,2668,2670,2672,2674,2676,2678,2680,2682,2684,2686,2688,2690,2692,2694,2696,2698,2700,2702,2704,2706,2708,2710,2712,2714,2716,2718,2720,2722,2724,2726,2728,2730,2732,2734,2736,2738,2740,2742,2744,2746,2748,2750,2752,2754,2756,2758,2760,2762,2764,2766,2768,2770,2772,2774,2776,2778,2780,2782,2784,2786,2788,2790,2792,2794,2796,2798,2800,2802,2804,2806,2808,2810,2812,2814,2816,2818,2820,2822,2824,2826,2828,2830,2832,2834,2836,2838,2840,2842,2844,2846,2848,2850,2852,2854,2856,2858,2860,2862,2864,2866,2868,2870,2872,2874,2876,2878,2880,2882,2884,2886,2888,2890,2892,2894,2896,2898,2900,2902,2904,2906,2908,2910,2912,2914,2916,2918,2920,2922,2924,2926,2928,2930,2932,2934,2936,2938,2940,2942,2944,2946,2948,2950,2952,2954,2956,2958,2960,2962,2964,2966,2968,2970,2972,2974,2976,2978,2980,2982,2984,2986,2988,2990,2992,2994,2996,2998,3000,3002,3004,3006,3008,3010,3012,3014,3016,3018,3020,3022,3024,3026,3028,3030,3032,3034,3036,3038,3040,3042,3044,3046,3048,3050,3052,3054,3056,3058,3060,3062,3064,3066,3068,3070,3072,3074,3076,3078,3080,3082,3084,3086,3088,3090,3092,3094,3096,3098,3100,3102,3104,3106,3108,3110,3112,3114,3116,3118,3120,3122,3124,3126,3128,3130,3132,3134,3136,3138,3140,3142,3144,3146,3148,3150,3152,3154,3156,3158,3160,3162,3164,3166,3168,3170,3172,3174,3176,3178,3180,3182,3184,3186,3188,3190,3192,3194,3196,3198,3200,3202,3204,3206,3208,3210,3212,3214,3216,3218,3220,3222,3224,3226,3228,3230,3232,3234,3236,3238,3240,3242,3244,3246,3248,3250,3252,3254,3256,3258,3260,3262,3264,3266,3268,3270,3272,3274,3276,3278,3280,3282,3284,3286,3288,3290,3292,3294,3296,3298,3300,3302,3304,3306,3308,3310,3312,3314,3316,3318,3320,3322,3324,3326,3328,3330,3332,3334,3336,3338,3340,3342,3344,3346,3348,3350,3352,3354,3356,3358,3360,3362,3364,3366,3368,3370,3372,3374,3376,3378,3380,3382,3384,3386,3388,3390,3392,3394,3396,3398,3400,3402,3404,3406,3408,3410,3412,3414,3416,3418,3420,3422,3424,3426,3428,3430,3432,3434,3436,3438,3440,3442,3444,3446,3448,3450,3452,3454,3456,3458,3460,3462,3464,3466,3468,3470,3472,3474,3476,3478,3480,3482,3484,3486,3488,3490,3492,3494,3496,3498,3500,3502,3504,3506,3508,3510,3512,3514,3516,3518,3520,3522,3524,3526,3528,3530,3532,3534,3536,3538,3540,3542,3544,3546,3548,3550,3552,3554,3556,3558,3560,3562,3564,3566,3568,3570,3572,3574,3576,3578,3580,3582,3584,3586,3588,3590,3592,3594,3596,3598,3600,3602,3604,3606,3608,3610,3612,3614,3616,3618,3620,3622,3624,3626,3628,3630,3632,3634,3636,3638,3640,3642,3644,3646,3648,3650,3652,3654,3656,3658,3660,3662,3664,3666,3668,3670,3672,3674,3676,3678,3680,3682,3684,3686,3688,3690,3692,3694,3696,3698,3700,3702,3704,3706,3708,3710],{"categories":144},[145],"Developer Productivity",{"categories":147},[148],"Business & SaaS",{"categories":150},[151],"AI & LLMs",{"categories":153},[154],"AI Automation",{"categories":156},[157],"Product Strategy",{"categories":159},[151],{"categories":161},[145],{"categories":163},[148],{"categories":165},[],{"categories":167},[151],{"categories":169},[],{"categories":171},[172],"AI News & Trends",{"categories":174},[154],{"categories":176},[172],{"categories":178},[154],{"categories":180},[154],{"categories":182},[151],{"categories":184},[151],{"categories":186},[172],{"categories":188},[151],{"categories":190},[],{"categories":192},[193],"Design & Frontend",{"categories":195},[196],"Data Science & Visualization",{"categories":198},[172],{"categories":200},[],{"categories":202},[203],"Software Engineering",{"categories":205},[151],{"categories":207},[154],{"categories":209},[210],"Marketing & Growth",{"categories":212},[151],{"categories":214},[154],{"categories":216},[],{"categories":218},[],{"categories":220},[193],{"categories":222},[154],{"categories":224},[145],{"categories":226},[193],{"categories":228},[151],{"categories":230},[154],{"categories":232},[172],{"categories":234},[],{"categories":236},[],{"categories":238},[154],{"categories":240},[203],{"categories":242},[],{"categories":244},[148],{"categories":246},[],{"categories":248},[],{"categories":250},[154],{"categories":252},[154],{"categories":254},[151],{"categories":256},[],{"categories":258},[203],{"categories":260},[],{"categories":262},[],{"categories":264},[],{"categories":266},[151],{"categories":268},[210],{"categories":270},[193],{"categories":272},[193],{"categories":274},[151],{"categories":276},[154],{"categories":278},[151],{"categories":280},[151],{"categories":282},[154],{"categories":284},[154],{"categories":286},[196],{"categories":288},[172],{"categories":290},[154],{"categories":292},[210],{"categories":294},[154],{"categories":296},[157],{"categories":298},[],{"categories":300},[154],{"categories":302},[],{"categories":304},[154],{"categories":306},[203],{"categories":308},[193],{"categories":310},[151],{"categories":312},[],{"categories":314},[],{"categories":316},[154],{"categories":318},[],{"categories":320},[151],{"categories":322},[],{"categories":324},[145],{"categories":326},[203],{"categories":328},[148],{"categories":330},[172],{"categories":332},[151],{"categories":334},[],{"categories":336},[151],{"categories":338},[],{"categories":340},[203],{"categories":342},[196],{"categories":344},[],{"categories":346},[151],{"categories":348},[193],{"categories":350},[],{"categories":352},[193],{"categories":354},[154],{"categories":356},[],{"categories":358},[154],{"categories":360},[172],{"categories":362},[151],{"categories":364},[],{"categories":366},[154],{"categories":368},[151],{"categories":370},[157],{"categories":372},[],{"categories":374},[151],{"categories":376},[154],{"categories":378},[154],{"categories":380},[],{"categories":382},[196],{"categories":384},[151],{"categories":386},[],{"categories":388},[145],{"categories":390},[148],{"categories":392},[151],{"categories":394},[154],{"categories":396},[203],{"categories":398},[151],{"categories":400},[],{"categories":402},[],{"categories":404},[151],{"categories":406},[],{"categories":408},[193],{"categories":410},[],{"categories":412},[151],{"categories":414},[],{"categories":416},[154],{"categories":418},[151],{"categories":420},[193],{"categories":422},[],{"categories":424},[151],{"categories":426},[151],{"categories":428},[148],{"categories":430},[154],{"categories":432},[151],{"categories":434},[193],{"categories":436},[154],{"categories":438},[],{"categories":440},[],{"categories":442},[172],{"categories":444},[],{"categories":446},[151],{"categories":448},[148,210],{"categories":450},[],{"categories":452},[151],{"categories":454},[],{"categories":456},[],{"categories":458},[151],{"categories":460},[],{"categories":462},[151],{"categories":464},[465],"DevOps & Cloud",{"categories":467},[],{"categories":469},[172],{"categories":471},[193],{"categories":473},[],{"categories":475},[172],{"categories":477},[172],{"categories":479},[151],{"categories":481},[210],{"categories":483},[],{"categories":485},[148],{"categories":487},[],{"categories":489},[151,465],{"categories":491},[151],{"categories":493},[151],{"categories":495},[154],{"categories":497},[151,203],{"categories":499},[196],{"categories":501},[151],{"categories":503},[210],{"categories":505},[154],{"categories":507},[154],{"categories":509},[],{"categories":511},[154],{"categories":513},[151,148],{"categories":515},[],{"categories":517},[193],{"categories":519},[193],{"categories":521},[],{"categories":523},[],{"categories":525},[172],{"categories":527},[],{"categories":529},[145],{"categories":531},[203],{"categories":533},[151],{"categories":535},[193],{"categories":537},[154],{"categories":539},[203],{"categories":541},[172],{"categories":543},[193],{"categories":545},[],{"categories":547},[151],{"categories":549},[151],{"categories":551},[151],{"categories":553},[172],{"categories":555},[145],{"categories":557},[151],{"categories":559},[154],{"categories":561},[465],{"categories":563},[193],{"categories":565},[154],{"categories":567},[],{"categories":569},[],{"categories":571},[193],{"categories":573},[172],{"categories":575},[196],{"categories":577},[],{"categories":579},[151],{"categories":581},[151],{"categories":583},[148],{"categories":585},[151],{"categories":587},[151],{"categories":589},[172],{"categories":591},[],{"categories":593},[154],{"categories":595},[203],{"categories":597},[],{"categories":599},[151],{"categories":601},[151],{"categories":603},[154],{"categories":605},[],{"categories":607},[],{"categories":609},[151],{"categories":611},[],{"categories":613},[148],{"categories":615},[154],{"categories":617},[],{"categories":619},[145],{"categories":621},[151],{"categories":623},[148],{"categories":625},[172],{"categories":627},[],{"categories":629},[],{"categories":631},[],{"categories":633},[172],{"categories":635},[172],{"categories":637},[],{"categories":639},[],{"categories":641},[148],{"categories":643},[],{"categories":645},[],{"categories":647},[145],{"categories":649},[],{"categories":651},[210],{"categories":653},[154],{"categories":655},[148],{"categories":657},[154],{"categories":659},[],{"categories":661},[157],{"categories":663},[193],{"categories":665},[203],{"categories":667},[151],{"categories":669},[154],{"categories":671},[148],{"categories":673},[151],{"categories":675},[],{"categories":677},[],{"categories":679},[203],{"categories":681},[196],{"categories":683},[157],{"categories":685},[154],{"categories":687},[151],{"categories":689},[],{"categories":691},[465],{"categories":693},[],{"categories":695},[154],{"categories":697},[],{"categories":699},[],{"categories":701},[151],{"categories":703},[193],{"categories":705},[210],{"categories":707},[154],{"categories":709},[],{"categories":711},[145],{"categories":713},[],{"categories":715},[172],{"categories":717},[151,465],{"categories":719},[172],{"categories":721},[151],{"categories":723},[148],{"categories":725},[151],{"categories":727},[],{"categories":729},[148],{"categories":731},[],{"categories":733},[203],{"categories":735},[193],{"categories":737},[172],{"categories":739},[196],{"categories":741},[145],{"categories":743},[151],{"categories":745},[203],{"categories":747},[],{"categories":749},[],{"categories":751},[157],{"categories":753},[],{"categories":755},[151],{"categories":757},[],{"categories":759},[193],{"categories":761},[193],{"categories":763},[193],{"categories":765},[],{"categories":767},[],{"categories":769},[172],{"categories":771},[154],{"categories":773},[151],{"categories":775},[151],{"categories":777},[151],{"categories":779},[148],{"categories":781},[151],{"categories":783},[],{"categories":785},[203],{"categories":787},[203],{"categories":789},[148],{"categories":791},[],{"categories":793},[151],{"categories":795},[151],{"categories":797},[148],{"categories":799},[172],{"categories":801},[210],{"categories":803},[154],{"categories":805},[],{"categories":807},[193],{"categories":809},[],{"categories":811},[151],{"categories":813},[],{"categories":815},[148],{"categories":817},[154],{"categories":819},[],{"categories":821},[465],{"categories":823},[196],{"categories":825},[203],{"categories":827},[210],{"categories":829},[203],{"categories":831},[154],{"categories":833},[],{"categories":835},[],{"categories":837},[154],{"categories":839},[145],{"categories":841},[154],{"categories":843},[157],{"categories":845},[148],{"categories":847},[],{"categories":849},[151],{"categories":851},[157],{"categories":853},[151],{"categories":855},[151],{"categories":857},[210],{"categories":859},[193],{"categories":861},[154],{"categories":863},[],{"categories":865},[],{"categories":867},[465],{"categories":869},[203],{"categories":871},[],{"categories":873},[154],{"categories":875},[151],{"categories":877},[193,151],{"categories":879},[145],{"categories":881},[],{"categories":883},[151],{"categories":885},[145],{"categories":887},[193],{"categories":889},[154],{"categories":891},[203],{"categories":893},[],{"categories":895},[151],{"categories":897},[],{"categories":899},[145],{"categories":901},[],{"categories":903},[154],{"categories":905},[157],{"categories":907},[151],{"categories":909},[151],{"categories":911},[193],{"categories":913},[154],{"categories":915},[465],{"categories":917},[193],{"categories":919},[154],{"categories":921},[151],{"categories":923},[151],{"categories":925},[151],{"categories":927},[172],{"categories":929},[],{"categories":931},[157],{"categories":933},[154],{"categories":935},[193],{"categories":937},[154],{"categories":939},[203],{"categories":941},[193],{"categories":943},[154],{"categories":945},[172],{"categories":947},[],{"categories":949},[151],{"categories":951},[193],{"categories":953},[151],{"categories":955},[145],{"categories":957},[172],{"categories":959},[151],{"categories":961},[210],{"categories":963},[151],{"categories":965},[151],{"categories":967},[154],{"categories":969},[154],{"categories":971},[151],{"categories":973},[154],{"categories":975},[193],{"categories":977},[151],{"categories":979},[],{"categories":981},[],{"categories":983},[203],{"categories":985},[],{"categories":987},[145],{"categories":989},[465],{"categories":991},[],{"categories":993},[145],{"categories":995},[148],{"categories":997},[210],{"categories":999},[],{"categories":1001},[148],{"categories":1003},[],{"categories":1005},[],{"categories":1007},[],{"categories":1009},[],{"categories":1011},[],{"categories":1013},[151],{"categories":1015},[154],{"categories":1017},[465],{"categories":1019},[145],{"categories":1021},[151],{"categories":1023},[203],{"categories":1025},[157],{"categories":1027},[151],{"categories":1029},[210],{"categories":1031},[151],{"categories":1033},[151],{"categories":1035},[151],{"categories":1037},[151,145],{"categories":1039},[203],{"categories":1041},[203],{"categories":1043},[193],{"categories":1045},[151],{"categories":1047},[],{"categories":1049},[],{"categories":1051},[],{"categories":1053},[203],{"categories":1055},[196],{"categories":1057},[172],{"categories":1059},[193],{"categories":1061},[],{"categories":1063},[151],{"categories":1065},[151],{"categories":1067},[],{"categories":1069},[],{"categories":1071},[154],{"categories":1073},[151],{"categories":1075},[148],{"categories":1077},[],{"categories":1079},[145],{"categories":1081},[151],{"categories":1083},[145],{"categories":1085},[151],{"categories":1087},[203],{"categories":1089},[210],{"categories":1091},[151,193],{"categories":1093},[172],{"categories":1095},[193],{"categories":1097},[],{"categories":1099},[465],{"categories":1101},[193],{"categories":1103},[154],{"categories":1105},[],{"categories":1107},[],{"categories":1109},[],{"categories":1111},[],{"categories":1113},[203],{"categories":1115},[154],{"categories":1117},[154],{"categories":1119},[151],{"categories":1121},[151],{"categories":1123},[],{"categories":1125},[193],{"categories":1127},[],{"categories":1129},[],{"categories":1131},[154],{"categories":1133},[],{"categories":1135},[],{"categories":1137},[210],{"categories":1139},[210],{"categories":1141},[154],{"categories":1143},[],{"categories":1145},[151],{"categories":1147},[151],{"categories":1149},[203],{"categories":1151},[193],{"categories":1153},[193],{"categories":1155},[154],{"categories":1157},[145],{"categories":1159},[151],{"categories":1161},[193],{"categories":1163},[193],{"categories":1165},[154],{"categories":1167},[154],{"categories":1169},[151],{"categories":1171},[],{"categories":1173},[],{"categories":1175},[151],{"categories":1177},[154],{"categories":1179},[172],{"categories":1181},[203],{"categories":1183},[145],{"categories":1185},[151],{"categories":1187},[],{"categories":1189},[154],{"categories":1191},[154],{"categories":1193},[],{"categories":1195},[145],{"categories":1197},[151],{"categories":1199},[145],{"categories":1201},[145],{"categories":1203},[],{"categories":1205},[],{"categories":1207},[154],{"categories":1209},[154],{"categories":1211},[151],{"categories":1213},[151],{"categories":1215},[172],{"categories":1217},[196],{"categories":1219},[157],{"categories":1221},[172],{"categories":1223},[193],{"categories":1225},[],{"categories":1227},[172],{"categories":1229},[],{"categories":1231},[],{"categories":1233},[],{"categories":1235},[],{"categories":1237},[203],{"categories":1239},[196],{"categories":1241},[],{"categories":1243},[151],{"categories":1245},[151],{"categories":1247},[196],{"categories":1249},[203],{"categories":1251},[],{"categories":1253},[],{"categories":1255},[154],{"categories":1257},[172],{"categories":1259},[172],{"categories":1261},[154],{"categories":1263},[145],{"categories":1265},[151,465],{"categories":1267},[],{"categories":1269},[193],{"categories":1271},[145],{"categories":1273},[154],{"categories":1275},[193],{"categories":1277},[],{"categories":1279},[154],{"categories":1281},[154],{"categories":1283},[151],{"categories":1285},[210],{"categories":1287},[203],{"categories":1289},[193],{"categories":1291},[],{"categories":1293},[154],{"categories":1295},[151],{"categories":1297},[154],{"categories":1299},[154],{"categories":1301},[154],{"categories":1303},[210],{"categories":1305},[154],{"categories":1307},[151],{"categories":1309},[],{"categories":1311},[210],{"categories":1313},[172],{"categories":1315},[154],{"categories":1317},[],{"categories":1319},[],{"categories":1321},[151],{"categories":1323},[154],{"categories":1325},[172],{"categories":1327},[154],{"categories":1329},[],{"categories":1331},[],{"categories":1333},[],{"categories":1335},[154],{"categories":1337},[],{"categories":1339},[],{"categories":1341},[196],{"categories":1343},[151],{"categories":1345},[196],{"categories":1347},[172],{"categories":1349},[151],{"categories":1351},[151],{"categories":1353},[154],{"categories":1355},[151],{"categories":1357},[],{"categories":1359},[],{"categories":1361},[465],{"categories":1363},[],{"categories":1365},[],{"categories":1367},[145],{"categories":1369},[],{"categories":1371},[],{"categories":1373},[],{"categories":1375},[],{"categories":1377},[203],{"categories":1379},[172],{"categories":1381},[210],{"categories":1383},[148],{"categories":1385},[151],{"categories":1387},[151],{"categories":1389},[148],{"categories":1391},[],{"categories":1393},[193],{"categories":1395},[154],{"categories":1397},[148],{"categories":1399},[151],{"categories":1401},[151],{"categories":1403},[145],{"categories":1405},[],{"categories":1407},[145],{"categories":1409},[151],{"categories":1411},[210],{"categories":1413},[154],{"categories":1415},[172],{"categories":1417},[148],{"categories":1419},[151],{"categories":1421},[154],{"categories":1423},[],{"categories":1425},[151],{"categories":1427},[145],{"categories":1429},[151],{"categories":1431},[],{"categories":1433},[172],{"categories":1435},[151],{"categories":1437},[],{"categories":1439},[148],{"categories":1441},[151],{"categories":1443},[],{"categories":1445},[],{"categories":1447},[],{"categories":1449},[151],{"categories":1451},[],{"categories":1453},[465],{"categories":1455},[151],{"categories":1457},[],{"categories":1459},[151],{"categories":1461},[151],{"categories":1463},[151],{"categories":1465},[151,465],{"categories":1467},[151],{"categories":1469},[151],{"categories":1471},[193],{"categories":1473},[154],{"categories":1475},[],{"categories":1477},[154],{"categories":1479},[151],{"categories":1481},[151],{"categories":1483},[151],{"categories":1485},[145],{"categories":1487},[145],{"categories":1489},[203],{"categories":1491},[193],{"categories":1493},[154],{"categories":1495},[],{"categories":1497},[151],{"categories":1499},[172],{"categories":1501},[151],{"categories":1503},[148],{"categories":1505},[],{"categories":1507},[465],{"categories":1509},[193],{"categories":1511},[193],{"categories":1513},[154],{"categories":1515},[172],{"categories":1517},[154],{"categories":1519},[151],{"categories":1521},[],{"categories":1523},[151],{"categories":1525},[],{"categories":1527},[],{"categories":1529},[151],{"categories":1531},[151],{"categories":1533},[151],{"categories":1535},[154],{"categories":1537},[151],{"categories":1539},[],{"categories":1541},[196],{"categories":1543},[154],{"categories":1545},[],{"categories":1547},[151],{"categories":1549},[172],{"categories":1551},[],{"categories":1553},[193],{"categories":1555},[465],{"categories":1557},[172],{"categories":1559},[203],{"categories":1561},[203],{"categories":1563},[172],{"categories":1565},[172],{"categories":1567},[465],{"categories":1569},[],{"categories":1571},[172],{"categories":1573},[151],{"categories":1575},[145],{"categories":1577},[172],{"categories":1579},[],{"categories":1581},[196],{"categories":1583},[172],{"categories":1585},[203],{"categories":1587},[172],{"categories":1589},[465],{"categories":1591},[151],{"categories":1593},[151],{"categories":1595},[],{"categories":1597},[148],{"categories":1599},[],{"categories":1601},[],{"categories":1603},[151],{"categories":1605},[151],{"categories":1607},[151],{"categories":1609},[151],{"categories":1611},[],{"categories":1613},[196],{"categories":1615},[145],{"categories":1617},[],{"categories":1619},[151],{"categories":1621},[151],{"categories":1623},[465],{"categories":1625},[465],{"categories":1627},[],{"categories":1629},[154],{"categories":1631},[172],{"categories":1633},[172],{"categories":1635},[151],{"categories":1637},[154],{"categories":1639},[],{"categories":1641},[193],{"categories":1643},[151],{"categories":1645},[151],{"categories":1647},[],{"categories":1649},[],{"categories":1651},[465],{"categories":1653},[151],{"categories":1655},[203],{"categories":1657},[148],{"categories":1659},[151],{"categories":1661},[],{"categories":1663},[154],{"categories":1665},[145],{"categories":1667},[145],{"categories":1669},[],{"categories":1671},[151],{"categories":1673},[193],{"categories":1675},[154],{"categories":1677},[],{"categories":1679},[151],{"categories":1681},[151],{"categories":1683},[154],{"categories":1685},[],{"categories":1687},[154],{"categories":1689},[203],{"categories":1691},[],{"categories":1693},[151],{"categories":1695},[],{"categories":1697},[151],{"categories":1699},[],{"categories":1701},[151],{"categories":1703},[151],{"categories":1705},[],{"categories":1707},[151],{"categories":1709},[172],{"categories":1711},[151],{"categories":1713},[151],{"categories":1715},[145],{"categories":1717},[151],{"categories":1719},[172],{"categories":1721},[154],{"categories":1723},[],{"categories":1725},[151],{"categories":1727},[210],{"categories":1729},[],{"categories":1731},[],{"categories":1733},[],{"categories":1735},[145],{"categories":1737},[172],{"categories":1739},[154],{"categories":1741},[151],{"categories":1743},[193],{"categories":1745},[154],{"categories":1747},[],{"categories":1749},[154],{"categories":1751},[],{"categories":1753},[151],{"categories":1755},[154],{"categories":1757},[151],{"categories":1759},[],{"categories":1761},[151],{"categories":1763},[151],{"categories":1765},[172],{"categories":1767},[193],{"categories":1769},[154],{"categories":1771},[193],{"categories":1773},[148],{"categories":1775},[],{"categories":1777},[],{"categories":1779},[151],{"categories":1781},[145],{"categories":1783},[172],{"categories":1785},[],{"categories":1787},[],{"categories":1789},[203],{"categories":1791},[193],{"categories":1793},[],{"categories":1795},[151],{"categories":1797},[],{"categories":1799},[210],{"categories":1801},[151],{"categories":1803},[465],{"categories":1805},[203],{"categories":1807},[],{"categories":1809},[154],{"categories":1811},[151],{"categories":1813},[154],{"categories":1815},[154],{"categories":1817},[151],{"categories":1819},[],{"categories":1821},[145],{"categories":1823},[151],{"categories":1825},[148],{"categories":1827},[203],{"categories":1829},[193],{"categories":1831},[],{"categories":1833},[],{"categories":1835},[],{"categories":1837},[154],{"categories":1839},[193],{"categories":1841},[172],{"categories":1843},[151],{"categories":1845},[172],{"categories":1847},[193],{"categories":1849},[],{"categories":1851},[193],{"categories":1853},[172],{"categories":1855},[148],{"categories":1857},[151],{"categories":1859},[172],{"categories":1861},[210],{"categories":1863},[],{"categories":1865},[],{"categories":1867},[196],{"categories":1869},[151,203],{"categories":1871},[172],{"categories":1873},[151],{"categories":1875},[154],{"categories":1877},[154],{"categories":1879},[151],{"categories":1881},[],{"categories":1883},[203],{"categories":1885},[151],{"categories":1887},[196],{"categories":1889},[154],{"categories":1891},[210],{"categories":1893},[465],{"categories":1895},[],{"categories":1897},[145],{"categories":1899},[154],{"categories":1901},[154],{"categories":1903},[203],{"categories":1905},[151],{"categories":1907},[151],{"categories":1909},[],{"categories":1911},[],{"categories":1913},[],{"categories":1915},[465],{"categories":1917},[172],{"categories":1919},[151],{"categories":1921},[151],{"categories":1923},[151],{"categories":1925},[],{"categories":1927},[196],{"categories":1929},[148],{"categories":1931},[],{"categories":1933},[154],{"categories":1935},[465],{"categories":1937},[],{"categories":1939},[193],{"categories":1941},[193],{"categories":1943},[],{"categories":1945},[203],{"categories":1947},[193],{"categories":1949},[151],{"categories":1951},[],{"categories":1953},[172],{"categories":1955},[151],{"categories":1957},[193],{"categories":1959},[154],{"categories":1961},[172],{"categories":1963},[],{"categories":1965},[154],{"categories":1967},[193],{"categories":1969},[151],{"categories":1971},[],{"categories":1973},[151],{"categories":1975},[151],{"categories":1977},[465],{"categories":1979},[172],{"categories":1981},[196],{"categories":1983},[196],{"categories":1985},[],{"categories":1987},[],{"categories":1989},[],{"categories":1991},[154],{"categories":1993},[203],{"categories":1995},[203],{"categories":1997},[],{"categories":1999},[],{"categories":2001},[151],{"categories":2003},[],{"categories":2005},[154],{"categories":2007},[151],{"categories":2009},[],{"categories":2011},[151],{"categories":2013},[148],{"categories":2015},[151],{"categories":2017},[210],{"categories":2019},[154],{"categories":2021},[151],{"categories":2023},[203],{"categories":2025},[172],{"categories":2027},[154],{"categories":2029},[],{"categories":2031},[172],{"categories":2033},[154],{"categories":2035},[154],{"categories":2037},[],{"categories":2039},[148],{"categories":2041},[154],{"categories":2043},[],{"categories":2045},[151],{"categories":2047},[145],{"categories":2049},[172],{"categories":2051},[465],{"categories":2053},[154],{"categories":2055},[154],{"categories":2057},[145],{"categories":2059},[151],{"categories":2061},[],{"categories":2063},[],{"categories":2065},[193],{"categories":2067},[151,148],{"categories":2069},[],{"categories":2071},[145],{"categories":2073},[196],{"categories":2075},[151],{"categories":2077},[203],{"categories":2079},[151],{"categories":2081},[154],{"categories":2083},[151],{"categories":2085},[151],{"categories":2087},[172],{"categories":2089},[154],{"categories":2091},[],{"categories":2093},[],{"categories":2095},[154],{"categories":2097},[151],{"categories":2099},[465],{"categories":2101},[],{"categories":2103},[151],{"categories":2105},[154],{"categories":2107},[],{"categories":2109},[151],{"categories":2111},[210],{"categories":2113},[196],{"categories":2115},[154],{"categories":2117},[151],{"categories":2119},[465],{"categories":2121},[],{"categories":2123},[151],{"categories":2125},[210],{"categories":2127},[193],{"categories":2129},[151],{"categories":2131},[],{"categories":2133},[210],{"categories":2135},[172],{"categories":2137},[151],{"categories":2139},[151],{"categories":2141},[145],{"categories":2143},[],{"categories":2145},[],{"categories":2147},[193],{"categories":2149},[151],{"categories":2151},[196],{"categories":2153},[210],{"categories":2155},[210],{"categories":2157},[172],{"categories":2159},[],{"categories":2161},[],{"categories":2163},[151],{"categories":2165},[],{"categories":2167},[151,203],{"categories":2169},[172],{"categories":2171},[154],{"categories":2173},[203],{"categories":2175},[151],{"categories":2177},[145],{"categories":2179},[],{"categories":2181},[],{"categories":2183},[145],{"categories":2185},[210],{"categories":2187},[151],{"categories":2189},[],{"categories":2191},[193,151],{"categories":2193},[465],{"categories":2195},[145],{"categories":2197},[],{"categories":2199},[148],{"categories":2201},[148],{"categories":2203},[151],{"categories":2205},[203],{"categories":2207},[154],{"categories":2209},[172],{"categories":2211},[210],{"categories":2213},[193],{"categories":2215},[151],{"categories":2217},[151],{"categories":2219},[151],{"categories":2221},[145],{"categories":2223},[151],{"categories":2225},[154],{"categories":2227},[172],{"categories":2229},[],{"categories":2231},[],{"categories":2233},[196],{"categories":2235},[203],{"categories":2237},[151],{"categories":2239},[193],{"categories":2241},[196],{"categories":2243},[151],{"categories":2245},[151],{"categories":2247},[154],{"categories":2249},[154],{"categories":2251},[151,148],{"categories":2253},[],{"categories":2255},[193],{"categories":2257},[],{"categories":2259},[151],{"categories":2261},[172],{"categories":2263},[145],{"categories":2265},[145],{"categories":2267},[154],{"categories":2269},[151],{"categories":2271},[148],{"categories":2273},[203],{"categories":2275},[210],{"categories":2277},[],{"categories":2279},[172],{"categories":2281},[151],{"categories":2283},[151],{"categories":2285},[172],{"categories":2287},[203],{"categories":2289},[151],{"categories":2291},[154],{"categories":2293},[172],{"categories":2295},[151],{"categories":2297},[193],{"categories":2299},[151],{"categories":2301},[151],{"categories":2303},[465],{"categories":2305},[157],{"categories":2307},[154],{"categories":2309},[151],{"categories":2311},[172],{"categories":2313},[154],{"categories":2315},[210],{"categories":2317},[151],{"categories":2319},[],{"categories":2321},[151],{"categories":2323},[],{"categories":2325},[],{"categories":2327},[],{"categories":2329},[148],{"categories":2331},[151],{"categories":2333},[154],{"categories":2335},[172],{"categories":2337},[172],{"categories":2339},[172],{"categories":2341},[172],{"categories":2343},[],{"categories":2345},[145],{"categories":2347},[154],{"categories":2349},[172],{"categories":2351},[145],{"categories":2353},[154],{"categories":2355},[151],{"categories":2357},[151,154],{"categories":2359},[154],{"categories":2361},[465],{"categories":2363},[172],{"categories":2365},[172],{"categories":2367},[154],{"categories":2369},[151],{"categories":2371},[],{"categories":2373},[172],{"categories":2375},[210],{"categories":2377},[145],{"categories":2379},[151],{"categories":2381},[151],{"categories":2383},[],{"categories":2385},[203],{"categories":2387},[],{"categories":2389},[145],{"categories":2391},[154],{"categories":2393},[172],{"categories":2395},[151],{"categories":2397},[172],{"categories":2399},[145],{"categories":2401},[172],{"categories":2403},[172],{"categories":2405},[],{"categories":2407},[148],{"categories":2409},[154],{"categories":2411},[172],{"categories":2413},[172],{"categories":2415},[172],{"categories":2417},[172],{"categories":2419},[172],{"categories":2421},[172],{"categories":2423},[172],{"categories":2425},[172],{"categories":2427},[172],{"categories":2429},[172],{"categories":2431},[196],{"categories":2433},[145],{"categories":2435},[151],{"categories":2437},[151],{"categories":2439},[],{"categories":2441},[151,145],{"categories":2443},[],{"categories":2445},[154],{"categories":2447},[172],{"categories":2449},[154],{"categories":2451},[151],{"categories":2453},[151],{"categories":2455},[151],{"categories":2457},[151],{"categories":2459},[151],{"categories":2461},[154],{"categories":2463},[148],{"categories":2465},[193],{"categories":2467},[172],{"categories":2469},[151],{"categories":2471},[],{"categories":2473},[],{"categories":2475},[154],{"categories":2477},[193],{"categories":2479},[151],{"categories":2481},[],{"categories":2483},[],{"categories":2485},[210],{"categories":2487},[151],{"categories":2489},[],{"categories":2491},[],{"categories":2493},[145],{"categories":2495},[148],{"categories":2497},[151],{"categories":2499},[148],{"categories":2501},[193],{"categories":2503},[],{"categories":2505},[172],{"categories":2507},[],{"categories":2509},[193],{"categories":2511},[151],{"categories":2513},[210],{"categories":2515},[],{"categories":2517},[210],{"categories":2519},[],{"categories":2521},[],{"categories":2523},[154],{"categories":2525},[],{"categories":2527},[148],{"categories":2529},[145],{"categories":2531},[193],{"categories":2533},[203],{"categories":2535},[],{"categories":2537},[],{"categories":2539},[151],{"categories":2541},[145],{"categories":2543},[210],{"categories":2545},[],{"categories":2547},[154],{"categories":2549},[154],{"categories":2551},[172],{"categories":2553},[151],{"categories":2555},[154],{"categories":2557},[151],{"categories":2559},[154],{"categories":2561},[151],{"categories":2563},[157],{"categories":2565},[172],{"categories":2567},[],{"categories":2569},[210],{"categories":2571},[203],{"categories":2573},[154],{"categories":2575},[],{"categories":2577},[151],{"categories":2579},[154],{"categories":2581},[148],{"categories":2583},[145],{"categories":2585},[151],{"categories":2587},[193],{"categories":2589},[203],{"categories":2591},[203],{"categories":2593},[151],{"categories":2595},[196],{"categories":2597},[151],{"categories":2599},[154],{"categories":2601},[148],{"categories":2603},[154],{"categories":2605},[151],{"categories":2607},[151],{"categories":2609},[154],{"categories":2611},[172],{"categories":2613},[],{"categories":2615},[145],{"categories":2617},[151],{"categories":2619},[154],{"categories":2621},[151],{"categories":2623},[151],{"categories":2625},[],{"categories":2627},[193],{"categories":2629},[148],{"categories":2631},[172],{"categories":2633},[151],{"categories":2635},[151],{"categories":2637},[193],{"categories":2639},[210],{"categories":2641},[196],{"categories":2643},[151],{"categories":2645},[172],{"categories":2647},[151],{"categories":2649},[154],{"categories":2651},[465],{"categories":2653},[151],{"categories":2655},[154],{"categories":2657},[196],{"categories":2659},[],{"categories":2661},[154],{"categories":2663},[203],{"categories":2665},[193],{"categories":2667},[151],{"categories":2669},[145],{"categories":2671},[148],{"categories":2673},[203],{"categories":2675},[],{"categories":2677},[154],{"categories":2679},[151],{"categories":2681},[],{"categories":2683},[172],{"categories":2685},[],{"categories":2687},[172],{"categories":2689},[151],{"categories":2691},[154],{"categories":2693},[154],{"categories":2695},[154],{"categories":2697},[],{"categories":2699},[],{"categories":2701},[151],{"categories":2703},[151],{"categories":2705},[],{"categories":2707},[193],{"categories":2709},[154],{"categories":2711},[210],{"categories":2713},[145],{"categories":2715},[],{"categories":2717},[],{"categories":2719},[172],{"categories":2721},[203],{"categories":2723},[151],{"categories":2725},[151],{"categories":2727},[151],{"categories":2729},[203],{"categories":2731},[172],{"categories":2733},[193],{"categories":2735},[151],{"categories":2737},[151],{"categories":2739},[151],{"categories":2741},[172],{"categories":2743},[151],{"categories":2745},[172],{"categories":2747},[154],{"categories":2749},[154],{"categories":2751},[203],{"categories":2753},[154],{"categories":2755},[151],{"categories":2757},[203],{"categories":2759},[193],{"categories":2761},[],{"categories":2763},[154],{"categories":2765},[],{"categories":2767},[],{"categories":2769},[148],{"categories":2771},[151],{"categories":2773},[154],{"categories":2775},[145],{"categories":2777},[154],{"categories":2779},[210],{"categories":2781},[],{"categories":2783},[154],{"categories":2785},[],{"categories":2787},[145],{"categories":2789},[154],{"categories":2791},[],{"categories":2793},[154],{"categories":2795},[151],{"categories":2797},[172],{"categories":2799},[151],{"categories":2801},[154],{"categories":2803},[172],{"categories":2805},[154],{"categories":2807},[203],{"categories":2809},[193],{"categories":2811},[145],{"categories":2813},[],{"categories":2815},[154],{"categories":2817},[193],{"categories":2819},[172],{"categories":2821},[151],{"categories":2823},[193],{"categories":2825},[145],{"categories":2827},[],{"categories":2829},[154],{"categories":2831},[154],{"categories":2833},[151],{"categories":2835},[],{"categories":2837},[154],{"categories":2839},[157],{"categories":2841},[172],{"categories":2843},[154],{"categories":2845},[148],{"categories":2847},[],{"categories":2849},[151],{"categories":2851},[157],{"categories":2853},[151],{"categories":2855},[154],{"categories":2857},[172],{"categories":2859},[145],{"categories":2861},[465],{"categories":2863},[151],{"categories":2865},[151],{"categories":2867},[151],{"categories":2869},[172],{"categories":2871},[148],{"categories":2873},[151],{"categories":2875},[193],{"categories":2877},[172],{"categories":2879},[465],{"categories":2881},[151],{"categories":2883},[],{"categories":2885},[],{"categories":2887},[465],{"categories":2889},[196],{"categories":2891},[154],{"categories":2893},[154],{"categories":2895},[172],{"categories":2897},[151],{"categories":2899},[145],{"categories":2901},[193],{"categories":2903},[154],{"categories":2905},[151],{"categories":2907},[210],{"categories":2909},[151],{"categories":2911},[154],{"categories":2913},[],{"categories":2915},[151],{"categories":2917},[151],{"categories":2919},[172],{"categories":2921},[145],{"categories":2923},[],{"categories":2925},[151],{"categories":2927},[151],{"categories":2929},[203],{"categories":2931},[193],{"categories":2933},[151,154],{"categories":2935},[210,148],{"categories":2937},[151],{"categories":2939},[],{"categories":2941},[154],{"categories":2943},[],{"categories":2945},[203],{"categories":2947},[151],{"categories":2949},[172],{"categories":2951},[],{"categories":2953},[154],{"categories":2955},[],{"categories":2957},[154],{"categories":2959},[145],{"categories":2961},[154],{"categories":2963},[151],{"categories":2965},[465],{"categories":2967},[210],{"categories":2969},[148],{"categories":2971},[148],{"categories":2973},[145],{"categories":2975},[145],{"categories":2977},[151],{"categories":2979},[154],{"categories":2981},[151],{"categories":2983},[151],{"categories":2985},[145],{"categories":2987},[151],{"categories":2989},[210],{"categories":2991},[172],{"categories":2993},[151],{"categories":2995},[154],{"categories":2997},[151],{"categories":2999},[],{"categories":3001},[203],{"categories":3003},[],{"categories":3005},[154],{"categories":3007},[145],{"categories":3009},[],{"categories":3011},[465],{"categories":3013},[151],{"categories":3015},[],{"categories":3017},[172],{"categories":3019},[154],{"categories":3021},[203],{"categories":3023},[151],{"categories":3025},[154],{"categories":3027},[203],{"categories":3029},[154],{"categories":3031},[172],{"categories":3033},[145],{"categories":3035},[172],{"categories":3037},[203],{"categories":3039},[151],{"categories":3041},[193],{"categories":3043},[151],{"categories":3045},[151],{"categories":3047},[151],{"categories":3049},[151],{"categories":3051},[154],{"categories":3053},[151],{"categories":3055},[154],{"categories":3057},[151],{"categories":3059},[145],{"categories":3061},[151],{"categories":3063},[154],{"categories":3065},[193],{"categories":3067},[145],{"categories":3069},[154],{"categories":3071},[193],{"categories":3073},[],{"categories":3075},[151],{"categories":3077},[151],{"categories":3079},[203],{"categories":3081},[],{"categories":3083},[154],{"categories":3085},[210],{"categories":3087},[151],{"categories":3089},[172],{"categories":3091},[210],{"categories":3093},[154],{"categories":3095},[148],{"categories":3097},[148],{"categories":3099},[151],{"categories":3101},[145],{"categories":3103},[],{"categories":3105},[151],{"categories":3107},[],{"categories":3109},[145],{"categories":3111},[151],{"categories":3113},[154],{"categories":3115},[154],{"categories":3117},[],{"categories":3119},[203],{"categories":3121},[203],{"categories":3123},[210],{"categories":3125},[193],{"categories":3127},[],{"categories":3129},[151],{"categories":3131},[145],{"categories":3133},[151],{"categories":3135},[203],{"categories":3137},[145],{"categories":3139},[172],{"categories":3141},[172],{"categories":3143},[],{"categories":3145},[172],{"categories":3147},[154],{"categories":3149},[193],{"categories":3151},[196],{"categories":3153},[151],{"categories":3155},[],{"categories":3157},[172],{"categories":3159},[203],{"categories":3161},[148],{"categories":3163},[151],{"categories":3165},[145],{"categories":3167},[465],{"categories":3169},[145],{"categories":3171},[],{"categories":3173},[],{"categories":3175},[172],{"categories":3177},[],{"categories":3179},[154],{"categories":3181},[154],{"categories":3183},[154],{"categories":3185},[],{"categories":3187},[151],{"categories":3189},[],{"categories":3191},[172],{"categories":3193},[145],{"categories":3195},[193],{"categories":3197},[151],{"categories":3199},[172],{"categories":3201},[172],{"categories":3203},[],{"categories":3205},[172],{"categories":3207},[145],{"categories":3209},[151],{"categories":3211},[],{"categories":3213},[154],{"categories":3215},[154],{"categories":3217},[145],{"categories":3219},[],{"categories":3221},[],{"categories":3223},[],{"categories":3225},[193],{"categories":3227},[154],{"categories":3229},[151],{"categories":3231},[],{"categories":3233},[],{"categories":3235},[],{"categories":3237},[193],{"categories":3239},[],{"categories":3241},[145],{"categories":3243},[],{"categories":3245},[],{"categories":3247},[193],{"categories":3249},[151],{"categories":3251},[172],{"categories":3253},[],{"categories":3255},[210],{"categories":3257},[172],{"categories":3259},[210],{"categories":3261},[151],{"categories":3263},[],{"categories":3265},[],{"categories":3267},[154],{"categories":3269},[],{"categories":3271},[],{"categories":3273},[154],{"categories":3275},[151],{"categories":3277},[],{"categories":3279},[154],{"categories":3281},[172],{"categories":3283},[210],{"categories":3285},[196],{"categories":3287},[154],{"categories":3289},[154],{"categories":3291},[],{"categories":3293},[],{"categories":3295},[],{"categories":3297},[172],{"categories":3299},[],{"categories":3301},[],{"categories":3303},[193],{"categories":3305},[145],{"categories":3307},[],{"categories":3309},[148],{"categories":3311},[210],{"categories":3313},[151],{"categories":3315},[203],{"categories":3317},[145],{"categories":3319},[196],{"categories":3321},[148],{"categories":3323},[203],{"categories":3325},[],{"categories":3327},[],{"categories":3329},[154],{"categories":3331},[145],{"categories":3333},[193],{"categories":3335},[145],{"categories":3337},[154],{"categories":3339},[465],{"categories":3341},[154],{"categories":3343},[],{"categories":3345},[151],{"categories":3347},[172],{"categories":3349},[203],{"categories":3351},[],{"categories":3353},[193],{"categories":3355},[172],{"categories":3357},[145],{"categories":3359},[154],{"categories":3361},[151],{"categories":3363},[148],{"categories":3365},[154,465],{"categories":3367},[154],{"categories":3369},[203],{"categories":3371},[151],{"categories":3373},[196],{"categories":3375},[210],{"categories":3377},[154],{"categories":3379},[],{"categories":3381},[154],{"categories":3383},[151],{"categories":3385},[148],{"categories":3387},[],{"categories":3389},[],{"categories":3391},[151],{"categories":3393},[196],{"categories":3395},[151],{"categories":3397},[],{"categories":3399},[172],{"categories":3401},[],{"categories":3403},[172],{"categories":3405},[203],{"categories":3407},[154],{"categories":3409},[151],{"categories":3411},[210],{"categories":3413},[203],{"categories":3415},[],{"categories":3417},[172],{"categories":3419},[151],{"categories":3421},[],{"categories":3423},[151],{"categories":3425},[154],{"categories":3427},[151],{"categories":3429},[154],{"categories":3431},[151],{"categories":3433},[151],{"categories":3435},[151],{"categories":3437},[151],{"categories":3439},[148],{"categories":3441},[],{"categories":3443},[157],{"categories":3445},[172],{"categories":3447},[151],{"categories":3449},[],{"categories":3451},[203],{"categories":3453},[151],{"categories":3455},[151],{"categories":3457},[154],{"categories":3459},[172],{"categories":3461},[151],{"categories":3463},[151],{"categories":3465},[148],{"categories":3467},[154],{"categories":3469},[193],{"categories":3471},[],{"categories":3473},[196],{"categories":3475},[151],{"categories":3477},[],{"categories":3479},[172],{"categories":3481},[210],{"categories":3483},[],{"categories":3485},[],{"categories":3487},[172],{"categories":3489},[172],{"categories":3491},[210],{"categories":3493},[145],{"categories":3495},[154],{"categories":3497},[154],{"categories":3499},[151],{"categories":3501},[148],{"categories":3503},[],{"categories":3505},[],{"categories":3507},[172],{"categories":3509},[196],{"categories":3511},[203],{"categories":3513},[154],{"categories":3515},[193],{"categories":3517},[196],{"categories":3519},[196],{"categories":3521},[],{"categories":3523},[172],{"categories":3525},[151],{"categories":3527},[151],{"categories":3529},[203],{"categories":3531},[],{"categories":3533},[172],{"categories":3535},[172],{"categories":3537},[172],{"categories":3539},[],{"categories":3541},[154],{"categories":3543},[151],{"categories":3545},[],{"categories":3547},[145],{"categories":3549},[148],{"categories":3551},[],{"categories":3553},[151],{"categories":3555},[151],{"categories":3557},[],{"categories":3559},[203],{"categories":3561},[],{"categories":3563},[],{"categories":3565},[],{"categories":3567},[],{"categories":3569},[151],{"categories":3571},[172],{"categories":3573},[],{"categories":3575},[],{"categories":3577},[151],{"categories":3579},[151],{"categories":3581},[151],{"categories":3583},[196],{"categories":3585},[151],{"categories":3587},[196],{"categories":3589},[],{"categories":3591},[196],{"categories":3593},[196],{"categories":3595},[465],{"categories":3597},[154],{"categories":3599},[203],{"categories":3601},[],{"categories":3603},[],{"categories":3605},[196],{"categories":3607},[203],{"categories":3609},[203],{"categories":3611},[203],{"categories":3613},[],{"categories":3615},[145],{"categories":3617},[203],{"categories":3619},[203],{"categories":3621},[145],{"categories":3623},[203],{"categories":3625},[148],{"categories":3627},[203],{"categories":3629},[203],{"categories":3631},[203],{"categories":3633},[196],{"categories":3635},[172],{"categories":3637},[172],{"categories":3639},[151],{"categories":3641},[203],{"categories":3643},[196],{"categories":3645},[465],{"categories":3647},[196],{"categories":3649},[196],{"categories":3651},[196],{"categories":3653},[],{"categories":3655},[148],{"categories":3657},[],{"categories":3659},[465],{"categories":3661},[203],{"categories":3663},[203],{"categories":3665},[203],{"categories":3667},[154],{"categories":3669},[172,148],{"categories":3671},[196],{"categories":3673},[],{"categories":3675},[],{"categories":3677},[196],{"categories":3679},[],{"categories":3681},[196],{"categories":3683},[172],{"categories":3685},[154],{"categories":3687},[],{"categories":3689},[203],{"categories":3691},[151],{"categories":3693},[193],{"categories":3695},[],{"categories":3697},[151],{"categories":3699},[],{"categories":3701},[172],{"categories":3703},[145],{"categories":3705},[196],{"categories":3707},[],{"categories":3709},[203],{"categories":3711},[172],[3713,3763,3898,4104],{"id":3714,"title":3715,"ai":3716,"body":3721,"categories":3749,"created_at":98,"date_modified":98,"description":91,"extension":99,"faq":98,"featured":100,"kicker_label":98,"meta":3750,"navigation":125,"path":3751,"published_at":3752,"question":98,"scraped_at":98,"seo":3753,"sitemap":3754,"source_id":3755,"source_name":3756,"source_type":132,"source_url":3757,"stem":3758,"tags":3759,"thumbnail_url":98,"tldr":3760,"tweet":98,"unknown_tags":3761,"__hash__":3762},"summaries\u002Fsummaries\u002Fgenerate-videos-by-slerp-walking-stable-diffusion--summary.md","Generate Videos by Slerp-Walking Stable Diffusion Latents",{"provider":7,"model":8,"input_tokens":3717,"output_tokens":3718,"processing_time_ms":3719,"cost_usd":3720},10775,1430,16123,0.00284735,{"type":14,"value":3722,"toc":3744},[3723,3727,3730,3734,3737,3741],[17,3724,3726],{"id":3725},"latent-space-walking-creates-hypnotic-videos","Latent Space Walking Creates Hypnotic Videos",[22,3728,3729],{},"Sample two random latents (shape 1x4x64x64 for 512x512 images), then use spherical linear interpolation (slerp) across 200 steps from init1 to init2. For each interpolated latent, run diffusion conditioned on a fixed text prompt (e.g., \"blueberry spaghetti\") with classifier-free guidance: concatenate unconditional and conditional embeddings, predict noise with UNet, apply guidance_scale=7.5, and denoise over num_inference_steps=50 using LMSDiscreteScheduler. Decode final latents via VAE to produce one frame per step. Repeat pairs up to max_frames=10000, saving JPEGs at 90% quality. Stitch with ffmpeg -r 10 -f image2 -s 512x512 -i frame%06d.jpg -vcodec libx264 -crf 10 -pix_fmt yuv420p output.mp4. This random walk yields surreal, morphing visuals without prompt changes.",[17,3731,3733],{"id":3732},"custom-diffuse-handles-guidance-and-schedulers","Custom Diffuse Handles Guidance and Schedulers",[22,3735,3736],{},"Bypass pipeline for fine control: compute unconditional embeddings from empty prompt, cat with conditional (1x77x768). Set timesteps with offset=1 if supported, eta=0.0 for DDIM compatibility. For each timestep, double latents for CFG, predict noise_pred, scale as uncond + guidance_scale*(text - uncond), step scheduler to prev_sample. Scale latents by 1\u002F0.18215 before VAE decode, clamp\u002Fpost-process to uint8 numpy. Supports LMSDiscreteScheduler (multiplies latents by sigmas initially, divides model input by sqrt(sigma^2 +1)). Slerp avoids straight-line artifacts in high-D latent space using arccos(dot) for theta, blending with sin terms if dot \u003C 0.9995.",[17,3738,3740],{"id":3739},"setup-params-and-optimizations","Setup, Params, and Optimizations",[22,3742,3743],{},"Requires Hugging Face access token for CompVis\u002Fstable-diffusion-v1-3-diffusers (or v1-4), diffusers library, torch, einops, PIL, fire (pip install fire), ~10GB VRAM for 512x512. Run: python stablediffusionwalk.py --prompt \"blueberry spaghetti\" --name outdir --num_steps 200 --num_inference_steps 50 --guidance_scale 7.5 --seed 1337 --max_frames 10000. Wrap diffuse in torch.autocast('cuda') for half-precision speedup. Higher inference steps (100-200) improve quality; guidance 3-10 tunes adherence. Users extended to prompt interpolation, fp16 models (fix dtype mismatches by upgrading diffusers\u002Ftransformers\u002Fscipy), or pipeline simplifications (pipe(prompt, latents=init, ...)).",{"title":91,"searchDepth":92,"depth":92,"links":3745},[3746,3747,3748],{"id":3725,"depth":92,"text":3726},{"id":3732,"depth":92,"text":3733},{"id":3739,"depth":92,"text":3740},[203],{},"\u002Fsummaries\u002Fgenerate-videos-by-slerp-walking-stable-diffusion-summary","2026-04-08 21:21:20",{"title":3715,"description":91},{"loc":3751},"9fd1fce56d7f77a1","Andrej Karpathy Gists","https:\u002F\u002Funknown","summaries\u002Fgenerate-videos-by-slerp-walking-stable-diffusion--summary",[138,136,137],"Interpolate random latents with slerp under a fixed prompt to create smooth, hypnotic videos from Stable Diffusion frames (50 inference steps, 7.5 guidance, 200 steps per pair).",[],"VddoAG9zJ0Akb8dH2o3dDgU_wO7ggV90n9VzfWlSvPE",{"id":3764,"title":3765,"ai":3766,"body":3771,"categories":3866,"created_at":98,"date_modified":98,"description":91,"extension":99,"faq":98,"featured":100,"kicker_label":98,"meta":3867,"navigation":125,"path":3884,"published_at":3885,"question":98,"scraped_at":3886,"seo":3887,"sitemap":3888,"source_id":3889,"source_name":3890,"source_type":132,"source_url":3891,"stem":3892,"tags":3893,"thumbnail_url":98,"tldr":3895,"tweet":98,"unknown_tags":3896,"__hash__":3897},"summaries\u002Fsummaries\u002F3082c3466d222001-ground-gemini-3-in-pdb-geometry-for-hallucination--summary.md","Ground Gemini 3 in PDB Geometry for Hallucination-Free Proteomics",{"provider":7,"model":8,"input_tokens":3767,"output_tokens":3768,"processing_time_ms":3769,"cost_usd":3770},6594,2415,25922,0.00201945,{"type":14,"value":3772,"toc":3861},[3773,3777,3780,3847,3851,3854,3858],[17,3774,3776],{"id":3775},"build-deterministic-protein-analysis-pipeline","Build Deterministic Protein Analysis Pipeline",[22,3778,3779],{},"Parse PDB files like 6M0J (SARS-CoV-2 Spike RBD bound to human ACE2) with Biopython's Bio.PDB to extract Cα backbone coordinates, reducing noise from side chains. Differentiate chains visually: Chain A (ACE2 receptor) in red, Chain E (viral Spike RBD) in blue. Use Plotly's go.Scatter3d to create connected 3D traces of the backbone, exporting as PNG for multimodal input. Configure Gemini 3 Pro API with types.ThinkingConfig(thinking_level='HIGH') and tools like run_simulation for agentic execution. Prompt combines image and text to analyze 'Red vs. Blue' spatial conflict as a molecular gateway, translating coordinates into pathogenic risk and therapeutic targets. This grounds AI in physical geometry, bypassing probabilistic text patterns.",[3781,3782,3783,3799],"table",{},[3784,3785,3786],"thead",{},[3787,3788,3789,3793,3796],"tr",{},[3790,3791,3792],"th",{},"Component",[3790,3794,3795],{},"Responsibility",[3790,3797,3798],{},"Stack",[3800,3801,3802,3814,3825,3836],"tbody",{},[3787,3803,3804,3808,3811],{},[3805,3806,3807],"td",{},"PDB Loader",[3805,3809,3810],{},"Retrieves ground truth data",[3805,3812,3813],{},"Biopython",[3787,3815,3816,3819,3822],{},[3805,3817,3818],{},"Geometric Engine",[3805,3820,3821],{},"Maps to 3D colored chains",[3805,3823,3824],{},"Plotly",[3787,3826,3827,3830,3833],{},[3805,3828,3829],{},"Multimodal Processor",[3805,3831,3832],{},"Interprets conflict",[3805,3834,3835],{},"Gemini 3 Pro (High Thinking)",[3787,3837,3838,3841,3844],{},[3805,3839,3840],{},"Agentic Controller",[3805,3842,3843],{},"Calls simulations",[3805,3845,3846],{},"Gemini SDK",[17,3848,3850],{"id":3849},"extract-actionable-insights-from-binding-interfaces","Extract Actionable Insights from Binding Interfaces",[22,3852,3853],{},"Gemini identifies the red-blue merge as the high-affinity contact zone enabling viral membrane fusion, the key target for neutralizing antibodies and vaccines. It frames ACE2 as cellular 'gateway' and Spike RBD as 'key', emphasizing physical obstruction for immunity. For drug discovery, it highlights PPIs' flat surfaces as traditionally undruggable but spots subtle energetic hotspots via coordinate precision. This accelerates in silico design of small-molecule inhibitors that wedge into the interface, cutting wet-lab costs and carbon footprint before trials. Aligns 6M0J as training data for AlphaFold 3, enabling AI to predict 'druggable pockets' invisible in static models.",[17,3855,3857],{"id":3856},"enforce-geometric-governance-to-kill-hallucinations","Enforce Geometric Governance to Kill Hallucinations",[22,3859,3860],{},"Anchor multimodal LLMs in PDB coordinates for verifiable reasoning: AI measures Cα distances, not linguistic probabilities, creating auditable 'ground truth' trails. Visual Plotly renders allow human experts to verify contact zones. H2E framework demands this accountability, evolving agents from observers to executors via tools. Scales to Sovereign AI with local A100\u002FL4 GPUs and vLLM quantization for data privacy and low-latency in aerospace (e.g., Orion ECLSS) or proteomics. Shifts from black-box hallucinations to physics-based certainty, blueprint for safety-critical domains like molecular diagnostics.",{"title":91,"searchDepth":92,"depth":92,"links":3862},[3863,3864,3865],{"id":3775,"depth":92,"text":3776},{"id":3849,"depth":92,"text":3850},{"id":3856,"depth":92,"text":3857},[],{"content_references":3868,"triage":3882},[3869,3872,3875,3878,3880],{"type":109,"title":3870,"url":3871,"context":107},"ALPHAFOLD3_GEMINI3.ipynb","https:\u002F\u002Fgithub.com\u002Ffrank-morales2020\u002FMLxDL\u002Fblob\u002Fmain\u002FALPHAFOLD3_GEMINI3.ipynb",{"type":3873,"title":3874,"context":107},"dataset","6M0J PDB structure",{"type":109,"title":3876,"url":3877,"context":107},"The Wall Before the Word: H2E Geometric Governance and the Future of AI Government","https:\u002F\u002Fmedium.com\u002Fai-simplified-in-plain-english\u002Fthe-wall-before-the-word-h2e-geometric-governance-and-the-future-of-ai-government-89ff82c7598a",{"type":114,"title":3879,"context":112},"AlphaFold 3",{"type":114,"title":3881,"context":107},"Gemini 3 Pro",{"relevance":121,"novelty":122,"quality":122,"actionability":122,"composite":123,"reasoning":3883},"Category: AI & LLMs. The article provides a detailed approach to building a deterministic protein analysis pipeline using AI tools, which directly addresses the audience's need for practical applications in AI-powered product development. It includes specific tools like Biopython and Plotly, and actionable insights for drug discovery, making it highly relevant and actionable.","\u002Fsummaries\u002F3082c3466d222001-ground-gemini-3-in-pdb-geometry-for-hallucination-summary","2026-04-19 20:16:41","2026-04-21 15:26:18",{"title":3765,"description":91},{"loc":3884},"3082c3466d222001","AI Simplified in Plain English","https:\u002F\u002Fmedium.com\u002Fai-simplified-in-plain-english\u002Fthe-convergence-of-geometric-governance-and-multimodal-ai-in-safety-critical-proteomics-with-fa8c6ba20303?source=rss----f37ab7d4e76b---4","summaries\u002F3082c3466d222001-ground-gemini-3-in-pdb-geometry-for-hallucination--summary",[3894,136,137,138],"llm","Use Biopython and Plotly to feed 3D protein structures (Red ACE2 vs. Blue Spike RBD in 6M0J PDB) into Gemini 3 Pro's high-thinking mode, enabling deterministic analysis of binding interfaces for drug discovery and safety-critical diagnostics.",[],"EVSAlvbQDEDwZ2pj0zaF21OgFD1XsUBeuYz9EVibk0g",{"id":3899,"title":3900,"ai":3901,"body":3906,"categories":4081,"created_at":98,"date_modified":98,"description":91,"extension":99,"faq":98,"featured":100,"kicker_label":98,"meta":4082,"navigation":125,"path":4090,"published_at":4091,"question":98,"scraped_at":4092,"seo":4093,"sitemap":4094,"source_id":4095,"source_name":4096,"source_type":132,"source_url":4097,"stem":4098,"tags":4099,"thumbnail_url":98,"tldr":4101,"tweet":98,"unknown_tags":4102,"__hash__":4103},"summaries\u002Fsummaries\u002F70fa59cd85bd7438-build-fno-pinn-surrogates-for-darcy-flow-with-phys-summary.md","Build FNO & PINN Surrogates for Darcy Flow with PhysicsNeMo",{"provider":7,"model":8,"input_tokens":3902,"output_tokens":3903,"processing_time_ms":3904,"cost_usd":3905},9889,3106,28970,0.00323995,{"type":14,"value":3907,"toc":4075},[3908,3912,3920,3943,3968,3972,3975,3978,3993,3997,4008,4011,4031,4035,4038,4041,4056,4059,4062,4065,4068,4071],[17,3909,3911],{"id":3910},"synthetic-darcy-flow-data-pipeline-from-grf-permeability-to-pressure-solutions","Synthetic Darcy Flow Data Pipeline: From GRF Permeability to Pressure Solutions",[22,3913,3914,3915,3919],{},"The core skill taught is generating high-fidelity training data for operator learning on the 2D Darcy equation: -∇·(k∇u) = f over ",[3916,3917,3918],"span",{},"0,1","² with Dirichlet BCs u=0. Start with DarcyFlowDataGenerator(resolution=32, length_scale=0.15, variance=1.0). It builds a Gaussian Random Field (GRF) covariance matrix for permeability k(x,y) = exp(GRF), using exponential kernel exp(-dist²\u002F(2*length_scale²)) + jitter, Cholesky decomposed for efficient sampling: z ~ N(0,I), samples = L @ z.",[22,3921,3922,3923,3926,3927,3930,3931,3934,3935,3938,3939,3942],{},"Solve for pressure u using iterative Jacobi: for interior points, u",[3916,3924,3925],{},"i,j"," = (k_e u",[3916,3928,3929],{},"i,j+1"," + k_w u",[3916,3932,3933],{},"i,j-1"," + k_n u",[3916,3936,3937],{},"i-1,j"," + k_s u",[3916,3940,3941],{},"i+1,j"," + dx² f) \u002F (k_e + k_w + k_n + k_s), converging in ~5000 steps or tol=1e-6. Generate n_samples=200 train\u002F50 test pairs. Wrap in PyTorch Dataset with channel dim and optional z-score normalization (store mean\u002Fstd for denorm). Use DataLoader(batch_size=16). Principle: GRF captures realistic heterogeneous permeability (e.g., subsurface flows); finite differences provide ground-truth without external solvers. Common mistake: Underdamped length_scale (>0.2) yields smooth k, poor generalization—use 0.1-0.15 for multiscale. Quality check: Visualize 3 samples side-by-side (viridis for k, hot for u) to confirm pressure pools in high-k regions.",[3944,3945,3948],"pre",{"className":3946,"code":3947,"language":138,"meta":91,"style":91},"language-python shiki shiki-themes github-light github-dark","# Key generation snippet\ngenerator = DarcyFlowDataGenerator(resolution=32, length_scale=0.15)\nperm_train, press_train = generator.generate_dataset(200)\n",[26,3949,3950,3957,3962],{"__ignoreMap":91},[3916,3951,3954],{"class":3952,"line":3953},"line",1,[3916,3955,3956],{},"# Key generation snippet\n",[3916,3958,3959],{"class":3952,"line":92},[3916,3960,3961],{},"generator = DarcyFlowDataGenerator(resolution=32, length_scale=0.15)\n",[3916,3963,3965],{"class":3952,"line":3964},3,[3916,3966,3967],{},"perm_train, press_train = generator.generate_dataset(200)\n",[17,3969,3971],{"id":3970},"fourier-neural-operator-spectral-kernels-for-resolution-independent-mapping","Fourier Neural Operator: Spectral Kernels for Resolution-Independent Mapping",[22,3973,3974],{},"FNO learns function-to-function operators k → u by parameterizing Fourier multipliers. Key blocks: SpectralConv2d(in_ch=1, out_ch=1, modes1=8, modes2=8) does FFT → low-freq multiply (weights ~1\u002F(in*out)) → iFFT; handles wraparound with dual weights for positive\u002Fnegative freqs. FNOBlock adds local Conv2d(1x1) residual + GELU. Full FourierNeuralOperator2D: lift k (32x32x1) + grid (x,y linspace 0-1) via Linear(3→width=32), pad=5, 4 FNOBlocks, unpad, project Linear(32→128→1). ~100k params. Forward: permute to NCHW, cat grid, process, return NC(1)HW.",[22,3976,3977],{},"Why spectral? Convolution = Fourier multiply; truncating high modes (modes=12 max for 64res) ignores noise, enables zero-shot super-res. Trade-off: Padding needed for FFT modes; fix via consistent pad\u002Funpad. Train with MSE on full fields (no points). Mistake: Forgetting grid encoding—FNOs are translation-equivariant but need pos for bounded domains. Eval: Relative L2 = ||u_pred - u|| \u002F ||u|| \u003C 1e-3 good for surrogates.",[3944,3979,3981],{"className":3946,"code":3980,"language":138,"meta":91,"style":91},"fno = FourierNeuralOperator2D(modes1=8, modes2=8, width=32, n_layers=4).to(device)\n# Forward: out = fno(perm_batch)  # learns k → u operator\n",[26,3982,3983,3988],{"__ignoreMap":91},[3916,3984,3985],{"class":3952,"line":3953},[3916,3986,3987],{},"fno = FourierNeuralOperator2D(modes1=8, modes2=8, width=32, n_layers=4).to(device)\n",[3916,3989,3990],{"class":3952,"line":92},[3916,3991,3992],{},"# Forward: out = fno(perm_batch)  # learns k → u operator\n",[17,3994,3996],{"id":3995},"physics-informed-nns-pde-residuals-without-full-data","Physics-Informed NNs: PDE Residuals Without Full Data",[22,3998,3999,4000,4003,4004,4007],{},"PINNs solve unsupervised via multi-task loss on sparse\u002Fno data. PINN_MLP(input_dim=3: x,y,k → u): Fourier embedding (sin\u002Fcos(2π B · ",[3916,4001,4002],{},"x,y","), B fixed rand, 64 freqs) + k, then Tanh MLP ",[3916,4005,4006],{},"256→128→...→1",", Xavier init. Loss (lambda_data=1, pde=1, bc=10): data MSE(u_pred, u_obs), PDE residual -k(u_xx + u_yy) -1 via dual autograd (grad(u,x)→u_x→u_xx), BC MSE(u_bc=0). Collocation: sample interior\u002Fpde\u002Fbc points uniformly.",[22,4009,4010],{},"Principle: Autodiff enforces physics everywhere; Fourier feats boost freq capture vs ReLU. Trade-off: Stiff losses (tune lambdas, start data>>physics); slower than data-driven (grad graph). Mistake: No requires_grad_(True) on coords or forgetting create_graph=True for Hessians. Quality: Balance losses \u003C1e-4 each; physics loss drops signal overfit.",[3944,4012,4014],{"className":3946,"code":4013,"language":138,"meta":91,"style":91},"pinn = PINN_MLP(hidden_dims=[128]*4, n_frequencies=64).to(device)\nloss_fn = DarcyPINNLoss()\n# Usage: losses = loss_fn(pinn, x_data,y_data,k_data,u_data, x_pde,...)\n",[26,4015,4016,4021,4026],{"__ignoreMap":91},[3916,4017,4018],{"class":3952,"line":3953},[3916,4019,4020],{},"pinn = PINN_MLP(hidden_dims=[128]*4, n_frequencies=64).to(device)\n",[3916,4022,4023],{"class":3952,"line":92},[3916,4024,4025],{},"loss_fn = DarcyPINNLoss()\n",[3916,4027,4028],{"class":3952,"line":3964},[3916,4029,4030],{},"# Usage: losses = loss_fn(pinn, x_data,y_data,k_data,u_data, x_pde,...)\n",[17,4032,4034],{"id":4033},"cnn-surrogate-baseline-and-inference-benchmarking","CNN Surrogate Baseline and Inference Benchmarking",[22,4036,4037],{},"Add convolutional surrogate: UNet-like with Conv2d blocks as baseline (not physics-aware). Train all (FNO\u002FPINN\u002FCNN) via Trainer: Adam(lr=1e-3), MSE\u002Fdata loss for supervised, full physics loss for PINN. Loop: train_epoch (zero_grad→pred→loss→backward→step), validate no_grad MSE, save best val state, CosineAnnealLR. Plot semilogy train\u002Fval curves.",[22,4039,4040],{},"Benchmark: Time 1000 inferences on test set (torch.no_grad(), sync). FNO fastest (spectral lift), CNN mid, PINN slowest (autodiff). Save torch.save(model.state_dict(), 'fno_darcy.pth'). Principle: Surrogates 1000x faster than FD solvers for repeated k. Trade-off: FNO best gen (res-invariant), PINN data-efficient but eval slow. Post-train: Denorm preds, L2\u002Frel err plots.",[3944,4042,4044],{"className":3946,"code":4043,"language":138,"meta":91,"style":91},"trainer = Trainer(fno, Adam(fno.parameters(),1e-3))\nhistory = trainer.train(train_loader, test_loader, 100)\n",[26,4045,4046,4051],{"__ignoreMap":91},[3916,4047,4048],{"class":3952,"line":3953},[3916,4049,4050],{},"trainer = Trainer(fno, Adam(fno.parameters(),1e-3))\n",[3916,4052,4053],{"class":3952,"line":92},[3916,4054,4055],{},"history = trainer.train(train_loader, test_loader, 100)\n",[22,4057,4058],{},"\"The Fourier Neural Operator (FNO) learns mappings between function spaces by parameterizing the integral kernel in Fourier space. Key insight: Convolution in physical space = multiplication in Fourier space.\"",[22,4060,4061],{},"\"Physics-Informed Neural Networks (PINNs) incorporate physical laws directly into the loss function... residual of the PDE at collocation points.\"",[22,4063,4064],{},"\"GRF for permeability: realistic heterogeneous fields critical for subsurface modeling—smooth k leads to trivial solutions.\"",[22,4066,4067],{},"\"Benchmark shows FNO at 50ms\u002Finference vs FD Jacobi 2s—key for real-time surrogates in optimization loops.\"",[22,4069,4070],{},"\"Fourier features in PINN: sine activations capture high freqs better than Tanh alone, converging 2x faster.\"",[4072,4073,4074],"style",{},"html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"title":91,"searchDepth":92,"depth":92,"links":4076},[4077,4078,4079,4080],{"id":3910,"depth":92,"text":3911},{"id":3970,"depth":92,"text":3971},{"id":3995,"depth":92,"text":3996},{"id":4033,"depth":92,"text":4034},[196],{"content_references":4083,"triage":4087},[4084],{"type":114,"title":4085,"url":4086,"context":112},"NVIDIA PhysicsNeMo","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fphysicsnemo",{"relevance":122,"novelty":3964,"quality":122,"actionability":122,"composite":4088,"reasoning":4089},3.8,"Category: AI & LLMs. The article provides a detailed step-by-step guide on building surrogate models for Darcy flow using PhysicsNeMo, which directly addresses practical applications in AI engineering. It includes specific coding examples and techniques that can be implemented, making it actionable for developers looking to integrate AI into their projects.","\u002Fsummaries\u002F70fa59cd85bd7438-build-fno-pinn-surrogates-for-darcy-flow-with-phys-summary","2026-04-13 17:07:34","2026-04-13 17:53:26",{"title":3900,"description":91},{"loc":4090},"70fa59cd85bd7438","MarkTechPost","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F04\u002F13\u002Fa-step-by-step-coding-tutorial-on-nvidia-physicsnemo-darcy-flow-fnos-pinns-surrogate-models-and-inference-benchmarking\u002F","summaries\u002F70fa59cd85bd7438-build-fno-pinn-surrogates-for-darcy-flow-with-phys-summary",[137,4100,138,136],"deep-learning","Step-by-step Colab guide: generate 2D Darcy datasets via GRF & finite differences, implement\u002Ftrain FNO operators and PINNs, add CNN baselines, benchmark inference speeds for fast physics surrogates.",[],"IPLxAt2cJRj6noXhMQUdc_wi_l1bco1LfSl-Q5gD5GI",{"id":4105,"title":4106,"ai":4107,"body":4112,"categories":4250,"created_at":98,"date_modified":98,"description":91,"extension":99,"faq":98,"featured":100,"kicker_label":98,"meta":4251,"navigation":125,"path":4272,"published_at":4273,"question":98,"scraped_at":4274,"seo":4275,"sitemap":4276,"source_id":4277,"source_name":4096,"source_type":132,"source_url":4278,"stem":4279,"tags":4280,"thumbnail_url":98,"tldr":4282,"tweet":98,"unknown_tags":4283,"__hash__":4284},"summaries\u002Fsummaries\u002F00328a14a70095c4-build-vibevoice-speech-pipelines-in-colab-summary.md","Build VibeVoice Speech Pipelines in Colab",{"provider":7,"model":8,"input_tokens":4108,"output_tokens":4109,"processing_time_ms":4110,"cost_usd":4111},9212,2845,29040,0.00324225,{"type":14,"value":4113,"toc":4244},[4114,4118,4150,4182,4186,4201,4208,4212,4215,4222,4226,4241],[17,4115,4117],{"id":4116},"setup-vibevoice-environment-for-instant-asr-and-tts","Setup VibeVoice Environment for Instant ASR and TTS",[22,4119,4120,4121,4124,4125,4130,4131,4134,4135,4138,4139,4142,4143,4145,4146,4149],{},"Install via ",[26,4122,4123],{},"!pip install git+https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Ftransformers.git"," plus torch, gradio, and clone ",[4126,4127,111],"a",{"href":111,"rel":4128},[4129],"nofollow",". Restart runtime after editable install ",[26,4132,4133],{},"-e \u002Fcontent\u002FVibeVoice",". Load 7B ASR (",[26,4136,4137],{},"microsoft\u002FVibeVoice-ASR-HF",", ~14GB download, float16 on auto device) and 0.5B TTS (",[26,4140,4141],{},"microsoft\u002FVibeVoice-Realtime-0.5B",", set DDPM steps to 20). Use ",[26,4144,28],{}," for ASR inputs and ",[26,4147,4148],{},"VibeVoiceTextTokenizerFast"," for TTS. This enables 50+ languages, single-pass 60min transcription, and ~300ms streaming latency from ultra-low 7.5Hz tokenizers combining LLM context with diffusion audio gen.",[22,4151,4152,4153,4156,4157,4160,4161,29,4164,4167,4168,4171,4172,78,4174,4177,4178,4181],{},"Key ",[26,4154,4155],{},"transcribe(audio_path, context=None)"," wraps ",[26,4158,4159],{},"apply_transcription_request"," then ",[26,4162,4163],{},"generate",[26,4165,4166],{},"decode"," (formats: 'parsed', 'transcription_only'). For TTS, ",[26,4169,4170],{},"synthesize(text, voice=\"Grace\", cfg_scale=3.0, steps=20)"," uses ",[26,4173,4163],{},[26,4175,4176],{},"return_speech=True",", ",[26,4179,4180],{},"speaker_name",", outputs 24kHz numpy audio—save via soundfile.",[17,4183,4185],{"id":4184},"unlock-asr-precision-with-speakers-context-and-batches","Unlock ASR Precision with Speakers, Context, and Batches",[22,4187,4188,4189,4192,4193,4196,4197,4200],{},"Achieve speaker diarization on podcasts: parsed output yields list of dicts with 'Speaker', 'Start\u002FEnd' timestamps (s), 'Content'—e.g., ",[3916,4190,4191],{},"Speaker 1"," 0.00s-5.23s: \"Hello...\". Context prompts fix hotwords: German sample mishears without ",[26,4194,4195],{},"context=\"About VibeVoice\"",", correctly IDs \"VibeVoice\" with it. Batch multiple audios: ",[26,4198,4199],{},"apply_transcription_request(audio=[path1,path2], prompt=[ctx1,None])"," generates all at once, decode to list of texts—scales for pipelines without loops.",[22,4202,4203,4204,4207],{},"Trade-offs: Long audio risks OOM; mitigate with ",[26,4205,4206],{},"acoustic_tokenizer_chunk_size=64000"," in generate or bfloat16 dtype. Handles MP3\u002FWAV\u002FFLAC uploads via Colab files.",[17,4209,4211],{"id":4210},"craft-expressive-tts-voices-cfg-and-long-form-scaling","Craft Expressive TTS: Voices, CFG, and Long-Form Scaling",[22,4213,4214],{},"Four presets (Carter, Grace, Emma, Davis) yield distinct styles—compare same text across voices for prosody variety. CFG scale 1-5 controls adherence (3.0 default natural), steps 5-50 trade quality\u002Fspeed (15 fast demo, 25 long-form). Generates 10min+ coherent speech: podcast script (~200 words) to 45s audio at cfg=3.5\u002Fsteps=25. Next-token diffusion ensures pauses, intonation unlike rigid TTS.",[22,4216,4217,4218,4221],{},"Real-time viable: low-param model on CUDA\u002FCPU. Gradio UI exposes text, voice dropdown, sliders for cfg\u002Fsteps—",[26,4219,4220],{},"gr.Interface(fn=tts_gradio)"," launches shareable demo.",[17,4223,4225],{"id":4224},"chain-into-speech-to-speech-pipelines-with-optimizations","Chain into Speech-to-Speech Pipelines with Optimizations",[22,4227,4228,4229,4232,4233,4236,4237,4240],{},"End-to-end: Transcribe input (",[26,4230,4231],{},"transcribe(SAMPLE_GERMAN, context=\"About VibeVoice\")"," → \"Über VibeVoice...\"), append response text, synthesize—yields conversational audio. Optimizations: ",[26,4234,4235],{},"torch.cuda.empty_cache()",", gradient checkpointing, reduce steps to 10 for speed. Download outputs like ",[26,4238,4239],{},"\u002Fcontent\u002Flongform_output.wav",". Responsible use: Research only, disclose AI speech, avoid impersonation.",[22,4242,4243],{},"Outcomes: Powers voice assistants, podcasts, accessibility—batch ASR cuts processing time, TTS enables interactive apps via Gradio.",{"title":91,"searchDepth":92,"depth":92,"links":4245},[4246,4247,4248,4249],{"id":4116,"depth":92,"text":4117},{"id":4184,"depth":92,"text":4185},{"id":4210,"depth":92,"text":4211},{"id":4224,"depth":92,"text":4225},[151],{"content_references":4252,"triage":4269},[4253,4255,4257,4260,4262,4265],{"type":114,"title":4254,"url":111,"context":112},"VibeVoice",{"type":114,"title":4256,"url":133,"context":112},"VibeVoice-ASR-HF",{"type":114,"title":4258,"url":4259,"context":112},"VibeVoice-Realtime-0.5B","https:\u002F\u002Fhuggingface.co\u002Fmicrosoft\u002FVibeVoice-Realtime-0.5B",{"type":104,"title":4261,"url":106,"context":112},"VibeVoice ASR Paper",{"type":104,"title":4263,"url":4264,"context":112},"VibeVoice TTS Paper","https:\u002F\u002Fopenreview.net\u002Fpdf?id=FihSkzyxdv",{"type":109,"title":4266,"url":4267,"context":4268},"Full Tutorial Codes","https:\u002F\u002Fgithub.com\u002FMarktechpost\u002FAI-Tutorial-Codes-Included\u002Fblob\u002Fmain\u002FVoice%20AI\u002Fmicrosoft_vibevoice_asr_realtime_tts_speech_to_speech_marktechpost.py","recommended",{"relevance":121,"novelty":122,"quality":122,"actionability":121,"composite":4270,"reasoning":4271},4.55,"Category: AI & LLMs. The article provides a detailed, hands-on tutorial for building speech pipelines using Microsoft VibeVoice, addressing practical applications for AI-powered products. It includes specific code snippets and setup instructions that developers can directly implement, making it highly actionable.","\u002Fsummaries\u002F00328a14a70095c4-build-vibevoice-speech-pipelines-in-colab-summary","2026-04-13 01:22:15","2026-04-13 17:53:25",{"title":4106,"description":91},{"loc":4272},"00328a14a70095c4","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F04\u002F12\u002Fa-hands-on-coding-tutorial-for-microsoft-vibevoice-covering-speaker-aware-asr-real-time-tts-and-speech-to-speech-pipelines\u002F","summaries\u002F00328a14a70095c4-build-vibevoice-speech-pipelines-in-colab-summary",[138,136,137,4281],"open-source","Run Microsoft VibeVoice's 7B ASR for speaker diarization and context-aware transcription plus 0.5B real-time TTS with 300ms latency using this Colab code—handles 60min audio and long-form synthesis.",[],"zmPVL5sYTbsBHWCVZHusK-U8VVYqFL1AzQHx0NUJRz8"]