[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-pytorch-nn-linear-mismatches-raw-matmul-by-1e-4-summary":3,"summaries-facets-categories":118,"summary-related-pytorch-nn-linear-mismatches-raw-matmul-by-1e-4-summary":3703},{"id":4,"title":5,"ai":6,"body":13,"categories":96,"created_at":98,"date_modified":98,"description":90,"extension":99,"faq":98,"featured":100,"kicker_label":98,"meta":101,"navigation":102,"path":103,"published_at":104,"question":98,"scraped_at":98,"seo":105,"sitemap":106,"source_id":107,"source_name":108,"source_type":109,"source_url":110,"stem":111,"tags":112,"thumbnail_url":98,"tldr":115,"tweet":98,"unknown_tags":116,"__hash__":117},"summaries\u002Fsummaries\u002Fpytorch-nn-linear-mismatches-raw-matmul-by-1e-4-summary.md","PyTorch nn.Linear Mismatches Raw Matmul by 1e-4",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","x-ai\u002Fgrok-4.1-fast",3920,1128,10617,0.00088105,{"type":14,"value":15,"toc":89},"minimark",[16,21,46,50,69,73],[17,18,20],"h2",{"id":19},"raw-matmul-preserves-precision-across-batch-sizes","Raw Matmul Preserves Precision Across Batch Sizes",[22,23,24,25,29,30,33,34,37,38,41,42,45],"p",{},"Use ",[26,27,28],"code",{},"torch.matmul"," for exact equivalence: with seed 42, ",[26,31,32],{},"x = torch.randn(2, 768)"," and ",[26,35,36],{},"w = torch.randn(768, 768)",", computing ",[26,39,40],{},"z1 = x[0] @ w"," matches ",[26,43,44],{},"(x @ w)[0]"," exactly—max absolute difference is 0. This holds because PyTorch's matrix multiply ignores batch dimensions consistently without introducing fusion artifacts.",[17,47,49],{"id":48},"nnlinear-introduces-numerical-drift","nn.Linear Introduces Numerical Drift",[22,51,52,53,56,57,60,61,64,65,68],{},"nn.Linear(768, 768, bias=False) with weight copied from ",[26,54,55],{},"w.T"," fails exactness. ",[26,58,59],{},"q1 = m(x[0])"," differs from ",[26,62,63],{},"q2 = m(x)[0]"," by max ~2e-5, and both deviate from raw ",[26,66,67],{},"z1"," by ~9e-5. Avoid assuming single-sample Linear matches batched or raw matmul outputs—use raw ops for precision-critical math.",[17,70,72],{"id":71},"root-cause-fused-operations-in-batched-mode","Root Cause: Fused Operations in Batched Mode",[22,74,75,76,80,81,84,85,88],{},"Commenter notes torch source shows fused kernels activate differently for batched (shape ",[77,78,79],"span",{},"2,768",") vs single (",[77,82,83],{},"768",") inputs, causing drift. Test by disabling autocast or fusions (e.g., ",[26,86,87],{},"torch.backends.cudnn.deterministic=True",") to isolate; impacts model debugging where exact reproducibility matters over speed.",{"title":90,"searchDepth":91,"depth":91,"links":92},"",2,[93,94,95],{"id":19,"depth":91,"text":20},{"id":48,"depth":91,"text":49},{"id":71,"depth":91,"text":72},[97],"Software Engineering",null,"md",false,{},true,"\u002Fsummaries\u002Fpytorch-nn-linear-mismatches-raw-matmul-by-1e-4-summary","2026-04-08 21:21:20",{"title":5,"description":90},{"loc":103},"c31c04ed51f90c10","Andrej Karpathy Gists","article","https:\u002F\u002Funknown","summaries\u002Fpytorch-nn-linear-mismatches-raw-matmul-by-1e-4-summary",[113,114],"python","machine-learning","Raw torch.matmul gives identical results for single vs batched inputs (diff=0), but nn.Linear differs by 2e-5 between single\u002Fbatched and 9e-5 from raw matmul due to fused ops.",[],"N4HIPkktA2CpEJX7Wbl2sDkMuAd2ARWc4-gOQSjiAUA",[119,122,125,128,131,134,136,138,140,142,144,146,149,151,153,155,157,159,161,163,165,167,170,173,175,177,179,181,183,186,188,190,192,194,196,198,200,202,204,206,208,210,212,214,216,218,220,222,224,226,228,230,232,234,236,238,240,242,244,246,248,250,252,254,256,258,260,262,264,266,268,270,272,274,276,278,280,282,284,286,288,290,292,294,296,298,300,302,304,306,308,310,312,314,316,318,320,322,324,326,328,330,332,334,336,338,340,342,344,346,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,443,445,447,449,451,453,455,457,459,461,463,465,467,469,471,473,475,477,479,481,483,485,487,489,491,493,495,497,499,501,503,505,507,509,511,513,515,517,519,521,523,525,527,529,531,533,535,537,539,541,543,545,547,549,551,553,555,557,559,561,563,565,567,569,571,573,575,577,579,581,583,585,587,589,591,593,595,597,599,601,603,605,607,609,611,613,615,617,619,621,623,625,627,629,631,633,635,637,639,641,643,645,647,649,651,653,655,657,659,661,663,665,667,669,671,673,675,677,679,681,683,685,687,689,691,693,695,697,699,701,703,705,707,709,711,713,715,717,719,721,723,725,727,729,731,733,735,737,739,741,743,745,747,749,751,753,755,757,759,761,763,765,767,769,771,773,775,777,779,781,783,785,787,789,791,793,795,797,799,801,803,805,807,809,811,813,815,817,819,821,823,825,827,829,831,833,835,837,839,841,843,845,847,849,851,853,855,857,859,861,863,865,867,869,871,873,875,877,879,881,883,885,887,889,891,893,895,897,899,901,903,905,907,909,911,913,915,917,919,921,923,925,927,929,931,933,935,937,939,941,943,945,947,949,951,953,955,957,959,961,963,965,967,969,971,973,975,977,979,981,983,985,987,989,991,993,995,997,999,1001,1003,1005,1007,1009,1011,1013,1015,1017,1019,1021,1023,1025,1027,1029,1031,1033,1035,1037,1039,1041,1043,1045,1047,1049,1051,1053,1055,1057,1059,1061,1063,1065,1067,1069,1071,1073,1075,1077,1079,1081,1083,1085,1087,1089,1091,1093,1095,1097,1099,1101,1103,1105,1107,1109,1111,1113,1115,1117,1119,1121,1123,1125,1127,1129,1131,1133,1135,1137,1139,1141,1143,1145,1147,1149,1151,1153,1155,1157,1159,1161,1163,1165,1167,1169,1171,1173,1175,1177,1179,1181,1183,1185,1187,1189,1191,1193,1195,1197,1199,1201,1203,1205,1207,1209,1211,1213,1215,1217,1219,1221,1223,1225,1227,1229,1231,1233,1235,1237,1239,1241,1243,1245,1247,1249,1251,1253,1255,1257,1259,1261,1263,1265,1267,1269,1271,1273,1275,1277,1279,1281,1283,1285,1287,1289,1291,1293,1295,1297,1299,1301,1303,1305,1307,1309,1311,1313,1315,1317,1319,1321,1323,1325,1327,1329,1331,1333,1335,1337,1339,1341,1343,1345,1347,1349,1351,1353,1355,1357,1359,1361,1363,1365,1367,1369,1371,1373,1375,1377,1379,1381,1383,1385,1387,1389,1391,1393,1395,1397,1399,1401,1403,1405,1407,1409,1411,1413,1415,1417,1419,1421,1423,1425,1427,1429,1431,1433,1435,1437,1439,1441,1443,1445,1447,1449,1451,1453,1455,1457,1459,1461,1463,1465,1467,1469,1471,1473,1475,1477,1479,1481,1483,1485,1487,1489,1491,1493,1495,1497,1499,1501,1503,1505,1507,1509,1511,1513,1515,1517,1519,1521,1523,1525,1527,1529,1531,1533,1535,1537,1539,1541,1543,1545,1547,1549,1551,1553,1555,1557,1559,1561,1563,1565,1567,1569,1571,1573,1575,1577,1579,1581,1583,1585,1587,1589,1591,1593,1595,1597,1599,1601,1603,1605,1607,1609,1611,1613,1615,1617,1619,1621,1623,1625,1627,1629,1631,1633,1635,1637,1639,1641,1643,1645,1647,1649,1651,1653,1655,1657,1659,1661,1663,1665,1667,1669,1671,1673,1675,1677,1679,1681,1683,1685,1687,1689,1691,1693,1695,1697,1699,1701,1703,1705,1707,1709,1711,1713,1715,1717,1719,1721,1723,1725,1727,1729,1731,1733,1735,1737,1739,1741,1743,1745,1747,1749,1751,1753,1755,1757,1759,1761,1763,1765,1767,1769,1771,1773,1775,1777,1779,1781,1783,1785,1787,1789,1791,1793,1795,1797,1799,1801,1803,1805,1807,1809,1811,1813,1815,1817,1819,1821,1823,1825,1827,1829,1831,1833,1835,1837,1839,1841,1843,1845,1847,1849,1851,1853,1855,1857,1859,1861,1863,1865,1867,1869,1871,1873,1875,1877,1879,1881,1883,1885,1887,1889,1891,1893,1895,1897,1899,1901,1903,1905,1907,1909,1911,1913,1915,1917,1919,1921,1923,1925,1927,1929,1931,1933,1935,1937,1939,1941,1943,1945,1947,1949,1951,1953,1955,1957,1959,1961,1963,1965,1967,1969,1971,1973,1975,1977,1979,1981,1983,1985,1987,1989,1991,1993,1995,1997,1999,2001,2003,2005,2007,2009,2011,2013,2015,2017,2019,2021,2023,2025,2027,2029,2031,2033,2035,2037,2039,2041,2043,2045,2047,2049,2051,2053,2055,2057,2059,2061,2063,2065,2067,2069,2071,2073,2075,2077,2079,2081,2083,2085,2087,2089,2091,2093,2095,2097,2099,2101,2103,2105,2107,2109,2111,2113,2115,2117,2119,2121,2123,2125,2127,2129,2131,2133,2135,2137,2139,2141,2143,2145,2147,2149,2151,2153,2155,2157,2159,2161,2163,2165,2167,2169,2171,2173,2175,2177,2179,2181,2183,2185,2187,2189,2191,2193,2195,2197,2199,2201,2203,2205,2207,2209,2211,2213,2215,2217,2219,2221,2223,2225,2227,2229,2231,2233,2235,2237,2239,2241,2243,2245,2247,2249,2251,2253,2255,2257,2259,2261,2263,2265,2267,2269,2271,2273,2275,2277,2279,2281,2283,2285,2287,2289,2291,2293,2295,2297,2299,2301,2303,2305,2307,2309,2311,2313,2315,2317,2319,2321,2323,2325,2327,2329,2331,2333,2335,2337,2339,2341,2343,2345,2347,2349,2351,2353,2355,2357,2359,2361,2363,2365,2367,2369,2371,2373,2375,2377,2379,2381,2383,2385,2387,2389,2391,2393,2395,2397,2399,2401,2403,2405,2407,2409,2411,2413,2415,2417,2419,2421,2423,2425,2427,2429,2431,2433,2435,2437,2439,2441,2443,2445,2447,2449,2451,2453,2455,2457,2459,2461,2463,2465,2467,2469,2471,2473,2475,2477,2479,2481,2483,2485,2487,2489,2491,2493,2495,2497,2499,2501,2503,2505,2507,2509,2511,2513,2515,2517,2519,2521,2523,2525,2527,2529,2531,2533,2535,2537,2539,2541,2543,2545,2547,2549,2551,2553,2555,2557,2559,2561,2563,2565,2567,2569,2571,2573,2575,2577,2579,2581,2583,2585,2587,2589,2591,2593,2595,2597,2599,2601,2603,2605,2607,2609,2611,2613,2615,2617,2619,2621,2623,2625,2627,2629,2631,2633,2635,2637,2639,2641,2643,2645,2647,2649,2651,2653,2655,2657,2659,2661,2663,2665,2667,2669,2671,2673,2675,2677,2679,2681,2683,2685,2687,2689,2691,2693,2695,2697,2699,2701,2703,2705,2707,2709,2711,2713,2715,2717,2719,2721,2723,2725,2727,2729,2731,2733,2735,2737,2739,2741,2743,2745,2747,2749,2751,2753,2755,2757,2759,2761,2763,2765,2767,2769,2771,2773,2775,2777,2779,2781,2783,2785,2787,2789,2791,2793,2795,2797,2799,2801,2803,2805,2807,2809,2811,2813,2815,2817,2819,2821,2823,2825,2827,2829,2831,2833,2835,2837,2839,2841,2843,2845,2847,2849,2851,2853,2855,2857,2859,2861,2863,2865,2867,2869,2871,2873,2875,2877,2879,2881,2883,2885,2887,2889,2891,2893,2895,2897,2899,2901,2903,2905,2907,2909,2911,2913,2915,2917,2919,2921,2923,2925,2927,2929,2931,2933,2935,2937,2939,2941,2943,2945,2947,2949,2951,2953,2955,2957,2959,2961,2963,2965,2967,2969,2971,2973,2975,2977,2979,2981,2983,2985,2987,2989,2991,2993,2995,2997,2999,3001,3003,3005,3007,3009,3011,3013,3015,3017,3019,3021,3023,3025,3027,3029,3031,3033,3035,3037,3039,3041,3043,3045,3047,3049,3051,3053,3055,3057,3059,3061,3063,3065,3067,3069,3071,3073,3075,3077,3079,3081,3083,3085,3087,3089,3091,3093,3095,3097,3099,3101,3103,3105,3107,3109,3111,3113,3115,3117,3119,3121,3123,3125,3127,3129,3131,3133,3135,3137,3139,3141,3143,3145,3147,3149,3151,3153,3155,3157,3159,3161,3163,3165,3167,3169,3171,3173,3175,3177,3179,3181,3183,3185,3187,3189,3191,3193,3195,3197,3199,3201,3203,3205,3207,3209,3211,3213,3215,3217,3219,3221,3223,3225,3227,3229,3231,3233,3235,3237,3239,3241,3243,3245,3247,3249,3251,3253,3255,3257,3259,3261,3263,3265,3267,3269,3271,3273,3275,3277,3279,3281,3283,3285,3287,3289,3291,3293,3295,3297,3299,3301,3303,3305,3307,3309,3311,3313,3315,3317,3319,3321,3323,3325,3327,3329,3331,3333,3335,3337,3339,3341,3343,3345,3347,3349,3351,3353,3355,3357,3359,3361,3363,3365,3367,3369,3371,3373,3375,3377,3379,3381,3383,3385,3387,3389,3391,3393,3395,3397,3399,3401,3403,3405,3407,3409,3411,3413,3415,3417,3419,3421,3423,3425,3427,3429,3431,3433,3435,3437,3439,3441,3443,3445,3447,3449,3451,3453,3455,3457,3459,3461,3463,3465,3467,3469,3471,3473,3475,3477,3479,3481,3483,3485,3487,3489,3491,3493,3495,3497,3499,3501,3503,3505,3507,3509,3511,3513,3515,3517,3519,3521,3523,3525,3527,3529,3531,3533,3535,3537,3539,3541,3543,3545,3547,3549,3551,3553,3555,3557,3559,3561,3563,3565,3567,3569,3571,3573,3575,3577,3579,3581,3583,3585,3587,3589,3591,3593,3595,3597,3599,3601,3603,3605,3607,3609,3611,3613,3615,3617,3619,3621,3623,3625,3627,3629,3631,3633,3635,3637,3639,3641,3643,3645,3647,3649,3651,3653,3655,3657,3659,3661,3663,3665,3667,3669,3671,3673,3675,3677,3679,3681,3683,3685,3687,3689,3691,3693,3695,3697,3699,3701],{"categories":120},[121],"Developer Productivity",{"categories":123},[124],"Business & SaaS",{"categories":126},[127],"AI & LLMs",{"categories":129},[130],"AI Automation",{"categories":132},[133],"Product Strategy",{"categories":135},[127],{"categories":137},[121],{"categories":139},[124],{"categories":141},[],{"categories":143},[127],{"categories":145},[],{"categories":147},[148],"AI News & Trends",{"categories":150},[130],{"categories":152},[148],{"categories":154},[130],{"categories":156},[130],{"categories":158},[127],{"categories":160},[127],{"categories":162},[148],{"categories":164},[127],{"categories":166},[],{"categories":168},[169],"Design & Frontend",{"categories":171},[172],"Data Science & Visualization",{"categories":174},[148],{"categories":176},[],{"categories":178},[97],{"categories":180},[127],{"categories":182},[130],{"categories":184},[185],"Marketing & Growth",{"categories":187},[127],{"categories":189},[130],{"categories":191},[],{"categories":193},[],{"categories":195},[169],{"categories":197},[130],{"categories":199},[121],{"categories":201},[169],{"categories":203},[127],{"categories":205},[130],{"categories":207},[148],{"categories":209},[],{"categories":211},[],{"categories":213},[130],{"categories":215},[97],{"categories":217},[],{"categories":219},[124],{"categories":221},[],{"categories":223},[],{"categories":225},[130],{"categories":227},[130],{"categories":229},[127],{"categories":231},[],{"categories":233},[97],{"categories":235},[],{"categories":237},[],{"categories":239},[],{"categories":241},[127],{"categories":243},[185],{"categories":245},[169],{"categories":247},[169],{"categories":249},[127],{"categories":251},[130],{"categories":253},[127],{"categories":255},[127],{"categories":257},[130],{"categories":259},[130],{"categories":261},[172],{"categories":263},[148],{"categories":265},[130],{"categories":267},[185],{"categories":269},[130],{"categories":271},[133],{"categories":273},[],{"categories":275},[130],{"categories":277},[],{"categories":279},[130],{"categories":281},[97],{"categories":283},[169],{"categories":285},[127],{"categories":287},[],{"categories":289},[],{"categories":291},[130],{"categories":293},[],{"categories":295},[127],{"categories":297},[],{"categories":299},[121],{"categories":301},[97],{"categories":303},[124],{"categories":305},[148],{"categories":307},[127],{"categories":309},[],{"categories":311},[127],{"categories":313},[],{"categories":315},[97],{"categories":317},[172],{"categories":319},[],{"categories":321},[127],{"categories":323},[169],{"categories":325},[],{"categories":327},[169],{"categories":329},[130],{"categories":331},[],{"categories":333},[130],{"categories":335},[148],{"categories":337},[124],{"categories":339},[127],{"categories":341},[],{"categories":343},[130],{"categories":345},[127],{"categories":347},[133],{"categories":349},[],{"categories":351},[127],{"categories":353},[130],{"categories":355},[130],{"categories":357},[],{"categories":359},[172],{"categories":361},[127],{"categories":363},[],{"categories":365},[121],{"categories":367},[124],{"categories":369},[127],{"categories":371},[130],{"categories":373},[97],{"categories":375},[127],{"categories":377},[],{"categories":379},[],{"categories":381},[127],{"categories":383},[],{"categories":385},[169],{"categories":387},[],{"categories":389},[127],{"categories":391},[],{"categories":393},[130],{"categories":395},[127],{"categories":397},[169],{"categories":399},[],{"categories":401},[127],{"categories":403},[127],{"categories":405},[124],{"categories":407},[130],{"categories":409},[127],{"categories":411},[169],{"categories":413},[130],{"categories":415},[],{"categories":417},[],{"categories":419},[148],{"categories":421},[],{"categories":423},[127],{"categories":425},[124,185],{"categories":427},[],{"categories":429},[127],{"categories":431},[],{"categories":433},[],{"categories":435},[127],{"categories":437},[],{"categories":439},[127],{"categories":441},[442],"DevOps & Cloud",{"categories":444},[],{"categories":446},[148],{"categories":448},[169],{"categories":450},[],{"categories":452},[148],{"categories":454},[148],{"categories":456},[127],{"categories":458},[185],{"categories":460},[],{"categories":462},[124],{"categories":464},[],{"categories":466},[127,442],{"categories":468},[127],{"categories":470},[127],{"categories":472},[130],{"categories":474},[127,97],{"categories":476},[172],{"categories":478},[127],{"categories":480},[185],{"categories":482},[130],{"categories":484},[130],{"categories":486},[],{"categories":488},[130],{"categories":490},[127,124],{"categories":492},[],{"categories":494},[169],{"categories":496},[169],{"categories":498},[],{"categories":500},[],{"categories":502},[148],{"categories":504},[],{"categories":506},[121],{"categories":508},[97],{"categories":510},[127],{"categories":512},[169],{"categories":514},[130],{"categories":516},[97],{"categories":518},[148],{"categories":520},[169],{"categories":522},[],{"categories":524},[127],{"categories":526},[127],{"categories":528},[127],{"categories":530},[148],{"categories":532},[121],{"categories":534},[127],{"categories":536},[130],{"categories":538},[442],{"categories":540},[169],{"categories":542},[130],{"categories":544},[],{"categories":546},[],{"categories":548},[169],{"categories":550},[148],{"categories":552},[172],{"categories":554},[],{"categories":556},[127],{"categories":558},[127],{"categories":560},[124],{"categories":562},[127],{"categories":564},[127],{"categories":566},[148],{"categories":568},[],{"categories":570},[130],{"categories":572},[97],{"categories":574},[],{"categories":576},[127],{"categories":578},[127],{"categories":580},[130],{"categories":582},[],{"categories":584},[],{"categories":586},[127],{"categories":588},[],{"categories":590},[124],{"categories":592},[130],{"categories":594},[],{"categories":596},[121],{"categories":598},[127],{"categories":600},[124],{"categories":602},[148],{"categories":604},[],{"categories":606},[],{"categories":608},[],{"categories":610},[148],{"categories":612},[148],{"categories":614},[],{"categories":616},[],{"categories":618},[124],{"categories":620},[],{"categories":622},[],{"categories":624},[121],{"categories":626},[],{"categories":628},[185],{"categories":630},[130],{"categories":632},[124],{"categories":634},[130],{"categories":636},[97],{"categories":638},[],{"categories":640},[133],{"categories":642},[169],{"categories":644},[97],{"categories":646},[127],{"categories":648},[130],{"categories":650},[124],{"categories":652},[127],{"categories":654},[],{"categories":656},[],{"categories":658},[97],{"categories":660},[172],{"categories":662},[133],{"categories":664},[130],{"categories":666},[127],{"categories":668},[],{"categories":670},[442],{"categories":672},[],{"categories":674},[130],{"categories":676},[],{"categories":678},[],{"categories":680},[127],{"categories":682},[169],{"categories":684},[185],{"categories":686},[130],{"categories":688},[],{"categories":690},[121],{"categories":692},[],{"categories":694},[148],{"categories":696},[127,442],{"categories":698},[148],{"categories":700},[127],{"categories":702},[124],{"categories":704},[127],{"categories":706},[],{"categories":708},[124],{"categories":710},[],{"categories":712},[97],{"categories":714},[169],{"categories":716},[148],{"categories":718},[172],{"categories":720},[121],{"categories":722},[127],{"categories":724},[97],{"categories":726},[],{"categories":728},[],{"categories":730},[133],{"categories":732},[],{"categories":734},[127],{"categories":736},[],{"categories":738},[169],{"categories":740},[169],{"categories":742},[169],{"categories":744},[],{"categories":746},[],{"categories":748},[148],{"categories":750},[130],{"categories":752},[127],{"categories":754},[127],{"categories":756},[127],{"categories":758},[124],{"categories":760},[127],{"categories":762},[],{"categories":764},[97],{"categories":766},[97],{"categories":768},[124],{"categories":770},[],{"categories":772},[127],{"categories":774},[127],{"categories":776},[124],{"categories":778},[148],{"categories":780},[185],{"categories":782},[130],{"categories":784},[],{"categories":786},[169],{"categories":788},[],{"categories":790},[127],{"categories":792},[],{"categories":794},[124],{"categories":796},[130],{"categories":798},[],{"categories":800},[442],{"categories":802},[172],{"categories":804},[97],{"categories":806},[185],{"categories":808},[97],{"categories":810},[130],{"categories":812},[],{"categories":814},[],{"categories":816},[130],{"categories":818},[121],{"categories":820},[130],{"categories":822},[133],{"categories":824},[124],{"categories":826},[],{"categories":828},[127],{"categories":830},[133],{"categories":832},[127],{"categories":834},[127],{"categories":836},[185],{"categories":838},[169],{"categories":840},[130],{"categories":842},[],{"categories":844},[],{"categories":846},[442],{"categories":848},[97],{"categories":850},[],{"categories":852},[130],{"categories":854},[127],{"categories":856},[169,127],{"categories":858},[121],{"categories":860},[],{"categories":862},[127],{"categories":864},[121],{"categories":866},[169],{"categories":868},[130],{"categories":870},[97],{"categories":872},[],{"categories":874},[127],{"categories":876},[],{"categories":878},[121],{"categories":880},[],{"categories":882},[130],{"categories":884},[133],{"categories":886},[127],{"categories":888},[127],{"categories":890},[169],{"categories":892},[130],{"categories":894},[442],{"categories":896},[169],{"categories":898},[130],{"categories":900},[127],{"categories":902},[127],{"categories":904},[127],{"categories":906},[148],{"categories":908},[],{"categories":910},[133],{"categories":912},[130],{"categories":914},[169],{"categories":916},[130],{"categories":918},[97],{"categories":920},[169],{"categories":922},[130],{"categories":924},[148],{"categories":926},[],{"categories":928},[127],{"categories":930},[169],{"categories":932},[127],{"categories":934},[121],{"categories":936},[148],{"categories":938},[127],{"categories":940},[185],{"categories":942},[127],{"categories":944},[127],{"categories":946},[130],{"categories":948},[130],{"categories":950},[127],{"categories":952},[130],{"categories":954},[169],{"categories":956},[127],{"categories":958},[],{"categories":960},[],{"categories":962},[97],{"categories":964},[],{"categories":966},[121],{"categories":968},[442],{"categories":970},[],{"categories":972},[121],{"categories":974},[124],{"categories":976},[185],{"categories":978},[],{"categories":980},[124],{"categories":982},[],{"categories":984},[],{"categories":986},[],{"categories":988},[],{"categories":990},[],{"categories":992},[127],{"categories":994},[130],{"categories":996},[442],{"categories":998},[121],{"categories":1000},[127],{"categories":1002},[97],{"categories":1004},[133],{"categories":1006},[127],{"categories":1008},[185],{"categories":1010},[127],{"categories":1012},[127],{"categories":1014},[127],{"categories":1016},[127,121],{"categories":1018},[97],{"categories":1020},[97],{"categories":1022},[169],{"categories":1024},[127],{"categories":1026},[],{"categories":1028},[],{"categories":1030},[],{"categories":1032},[97],{"categories":1034},[172],{"categories":1036},[148],{"categories":1038},[169],{"categories":1040},[],{"categories":1042},[127],{"categories":1044},[127],{"categories":1046},[],{"categories":1048},[],{"categories":1050},[130],{"categories":1052},[127],{"categories":1054},[124],{"categories":1056},[],{"categories":1058},[121],{"categories":1060},[127],{"categories":1062},[121],{"categories":1064},[127],{"categories":1066},[97],{"categories":1068},[185],{"categories":1070},[127,169],{"categories":1072},[148],{"categories":1074},[169],{"categories":1076},[],{"categories":1078},[442],{"categories":1080},[169],{"categories":1082},[130],{"categories":1084},[],{"categories":1086},[],{"categories":1088},[],{"categories":1090},[],{"categories":1092},[97],{"categories":1094},[130],{"categories":1096},[130],{"categories":1098},[442],{"categories":1100},[127],{"categories":1102},[127],{"categories":1104},[127],{"categories":1106},[],{"categories":1108},[169],{"categories":1110},[],{"categories":1112},[],{"categories":1114},[130],{"categories":1116},[],{"categories":1118},[],{"categories":1120},[185],{"categories":1122},[185],{"categories":1124},[130],{"categories":1126},[],{"categories":1128},[127],{"categories":1130},[127],{"categories":1132},[97],{"categories":1134},[169],{"categories":1136},[169],{"categories":1138},[130],{"categories":1140},[121],{"categories":1142},[127],{"categories":1144},[169],{"categories":1146},[169],{"categories":1148},[130],{"categories":1150},[130],{"categories":1152},[127],{"categories":1154},[],{"categories":1156},[],{"categories":1158},[127],{"categories":1160},[130],{"categories":1162},[148],{"categories":1164},[97],{"categories":1166},[121],{"categories":1168},[127],{"categories":1170},[],{"categories":1172},[130],{"categories":1174},[130],{"categories":1176},[],{"categories":1178},[121],{"categories":1180},[127],{"categories":1182},[121],{"categories":1184},[121],{"categories":1186},[],{"categories":1188},[],{"categories":1190},[130],{"categories":1192},[130],{"categories":1194},[127],{"categories":1196},[127],{"categories":1198},[148],{"categories":1200},[172],{"categories":1202},[133],{"categories":1204},[148],{"categories":1206},[169],{"categories":1208},[],{"categories":1210},[148],{"categories":1212},[],{"categories":1214},[],{"categories":1216},[],{"categories":1218},[],{"categories":1220},[97],{"categories":1222},[172],{"categories":1224},[],{"categories":1226},[127],{"categories":1228},[127],{"categories":1230},[172],{"categories":1232},[97],{"categories":1234},[],{"categories":1236},[],{"categories":1238},[130],{"categories":1240},[148],{"categories":1242},[148],{"categories":1244},[130],{"categories":1246},[121],{"categories":1248},[127,442],{"categories":1250},[],{"categories":1252},[169],{"categories":1254},[121],{"categories":1256},[130],{"categories":1258},[169],{"categories":1260},[],{"categories":1262},[130],{"categories":1264},[130],{"categories":1266},[127],{"categories":1268},[185],{"categories":1270},[97],{"categories":1272},[169],{"categories":1274},[],{"categories":1276},[130],{"categories":1278},[127],{"categories":1280},[130],{"categories":1282},[130],{"categories":1284},[130],{"categories":1286},[185],{"categories":1288},[130],{"categories":1290},[127],{"categories":1292},[],{"categories":1294},[185],{"categories":1296},[148],{"categories":1298},[130],{"categories":1300},[],{"categories":1302},[],{"categories":1304},[127],{"categories":1306},[130],{"categories":1308},[148],{"categories":1310},[130],{"categories":1312},[],{"categories":1314},[],{"categories":1316},[],{"categories":1318},[130],{"categories":1320},[],{"categories":1322},[],{"categories":1324},[172],{"categories":1326},[127],{"categories":1328},[172],{"categories":1330},[148],{"categories":1332},[127],{"categories":1334},[127],{"categories":1336},[130],{"categories":1338},[127],{"categories":1340},[],{"categories":1342},[],{"categories":1344},[442],{"categories":1346},[],{"categories":1348},[],{"categories":1350},[121],{"categories":1352},[],{"categories":1354},[],{"categories":1356},[],{"categories":1358},[],{"categories":1360},[97],{"categories":1362},[148],{"categories":1364},[185],{"categories":1366},[124],{"categories":1368},[127],{"categories":1370},[127],{"categories":1372},[124],{"categories":1374},[],{"categories":1376},[169],{"categories":1378},[130],{"categories":1380},[124],{"categories":1382},[127],{"categories":1384},[127],{"categories":1386},[121],{"categories":1388},[],{"categories":1390},[121],{"categories":1392},[127],{"categories":1394},[185],{"categories":1396},[130],{"categories":1398},[148],{"categories":1400},[124],{"categories":1402},[127],{"categories":1404},[130],{"categories":1406},[],{"categories":1408},[127],{"categories":1410},[121],{"categories":1412},[127],{"categories":1414},[],{"categories":1416},[148],{"categories":1418},[127],{"categories":1420},[],{"categories":1422},[124],{"categories":1424},[127],{"categories":1426},[],{"categories":1428},[],{"categories":1430},[],{"categories":1432},[127],{"categories":1434},[],{"categories":1436},[442],{"categories":1438},[127],{"categories":1440},[],{"categories":1442},[127],{"categories":1444},[127],{"categories":1446},[127],{"categories":1448},[127,442],{"categories":1450},[127],{"categories":1452},[127],{"categories":1454},[169],{"categories":1456},[130],{"categories":1458},[],{"categories":1460},[130],{"categories":1462},[127],{"categories":1464},[127],{"categories":1466},[127],{"categories":1468},[121],{"categories":1470},[121],{"categories":1472},[97],{"categories":1474},[169],{"categories":1476},[130],{"categories":1478},[],{"categories":1480},[127],{"categories":1482},[148],{"categories":1484},[127],{"categories":1486},[124],{"categories":1488},[],{"categories":1490},[442],{"categories":1492},[169],{"categories":1494},[169],{"categories":1496},[130],{"categories":1498},[148],{"categories":1500},[130],{"categories":1502},[127],{"categories":1504},[],{"categories":1506},[127],{"categories":1508},[],{"categories":1510},[],{"categories":1512},[127],{"categories":1514},[127],{"categories":1516},[127],{"categories":1518},[130],{"categories":1520},[127],{"categories":1522},[],{"categories":1524},[172],{"categories":1526},[130],{"categories":1528},[],{"categories":1530},[],{"categories":1532},[127],{"categories":1534},[148],{"categories":1536},[],{"categories":1538},[169],{"categories":1540},[442],{"categories":1542},[148],{"categories":1544},[97],{"categories":1546},[97],{"categories":1548},[148],{"categories":1550},[148],{"categories":1552},[442],{"categories":1554},[],{"categories":1556},[148],{"categories":1558},[127],{"categories":1560},[121],{"categories":1562},[148],{"categories":1564},[],{"categories":1566},[172],{"categories":1568},[148],{"categories":1570},[97],{"categories":1572},[148],{"categories":1574},[442],{"categories":1576},[127],{"categories":1578},[127],{"categories":1580},[],{"categories":1582},[124],{"categories":1584},[],{"categories":1586},[],{"categories":1588},[127],{"categories":1590},[127],{"categories":1592},[127],{"categories":1594},[127],{"categories":1596},[],{"categories":1598},[172],{"categories":1600},[121],{"categories":1602},[],{"categories":1604},[127],{"categories":1606},[127],{"categories":1608},[442],{"categories":1610},[442],{"categories":1612},[],{"categories":1614},[130],{"categories":1616},[148],{"categories":1618},[148],{"categories":1620},[127],{"categories":1622},[130],{"categories":1624},[],{"categories":1626},[169],{"categories":1628},[127],{"categories":1630},[127],{"categories":1632},[],{"categories":1634},[],{"categories":1636},[442],{"categories":1638},[127],{"categories":1640},[97],{"categories":1642},[124],{"categories":1644},[127],{"categories":1646},[],{"categories":1648},[130],{"categories":1650},[121],{"categories":1652},[121],{"categories":1654},[],{"categories":1656},[127],{"categories":1658},[169],{"categories":1660},[130],{"categories":1662},[],{"categories":1664},[127],{"categories":1666},[127],{"categories":1668},[130],{"categories":1670},[],{"categories":1672},[130],{"categories":1674},[97],{"categories":1676},[],{"categories":1678},[127],{"categories":1680},[],{"categories":1682},[127],{"categories":1684},[],{"categories":1686},[127],{"categories":1688},[127],{"categories":1690},[],{"categories":1692},[127],{"categories":1694},[148],{"categories":1696},[127],{"categories":1698},[127],{"categories":1700},[121],{"categories":1702},[127],{"categories":1704},[148],{"categories":1706},[130],{"categories":1708},[],{"categories":1710},[127],{"categories":1712},[185],{"categories":1714},[],{"categories":1716},[],{"categories":1718},[],{"categories":1720},[121],{"categories":1722},[148],{"categories":1724},[130],{"categories":1726},[127],{"categories":1728},[169],{"categories":1730},[130],{"categories":1732},[],{"categories":1734},[130],{"categories":1736},[],{"categories":1738},[127],{"categories":1740},[130],{"categories":1742},[127],{"categories":1744},[],{"categories":1746},[127],{"categories":1748},[127],{"categories":1750},[148],{"categories":1752},[169],{"categories":1754},[130],{"categories":1756},[169],{"categories":1758},[124],{"categories":1760},[],{"categories":1762},[],{"categories":1764},[127],{"categories":1766},[121],{"categories":1768},[148],{"categories":1770},[],{"categories":1772},[],{"categories":1774},[97],{"categories":1776},[169],{"categories":1778},[],{"categories":1780},[127],{"categories":1782},[],{"categories":1784},[185],{"categories":1786},[127],{"categories":1788},[442],{"categories":1790},[97],{"categories":1792},[],{"categories":1794},[130],{"categories":1796},[127],{"categories":1798},[130],{"categories":1800},[130],{"categories":1802},[127],{"categories":1804},[],{"categories":1806},[121],{"categories":1808},[127],{"categories":1810},[124],{"categories":1812},[97],{"categories":1814},[169],{"categories":1816},[],{"categories":1818},[],{"categories":1820},[],{"categories":1822},[130],{"categories":1824},[169],{"categories":1826},[148],{"categories":1828},[127],{"categories":1830},[148],{"categories":1832},[169],{"categories":1834},[],{"categories":1836},[169],{"categories":1838},[148],{"categories":1840},[124],{"categories":1842},[127],{"categories":1844},[148],{"categories":1846},[185],{"categories":1848},[],{"categories":1850},[],{"categories":1852},[172],{"categories":1854},[127,97],{"categories":1856},[148],{"categories":1858},[127],{"categories":1860},[130],{"categories":1862},[130],{"categories":1864},[127],{"categories":1866},[],{"categories":1868},[97],{"categories":1870},[127],{"categories":1872},[172],{"categories":1874},[130],{"categories":1876},[185],{"categories":1878},[442],{"categories":1880},[],{"categories":1882},[121],{"categories":1884},[130],{"categories":1886},[130],{"categories":1888},[97],{"categories":1890},[127],{"categories":1892},[127],{"categories":1894},[],{"categories":1896},[],{"categories":1898},[],{"categories":1900},[442],{"categories":1902},[148],{"categories":1904},[127],{"categories":1906},[127],{"categories":1908},[127],{"categories":1910},[],{"categories":1912},[172],{"categories":1914},[124],{"categories":1916},[],{"categories":1918},[130],{"categories":1920},[442],{"categories":1922},[],{"categories":1924},[169],{"categories":1926},[169],{"categories":1928},[],{"categories":1930},[97],{"categories":1932},[169],{"categories":1934},[127],{"categories":1936},[],{"categories":1938},[148],{"categories":1940},[127],{"categories":1942},[169],{"categories":1944},[130],{"categories":1946},[148],{"categories":1948},[],{"categories":1950},[130],{"categories":1952},[169],{"categories":1954},[127],{"categories":1956},[],{"categories":1958},[127],{"categories":1960},[127],{"categories":1962},[442],{"categories":1964},[148],{"categories":1966},[172],{"categories":1968},[172],{"categories":1970},[],{"categories":1972},[],{"categories":1974},[],{"categories":1976},[130],{"categories":1978},[97],{"categories":1980},[97],{"categories":1982},[],{"categories":1984},[],{"categories":1986},[127],{"categories":1988},[],{"categories":1990},[130],{"categories":1992},[127],{"categories":1994},[],{"categories":1996},[127],{"categories":1998},[124],{"categories":2000},[127],{"categories":2002},[185],{"categories":2004},[130],{"categories":2006},[127],{"categories":2008},[97],{"categories":2010},[148],{"categories":2012},[130],{"categories":2014},[],{"categories":2016},[148],{"categories":2018},[130],{"categories":2020},[130],{"categories":2022},[],{"categories":2024},[124],{"categories":2026},[130],{"categories":2028},[],{"categories":2030},[127],{"categories":2032},[121],{"categories":2034},[148],{"categories":2036},[442],{"categories":2038},[130],{"categories":2040},[130],{"categories":2042},[121],{"categories":2044},[127],{"categories":2046},[],{"categories":2048},[],{"categories":2050},[169],{"categories":2052},[127,124],{"categories":2054},[],{"categories":2056},[121],{"categories":2058},[172],{"categories":2060},[127],{"categories":2062},[97],{"categories":2064},[127],{"categories":2066},[130],{"categories":2068},[127],{"categories":2070},[127],{"categories":2072},[148],{"categories":2074},[130],{"categories":2076},[],{"categories":2078},[],{"categories":2080},[130],{"categories":2082},[127],{"categories":2084},[442],{"categories":2086},[],{"categories":2088},[127],{"categories":2090},[130],{"categories":2092},[],{"categories":2094},[127],{"categories":2096},[185],{"categories":2098},[172],{"categories":2100},[130],{"categories":2102},[127],{"categories":2104},[442],{"categories":2106},[],{"categories":2108},[127],{"categories":2110},[185],{"categories":2112},[169],{"categories":2114},[127],{"categories":2116},[],{"categories":2118},[185],{"categories":2120},[148],{"categories":2122},[127],{"categories":2124},[127],{"categories":2126},[121],{"categories":2128},[],{"categories":2130},[],{"categories":2132},[169],{"categories":2134},[127],{"categories":2136},[172],{"categories":2138},[185],{"categories":2140},[185],{"categories":2142},[148],{"categories":2144},[],{"categories":2146},[],{"categories":2148},[127],{"categories":2150},[],{"categories":2152},[127,97],{"categories":2154},[148],{"categories":2156},[130],{"categories":2158},[97],{"categories":2160},[127],{"categories":2162},[121],{"categories":2164},[],{"categories":2166},[],{"categories":2168},[121],{"categories":2170},[185],{"categories":2172},[127],{"categories":2174},[],{"categories":2176},[169,127],{"categories":2178},[442],{"categories":2180},[121],{"categories":2182},[],{"categories":2184},[124],{"categories":2186},[124],{"categories":2188},[127],{"categories":2190},[97],{"categories":2192},[130],{"categories":2194},[148],{"categories":2196},[185],{"categories":2198},[169],{"categories":2200},[127],{"categories":2202},[127],{"categories":2204},[127],{"categories":2206},[121],{"categories":2208},[127],{"categories":2210},[130],{"categories":2212},[148],{"categories":2214},[],{"categories":2216},[],{"categories":2218},[172],{"categories":2220},[97],{"categories":2222},[127],{"categories":2224},[169],{"categories":2226},[172],{"categories":2228},[127],{"categories":2230},[127],{"categories":2232},[130],{"categories":2234},[130],{"categories":2236},[127,124],{"categories":2238},[],{"categories":2240},[169],{"categories":2242},[],{"categories":2244},[127],{"categories":2246},[148],{"categories":2248},[121],{"categories":2250},[121],{"categories":2252},[130],{"categories":2254},[127],{"categories":2256},[124],{"categories":2258},[97],{"categories":2260},[185],{"categories":2262},[],{"categories":2264},[148],{"categories":2266},[127],{"categories":2268},[127],{"categories":2270},[148],{"categories":2272},[97],{"categories":2274},[127],{"categories":2276},[130],{"categories":2278},[148],{"categories":2280},[127],{"categories":2282},[169],{"categories":2284},[127],{"categories":2286},[127],{"categories":2288},[442],{"categories":2290},[133],{"categories":2292},[130],{"categories":2294},[127],{"categories":2296},[148],{"categories":2298},[130],{"categories":2300},[185],{"categories":2302},[127],{"categories":2304},[],{"categories":2306},[127],{"categories":2308},[],{"categories":2310},[],{"categories":2312},[],{"categories":2314},[124],{"categories":2316},[127],{"categories":2318},[130],{"categories":2320},[148],{"categories":2322},[148],{"categories":2324},[148],{"categories":2326},[148],{"categories":2328},[],{"categories":2330},[121],{"categories":2332},[130],{"categories":2334},[148],{"categories":2336},[121],{"categories":2338},[130],{"categories":2340},[127],{"categories":2342},[127,130],{"categories":2344},[130],{"categories":2346},[442],{"categories":2348},[148],{"categories":2350},[148],{"categories":2352},[130],{"categories":2354},[127],{"categories":2356},[],{"categories":2358},[148],{"categories":2360},[185],{"categories":2362},[121],{"categories":2364},[127],{"categories":2366},[127],{"categories":2368},[],{"categories":2370},[97],{"categories":2372},[],{"categories":2374},[121],{"categories":2376},[130],{"categories":2378},[148],{"categories":2380},[127],{"categories":2382},[148],{"categories":2384},[121],{"categories":2386},[148],{"categories":2388},[148],{"categories":2390},[],{"categories":2392},[124],{"categories":2394},[130],{"categories":2396},[148],{"categories":2398},[148],{"categories":2400},[148],{"categories":2402},[148],{"categories":2404},[148],{"categories":2406},[148],{"categories":2408},[148],{"categories":2410},[148],{"categories":2412},[148],{"categories":2414},[148],{"categories":2416},[172],{"categories":2418},[121],{"categories":2420},[127],{"categories":2422},[127],{"categories":2424},[],{"categories":2426},[127,121],{"categories":2428},[],{"categories":2430},[130],{"categories":2432},[148],{"categories":2434},[130],{"categories":2436},[127],{"categories":2438},[127],{"categories":2440},[127],{"categories":2442},[127],{"categories":2444},[127],{"categories":2446},[130],{"categories":2448},[124],{"categories":2450},[169],{"categories":2452},[148],{"categories":2454},[127],{"categories":2456},[],{"categories":2458},[],{"categories":2460},[130],{"categories":2462},[169],{"categories":2464},[127],{"categories":2466},[],{"categories":2468},[],{"categories":2470},[185],{"categories":2472},[127],{"categories":2474},[],{"categories":2476},[],{"categories":2478},[121],{"categories":2480},[124],{"categories":2482},[127],{"categories":2484},[124],{"categories":2486},[169],{"categories":2488},[],{"categories":2490},[148],{"categories":2492},[],{"categories":2494},[169],{"categories":2496},[127],{"categories":2498},[185],{"categories":2500},[],{"categories":2502},[185],{"categories":2504},[],{"categories":2506},[],{"categories":2508},[130],{"categories":2510},[],{"categories":2512},[124],{"categories":2514},[121],{"categories":2516},[169],{"categories":2518},[97],{"categories":2520},[],{"categories":2522},[],{"categories":2524},[127],{"categories":2526},[121],{"categories":2528},[185],{"categories":2530},[],{"categories":2532},[130],{"categories":2534},[130],{"categories":2536},[148],{"categories":2538},[127],{"categories":2540},[130],{"categories":2542},[127],{"categories":2544},[130],{"categories":2546},[127],{"categories":2548},[133],{"categories":2550},[148],{"categories":2552},[],{"categories":2554},[185],{"categories":2556},[97],{"categories":2558},[130],{"categories":2560},[],{"categories":2562},[127],{"categories":2564},[130],{"categories":2566},[124],{"categories":2568},[121],{"categories":2570},[127],{"categories":2572},[169],{"categories":2574},[97],{"categories":2576},[97],{"categories":2578},[127],{"categories":2580},[172],{"categories":2582},[127],{"categories":2584},[130],{"categories":2586},[124],{"categories":2588},[130],{"categories":2590},[127],{"categories":2592},[127],{"categories":2594},[130],{"categories":2596},[148],{"categories":2598},[],{"categories":2600},[121],{"categories":2602},[127],{"categories":2604},[130],{"categories":2606},[127],{"categories":2608},[127],{"categories":2610},[],{"categories":2612},[169],{"categories":2614},[124],{"categories":2616},[148],{"categories":2618},[127],{"categories":2620},[127],{"categories":2622},[169],{"categories":2624},[185],{"categories":2626},[172],{"categories":2628},[127],{"categories":2630},[148],{"categories":2632},[127],{"categories":2634},[130],{"categories":2636},[442],{"categories":2638},[127],{"categories":2640},[130],{"categories":2642},[172],{"categories":2644},[],{"categories":2646},[130],{"categories":2648},[97],{"categories":2650},[169],{"categories":2652},[127],{"categories":2654},[121],{"categories":2656},[124],{"categories":2658},[97],{"categories":2660},[],{"categories":2662},[130],{"categories":2664},[127],{"categories":2666},[],{"categories":2668},[148],{"categories":2670},[],{"categories":2672},[148],{"categories":2674},[127],{"categories":2676},[130],{"categories":2678},[130],{"categories":2680},[130],{"categories":2682},[],{"categories":2684},[],{"categories":2686},[127],{"categories":2688},[127],{"categories":2690},[],{"categories":2692},[169],{"categories":2694},[130],{"categories":2696},[185],{"categories":2698},[121],{"categories":2700},[],{"categories":2702},[],{"categories":2704},[148],{"categories":2706},[97],{"categories":2708},[127],{"categories":2710},[127],{"categories":2712},[127],{"categories":2714},[97],{"categories":2716},[148],{"categories":2718},[169],{"categories":2720},[127],{"categories":2722},[127],{"categories":2724},[127],{"categories":2726},[148],{"categories":2728},[127],{"categories":2730},[148],{"categories":2732},[130],{"categories":2734},[130],{"categories":2736},[97],{"categories":2738},[130],{"categories":2740},[127],{"categories":2742},[97],{"categories":2744},[169],{"categories":2746},[],{"categories":2748},[130],{"categories":2750},[],{"categories":2752},[],{"categories":2754},[],{"categories":2756},[124],{"categories":2758},[127],{"categories":2760},[130],{"categories":2762},[121],{"categories":2764},[130],{"categories":2766},[185],{"categories":2768},[],{"categories":2770},[130],{"categories":2772},[],{"categories":2774},[121],{"categories":2776},[130],{"categories":2778},[],{"categories":2780},[130],{"categories":2782},[127],{"categories":2784},[148],{"categories":2786},[127],{"categories":2788},[130],{"categories":2790},[148],{"categories":2792},[130],{"categories":2794},[97],{"categories":2796},[169],{"categories":2798},[121],{"categories":2800},[],{"categories":2802},[130],{"categories":2804},[169],{"categories":2806},[442],{"categories":2808},[148],{"categories":2810},[127],{"categories":2812},[169],{"categories":2814},[121],{"categories":2816},[],{"categories":2818},[130],{"categories":2820},[130],{"categories":2822},[127],{"categories":2824},[],{"categories":2826},[130],{"categories":2828},[133],{"categories":2830},[148],{"categories":2832},[130],{"categories":2834},[124],{"categories":2836},[],{"categories":2838},[127],{"categories":2840},[133],{"categories":2842},[127],{"categories":2844},[130],{"categories":2846},[148],{"categories":2848},[121],{"categories":2850},[442],{"categories":2852},[127],{"categories":2854},[127],{"categories":2856},[127],{"categories":2858},[148],{"categories":2860},[124],{"categories":2862},[127],{"categories":2864},[169],{"categories":2866},[148],{"categories":2868},[442],{"categories":2870},[127],{"categories":2872},[],{"categories":2874},[],{"categories":2876},[442],{"categories":2878},[172],{"categories":2880},[130],{"categories":2882},[130],{"categories":2884},[148],{"categories":2886},[127],{"categories":2888},[121],{"categories":2890},[169],{"categories":2892},[130],{"categories":2894},[127],{"categories":2896},[185],{"categories":2898},[127],{"categories":2900},[130],{"categories":2902},[],{"categories":2904},[127],{"categories":2906},[127],{"categories":2908},[148],{"categories":2910},[121],{"categories":2912},[],{"categories":2914},[127],{"categories":2916},[127],{"categories":2918},[97],{"categories":2920},[169],{"categories":2922},[127,130],{"categories":2924},[185,124],{"categories":2926},[127],{"categories":2928},[],{"categories":2930},[130],{"categories":2932},[],{"categories":2934},[97],{"categories":2936},[127],{"categories":2938},[148],{"categories":2940},[],{"categories":2942},[130],{"categories":2944},[],{"categories":2946},[169],{"categories":2948},[130],{"categories":2950},[121],{"categories":2952},[130],{"categories":2954},[127],{"categories":2956},[442],{"categories":2958},[185],{"categories":2960},[124],{"categories":2962},[124],{"categories":2964},[121],{"categories":2966},[121],{"categories":2968},[127],{"categories":2970},[130],{"categories":2972},[127],{"categories":2974},[127],{"categories":2976},[121],{"categories":2978},[127],{"categories":2980},[185],{"categories":2982},[148],{"categories":2984},[127],{"categories":2986},[130],{"categories":2988},[127],{"categories":2990},[],{"categories":2992},[97],{"categories":2994},[],{"categories":2996},[130],{"categories":2998},[121],{"categories":3000},[],{"categories":3002},[442],{"categories":3004},[127],{"categories":3006},[],{"categories":3008},[148],{"categories":3010},[130],{"categories":3012},[97],{"categories":3014},[127],{"categories":3016},[130],{"categories":3018},[97],{"categories":3020},[130],{"categories":3022},[148],{"categories":3024},[121],{"categories":3026},[148],{"categories":3028},[97],{"categories":3030},[127],{"categories":3032},[169],{"categories":3034},[127],{"categories":3036},[127],{"categories":3038},[127],{"categories":3040},[127],{"categories":3042},[130],{"categories":3044},[127],{"categories":3046},[130],{"categories":3048},[127],{"categories":3050},[121],{"categories":3052},[127],{"categories":3054},[130],{"categories":3056},[169],{"categories":3058},[121],{"categories":3060},[130],{"categories":3062},[169],{"categories":3064},[],{"categories":3066},[127],{"categories":3068},[127],{"categories":3070},[97],{"categories":3072},[],{"categories":3074},[130],{"categories":3076},[185],{"categories":3078},[127],{"categories":3080},[148],{"categories":3082},[185],{"categories":3084},[130],{"categories":3086},[124],{"categories":3088},[124],{"categories":3090},[127],{"categories":3092},[121],{"categories":3094},[],{"categories":3096},[127],{"categories":3098},[],{"categories":3100},[121],{"categories":3102},[127],{"categories":3104},[130],{"categories":3106},[130],{"categories":3108},[],{"categories":3110},[97],{"categories":3112},[97],{"categories":3114},[185],{"categories":3116},[169],{"categories":3118},[],{"categories":3120},[127],{"categories":3122},[121],{"categories":3124},[127],{"categories":3126},[97],{"categories":3128},[121],{"categories":3130},[148],{"categories":3132},[148],{"categories":3134},[],{"categories":3136},[148],{"categories":3138},[130],{"categories":3140},[169],{"categories":3142},[172],{"categories":3144},[127],{"categories":3146},[],{"categories":3148},[148],{"categories":3150},[97],{"categories":3152},[124],{"categories":3154},[127],{"categories":3156},[121],{"categories":3158},[442],{"categories":3160},[121],{"categories":3162},[],{"categories":3164},[],{"categories":3166},[148],{"categories":3168},[],{"categories":3170},[130],{"categories":3172},[130],{"categories":3174},[130],{"categories":3176},[],{"categories":3178},[127],{"categories":3180},[],{"categories":3182},[148],{"categories":3184},[121],{"categories":3186},[169],{"categories":3188},[127],{"categories":3190},[148],{"categories":3192},[148],{"categories":3194},[],{"categories":3196},[148],{"categories":3198},[121],{"categories":3200},[127],{"categories":3202},[],{"categories":3204},[130],{"categories":3206},[130],{"categories":3208},[121],{"categories":3210},[],{"categories":3212},[],{"categories":3214},[],{"categories":3216},[169],{"categories":3218},[130],{"categories":3220},[127],{"categories":3222},[],{"categories":3224},[],{"categories":3226},[],{"categories":3228},[169],{"categories":3230},[],{"categories":3232},[121],{"categories":3234},[],{"categories":3236},[],{"categories":3238},[169],{"categories":3240},[127],{"categories":3242},[148],{"categories":3244},[],{"categories":3246},[185],{"categories":3248},[148],{"categories":3250},[185],{"categories":3252},[127],{"categories":3254},[],{"categories":3256},[],{"categories":3258},[130],{"categories":3260},[],{"categories":3262},[],{"categories":3264},[130],{"categories":3266},[127],{"categories":3268},[],{"categories":3270},[130],{"categories":3272},[148],{"categories":3274},[185],{"categories":3276},[172],{"categories":3278},[130],{"categories":3280},[130],{"categories":3282},[],{"categories":3284},[],{"categories":3286},[],{"categories":3288},[148],{"categories":3290},[],{"categories":3292},[],{"categories":3294},[169],{"categories":3296},[121],{"categories":3298},[],{"categories":3300},[124],{"categories":3302},[185],{"categories":3304},[127],{"categories":3306},[97],{"categories":3308},[121],{"categories":3310},[172],{"categories":3312},[124],{"categories":3314},[97],{"categories":3316},[],{"categories":3318},[],{"categories":3320},[130],{"categories":3322},[121],{"categories":3324},[169],{"categories":3326},[121],{"categories":3328},[130],{"categories":3330},[442],{"categories":3332},[130],{"categories":3334},[],{"categories":3336},[127],{"categories":3338},[148],{"categories":3340},[97],{"categories":3342},[],{"categories":3344},[169],{"categories":3346},[148],{"categories":3348},[121],{"categories":3350},[130],{"categories":3352},[127],{"categories":3354},[124],{"categories":3356},[130,442],{"categories":3358},[130],{"categories":3360},[97],{"categories":3362},[127],{"categories":3364},[172],{"categories":3366},[185],{"categories":3368},[130],{"categories":3370},[],{"categories":3372},[130],{"categories":3374},[127],{"categories":3376},[124],{"categories":3378},[],{"categories":3380},[],{"categories":3382},[127],{"categories":3384},[172],{"categories":3386},[127],{"categories":3388},[],{"categories":3390},[148],{"categories":3392},[],{"categories":3394},[148],{"categories":3396},[97],{"categories":3398},[130],{"categories":3400},[127],{"categories":3402},[185],{"categories":3404},[97],{"categories":3406},[],{"categories":3408},[148],{"categories":3410},[127],{"categories":3412},[],{"categories":3414},[127],{"categories":3416},[130],{"categories":3418},[127],{"categories":3420},[130],{"categories":3422},[127],{"categories":3424},[127],{"categories":3426},[127],{"categories":3428},[127],{"categories":3430},[124],{"categories":3432},[],{"categories":3434},[133],{"categories":3436},[148],{"categories":3438},[127],{"categories":3440},[],{"categories":3442},[97],{"categories":3444},[127],{"categories":3446},[127],{"categories":3448},[130],{"categories":3450},[148],{"categories":3452},[127],{"categories":3454},[127],{"categories":3456},[124],{"categories":3458},[130],{"categories":3460},[169],{"categories":3462},[],{"categories":3464},[172],{"categories":3466},[127],{"categories":3468},[],{"categories":3470},[148],{"categories":3472},[185],{"categories":3474},[],{"categories":3476},[],{"categories":3478},[148],{"categories":3480},[148],{"categories":3482},[185],{"categories":3484},[121],{"categories":3486},[130],{"categories":3488},[130],{"categories":3490},[127],{"categories":3492},[124],{"categories":3494},[],{"categories":3496},[],{"categories":3498},[148],{"categories":3500},[172],{"categories":3502},[97],{"categories":3504},[130],{"categories":3506},[169],{"categories":3508},[172],{"categories":3510},[172],{"categories":3512},[],{"categories":3514},[148],{"categories":3516},[127],{"categories":3518},[127],{"categories":3520},[97],{"categories":3522},[],{"categories":3524},[148],{"categories":3526},[148],{"categories":3528},[148],{"categories":3530},[],{"categories":3532},[130],{"categories":3534},[127],{"categories":3536},[],{"categories":3538},[121],{"categories":3540},[124],{"categories":3542},[],{"categories":3544},[127],{"categories":3546},[127],{"categories":3548},[],{"categories":3550},[97],{"categories":3552},[],{"categories":3554},[],{"categories":3556},[],{"categories":3558},[],{"categories":3560},[127],{"categories":3562},[148],{"categories":3564},[],{"categories":3566},[],{"categories":3568},[127],{"categories":3570},[127],{"categories":3572},[127],{"categories":3574},[172],{"categories":3576},[127],{"categories":3578},[172],{"categories":3580},[],{"categories":3582},[172],{"categories":3584},[172],{"categories":3586},[442],{"categories":3588},[130],{"categories":3590},[97],{"categories":3592},[],{"categories":3594},[],{"categories":3596},[172],{"categories":3598},[97],{"categories":3600},[97],{"categories":3602},[97],{"categories":3604},[],{"categories":3606},[121],{"categories":3608},[97],{"categories":3610},[97],{"categories":3612},[121],{"categories":3614},[97],{"categories":3616},[124],{"categories":3618},[97],{"categories":3620},[97],{"categories":3622},[97],{"categories":3624},[172],{"categories":3626},[148],{"categories":3628},[148],{"categories":3630},[127],{"categories":3632},[97],{"categories":3634},[172],{"categories":3636},[442],{"categories":3638},[172],{"categories":3640},[172],{"categories":3642},[172],{"categories":3644},[],{"categories":3646},[124],{"categories":3648},[],{"categories":3650},[442],{"categories":3652},[97],{"categories":3654},[97],{"categories":3656},[97],{"categories":3658},[130],{"categories":3660},[148,124],{"categories":3662},[172],{"categories":3664},[],{"categories":3666},[],{"categories":3668},[172],{"categories":3670},[],{"categories":3672},[172],{"categories":3674},[148],{"categories":3676},[130],{"categories":3678},[],{"categories":3680},[97],{"categories":3682},[127],{"categories":3684},[169],{"categories":3686},[],{"categories":3688},[127],{"categories":3690},[],{"categories":3692},[148],{"categories":3694},[121],{"categories":3696},[172],{"categories":3698},[],{"categories":3700},[97],{"categories":3702},[148],[3704,3770,3927,4049],{"id":3705,"title":3706,"ai":3707,"body":3712,"categories":3740,"created_at":98,"date_modified":98,"description":90,"extension":99,"faq":98,"featured":100,"kicker_label":98,"meta":3741,"navigation":102,"path":3757,"published_at":3758,"question":98,"scraped_at":3759,"seo":3760,"sitemap":3761,"source_id":3762,"source_name":3763,"source_type":109,"source_url":3764,"stem":3765,"tags":3766,"thumbnail_url":98,"tldr":3767,"tweet":98,"unknown_tags":3768,"__hash__":3769},"summaries\u002Fsummaries\u002F092f953f13e749e1-reproduce-2011-sentiment-word-vectors-in-python-summary.md","Reproduce 2011 Sentiment Word Vectors in Python",{"provider":7,"model":8,"input_tokens":3708,"output_tokens":3709,"processing_time_ms":3710,"cost_usd":3711},3933,1516,16200,0.00152195,{"type":14,"value":3713,"toc":3735},[3714,3718,3721,3725,3728,3732],[17,3715,3717],{"id":3716},"elegant-core-technique-semantic-learning-from-ratings","Elegant Core Technique: Semantic Learning from Ratings",[22,3719,3720],{},"Maas et al. (2011) train sentiment-specific word vectors directly from unlabeled IMDb movie reviews paired with star ratings (1-10 scale). Words co-occurring in high-rated reviews pull closer in vector space; low-rated push apart. This creates representations capturing sentiment polarity without explicit labels. Final classification uses linear SVM on averaged review vectors, achieving strong accuracy through interpretable, low-dimensional embeddings. Author notes its logistic regression-like simplicity: powerful when data aligns with task, avoiding black-box complexity.",[17,3722,3724],{"id":3723},"reproduction-insights-and-modern-relevance","Reproduction Insights and Modern Relevance",[22,3726,3727],{},"Reproducing the paper in Python reveals its enduring strength – elegant semantic learning outperforms hype-driven alternatives in targeted tasks like sentiment. Author challenges original methods, tests against other representations (including LLMs), and automates full pipeline. Trade-off: excels on review-style text but needs domain data; not general-purpose like transformers. GitHub repo provides end-to-end code for immediate use or extension.",[17,3729,3731],{"id":3730},"practical-takeaways-for-builders","Practical Takeaways for Builders",[22,3733,3734],{},"Start with this for sentiment features in products: download IMDb data, train vectors via contrastive objective on ratings, classify with SVM. Scales to custom corpora (e.g., product feedback). Compares favorably to LLMs on cost\u002Finterpretability; use as baseline before deploying APIs. Avoids overfitting by leveraging vast unlabeled text – key for production ML pipelines.",{"title":90,"searchDepth":91,"depth":91,"links":3736},[3737,3738,3739],{"id":3716,"depth":91,"text":3717},{"id":3723,"depth":91,"text":3724},{"id":3730,"depth":91,"text":3731},[172],{"content_references":3742,"triage":3752},[3743,3748],{"type":3744,"title":3745,"author":3746,"context":3747},"paper","Learning Word Vectors for Sentiment Analysis","Maas et al.","mentioned",{"type":3749,"title":3750,"url":3751,"context":3747},"other","Sentiment_analysis","https:\u002F\u002Fgithub.com\u002FJumbong\u002FSentiment_analysis",{"relevance":3753,"novelty":3754,"quality":3754,"actionability":3753,"composite":3755,"reasoning":3756},5,4,4.55,"Category: AI & LLMs. The article provides a practical method for building sentiment-aware word embeddings, which is directly applicable for product builders looking to integrate sentiment analysis into their AI-powered products. It includes actionable steps and a GitHub repository for implementation, making it highly relevant and actionable.","\u002Fsummaries\u002F092f953f13e749e1-reproduce-2011-sentiment-word-vectors-in-python-summary","2026-05-10 00:01:00","2026-05-10 15:26:28",{"title":3706,"description":90},{"loc":3757},"092f953f13e749e1","Towards AI","https:\u002F\u002Fpub.towardsai.net\u002Flearning-word-vectors-for-sentiment-analysis-a-python-reproduction-f8c8c77df38f?source=rss----98111c9905da---4","summaries\u002F092f953f13e749e1-reproduce-2011-sentiment-word-vectors-in-python-summary",[113,114],"Build sentiment-aware word embeddings from IMDb reviews via semantic learning with star ratings and linear SVM classification, reproducing Maas et al. (2011) – simple method rivals modern LLMs.",[],"v2XTBE5rFNMZcIts4tjxKmc0d5a3j51Waw-d4ggTQcI",{"id":3771,"title":3772,"ai":3773,"body":3778,"categories":3916,"created_at":98,"date_modified":98,"description":90,"extension":99,"faq":98,"featured":100,"kicker_label":98,"meta":3917,"navigation":102,"path":3918,"published_at":104,"question":98,"scraped_at":98,"seo":3919,"sitemap":3920,"source_id":3921,"source_name":108,"source_type":109,"source_url":110,"stem":3922,"tags":3923,"thumbnail_url":98,"tldr":3924,"tweet":98,"unknown_tags":3925,"__hash__":3926},"summaries\u002Fsummaries\u002Fnes-optimizes-quadratic-bowl-via-gaussian-perturba-summary.md","NES optimizes quadratic bowl via gaussian perturbations",{"provider":7,"model":8,"input_tokens":3774,"output_tokens":3775,"processing_time_ms":3776,"cost_usd":3777},8855,1292,10281,0.0019466,{"type":14,"value":3779,"toc":3911},[3780,3784,3787,3824,3835,3848,3851,3855,3858,3873,3876,3880,3907],[17,3781,3783],{"id":3782},"nes-core-loop-for-black-box-optimization","NES Core Loop for Black-Box Optimization",[22,3785,3786],{},"NES treats parameters w as mean of a fixed-variance gaussian (sigma=0.1). To maximize black-box reward f(w) without gradients:",[3788,3789,3790,3794,3814,3817],"ol",{},[3791,3792,3793],"li",{},"Generate npop=50 noise samples N ~ N(0,1) (shape 50x3).",[3791,3795,3796,3797,3800,3801,3803,3804,3806,3807,3809,3810,3813],{},"Perturb: w_try",[77,3798,3799],{},"j"," = w + sigma * N",[77,3802,3799],{},", compute R",[77,3805,3799],{}," = f(w_try",[77,3808,3799],{},"). Here f(w) = -||w - ",[77,3811,3812],{},"0.5,0.1,-0.3","||^2_2 (max reward=0 at solution).",[3791,3815,3816],{},"Standardize: A = (R - mean(R)) \u002F std(R) to zero-mean unit-variance (avoids div-by-zero on flat rewards; speeds convergence vs raw R).",[3791,3818,3819,3820,3823],{},"Update: w += alpha\u002F(npop * sigma) * N.T @ A (alpha=0.001). This is score-function gradient estimator E",[77,3821,3822],{},"reward * noise","\u002Fsigma.",[22,3825,3826,3827,3830,3831,3834],{},"Starts from random w≈",[77,3828,3829],{},"1.76,0.40,0.98"," (reward -3.32), reaches ",[77,3832,3833],{},"-0.000009"," error by iter 280.",[3836,3837,3840],"pre",{"className":3838,"code":3839,"language":113,"meta":90,"style":90},"language-python shiki shiki-themes github-light github-dark","w = w + alpha\u002F(npop*sigma) * np.dot(N.T, A)\n",[26,3841,3842],{"__ignoreMap":90},[77,3843,3846],{"class":3844,"line":3845},"line",1,[77,3847,3839],{},[22,3849,3850],{},"sigma scales perturbation size and normalizes estimator (divisor matches multiplier for consistent gradient scale).",[17,3852,3854],{"id":3853},"proven-convergence-on-toy-quadratic","Proven Convergence on Toy Quadratic",[22,3856,3857],{},"300 iters suffice; prints every 20 show steady progress:",[3859,3860,3861,3864,3867,3870],"ul",{},[3791,3862,3863],{},"Iter 0: reward -3.323",[3791,3865,3866],{},"Iter 100: -0.727",[3791,3868,3869],{},"Iter 200: -0.001",[3791,3871,3872],{},"Iter 280: -0.000009",[22,3874,3875],{},"Toy mimics NN optimization: f(w) would forward NN on env, return total reward. Solution hidden from optimizer.",[17,3877,3879],{"id":3878},"insights-from-implementers","Insights from Implementers",[3859,3881,3882,3889,3895,3901],{},[3791,3883,3884,3888],{},[3885,3886,3887],"strong",{},"Standardization optional but boosts speed",": Raw R works (paper-equivalent via Section 3.2), but centering\u002Fscaling prevents stagnation on negative\u002Fflat rewards.",[3791,3890,3891,3894],{},[3885,3892,3893],{},"Edge cases",": Add epsilon to std(R) avoids div0 when all R equal (common early\u002Fsimple problems).",[3791,3896,3897,3900],{},[3885,3898,3899],{},"Extensions",": Handles moving targets with small jitters; libs like evostra apply to Flappy Bird. No crossover needed vs GA—NES is gradient-like via log-prob derivative.",[3791,3902,3903,3906],{},[3885,3904,3905],{},"Deployment",": Save final w; reconstruct NN. Practical for RL vs DQN (no backprop, parallelizable evals).",[3908,3909,3910],"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":90,"searchDepth":91,"depth":91,"links":3912},[3913,3914,3915],{"id":3782,"depth":91,"text":3783},{"id":3853,"depth":91,"text":3854},{"id":3878,"depth":91,"text":3879},[172],{},"\u002Fsummaries\u002Fnes-optimizes-quadratic-bowl-via-gaussian-perturba-summary",{"title":3772,"description":90},{"loc":3918},"24c62cc73ee60bc6","summaries\u002Fnes-optimizes-quadratic-bowl-via-gaussian-perturba-summary",[113,114],"Sample 50 perturbed weights from N(w, 0.1), weight by standardized rewards, update w by 0.001\u002F(50*0.1) * sum(noise * weights) to converge in 300 iters.",[],"THgP6_hPLQzW9Arl2BqfDCHYij8HS6-ncC3XkmeXu-Y",{"id":3928,"title":3929,"ai":3930,"body":3935,"categories":4036,"created_at":98,"date_modified":98,"description":90,"extension":99,"faq":98,"featured":100,"kicker_label":98,"meta":4037,"navigation":102,"path":4038,"published_at":4039,"question":98,"scraped_at":98,"seo":4040,"sitemap":4041,"source_id":4042,"source_name":4043,"source_type":109,"source_url":110,"stem":4044,"tags":4045,"thumbnail_url":98,"tldr":4046,"tweet":98,"unknown_tags":4047,"__hash__":4048},"summaries\u002Fsummaries\u002Ffix-randomness-first-for-stable-ml-pipelines-summary.md","Fix Randomness First for Stable ML Pipelines",{"provider":7,"model":8,"input_tokens":3931,"output_tokens":3932,"processing_time_ms":3933,"cost_usd":3934},3629,1311,12564,0.0013588,{"type":14,"value":3936,"toc":4032},[3937,3941,3944,3948,3951,4017,4024,4030],[17,3938,3940],{"id":3939},"pipelines-not-models-break-ml-systems","Pipelines, Not Models, Break ML Systems",[22,3942,3943],{},"After 4+ years building ML systems, the core failure mode isn't weak models but unstable pipelines that produce inconsistent results. A one-time success turns into quiet failures without disciplined stability practices. Treat stability as a non-negotiable discipline, not an afterthought.",[17,3945,3947],{"id":3946},"enforce-reproducibility-by-seeding-everything","Enforce Reproducibility by Seeding Everything",[22,3949,3950],{},"Randomness turns models into unreliable slot machines—results vary per run, undermining debugging and deployment. Fix it with a global seed function covering all sources:",[3836,3952,3954],{"className":3838,"code":3953,"language":113,"meta":90,"style":90},"import random\nimport numpy as np\nimport torch\n\ndef set_seed(seed=42):\n    random.seed(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed_all(seed)\n\nset_seed(42)\n",[26,3955,3956,3961,3966,3972,3977,3982,3988,3994,4000,4006,4011],{"__ignoreMap":90},[77,3957,3958],{"class":3844,"line":3845},[77,3959,3960],{},"import random\n",[77,3962,3963],{"class":3844,"line":91},[77,3964,3965],{},"import numpy as np\n",[77,3967,3969],{"class":3844,"line":3968},3,[77,3970,3971],{},"import torch\n",[77,3973,3974],{"class":3844,"line":3754},[77,3975,3976],{"emptyLinePlaceholder":102},"\n",[77,3978,3979],{"class":3844,"line":3753},[77,3980,3981],{},"def set_seed(seed=42):\n",[77,3983,3985],{"class":3844,"line":3984},6,[77,3986,3987],{},"    random.seed(seed)\n",[77,3989,3991],{"class":3844,"line":3990},7,[77,3992,3993],{},"    np.random.seed(seed)\n",[77,3995,3997],{"class":3844,"line":3996},8,[77,3998,3999],{},"    torch.manual_seed(seed)\n",[77,4001,4003],{"class":3844,"line":4002},9,[77,4004,4005],{},"    torch.cuda.manual_seed_all(seed)\n",[77,4007,4009],{"class":3844,"line":4008},10,[77,4010,3976],{"emptyLinePlaceholder":102},[77,4012,4014],{"class":3844,"line":4013},11,[77,4015,4016],{},"set_seed(42)\n",[22,4018,4019,4020,4023],{},"Call this early. ",[3885,4021,4022],{},"Key caveat:"," Seeds don't fully eliminate non-determinism in some GPU operations—explicitly configure those for true reproducibility.",[22,4025,4026],{},[4027,4028,4029],"em",{},"Note: Article outlines 9 rules total but details only the first here.",[3908,4031,3910],{},{"title":90,"searchDepth":91,"depth":91,"links":4033},[4034,4035],{"id":3939,"depth":91,"text":3940},{"id":3946,"depth":91,"text":3947},[172],{},"\u002Fsummaries\u002Ffix-randomness-first-for-stable-ml-pipelines-summary","2026-04-08 21:21:17",{"title":3929,"description":90},{"loc":4038},"ed293f2ee2f46e73","Python in Plain English","summaries\u002Ffix-randomness-first-for-stable-ml-pipelines-summary",[113,114],"ML systems fail from unstable pipelines, not bad models—control randomness by setting seeds across random, NumPy, and PyTorch to ensure reproducible results.",[],"w_GpfcH_eP9a4oHynSujBQl1BptGg4S_T_nFYUIStoo",{"id":4050,"title":4051,"ai":4052,"body":4057,"categories":4085,"created_at":98,"date_modified":98,"description":90,"extension":99,"faq":98,"featured":100,"kicker_label":98,"meta":4086,"navigation":102,"path":4087,"published_at":104,"question":98,"scraped_at":98,"seo":4088,"sitemap":4089,"source_id":4090,"source_name":108,"source_type":109,"source_url":110,"stem":4091,"tags":4092,"thumbnail_url":98,"tldr":4094,"tweet":98,"unknown_tags":4095,"__hash__":4096},"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":4053,"output_tokens":4054,"processing_time_ms":4055,"cost_usd":4056},10775,1430,16123,0.00284735,{"type":14,"value":4058,"toc":4080},[4059,4063,4066,4070,4073,4077],[17,4060,4062],{"id":4061},"latent-space-walking-creates-hypnotic-videos","Latent Space Walking Creates Hypnotic Videos",[22,4064,4065],{},"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.",[17,4067,4069],{"id":4068},"custom-diffuse-handles-guidance-and-schedulers","Custom Diffuse Handles Guidance and Schedulers",[22,4071,4072],{},"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.",[17,4074,4076],{"id":4075},"setup-params-and-optimizations","Setup, Params, and Optimizations",[22,4078,4079],{},"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":90,"searchDepth":91,"depth":91,"links":4081},[4082,4083,4084],{"id":4061,"depth":91,"text":4062},{"id":4068,"depth":91,"text":4069},{"id":4075,"depth":91,"text":4076},[97],{},"\u002Fsummaries\u002Fgenerate-videos-by-slerp-walking-stable-diffusion-summary",{"title":4051,"description":90},{"loc":4087},"9fd1fce56d7f77a1","summaries\u002Fgenerate-videos-by-slerp-walking-stable-diffusion--summary",[113,4093,114],"ai-tools","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"]