{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/census/sigmoid","entry":"sigmoid","source":"Syntology differential census (groundwork/55, run v2_2026-09-22), per sample; not an archive number","census_date":"2026-09-22","battery_sha256":["b986f7e04d794a0d88ad4c5f32cf63ec3590b5deff0192150737bc5f1c0b4677"],"runner_sha256":["5a452d0e7c0da5b80771d1be2afe3572e253568cf5c5d59a0d08ebd663d00808"],"bucket_key":"positional (rank, kind, dtype) of each array argument; the argument name is not part of the key because the harness draws the shared array from (rank, kind) and casts it to the dtype, whatever the name","bucket_fields":["rank","kind","dtype"],"claim":"Implementations sharing this entry name were each run on one shared input fixed by the positional (rank, kind, dtype) of their array arguments (the bucket). A cluster is the set whose recorded output digest (sha256 of the output rounded to 6 decimals) is identical. Identical values to six decimals on the shared input are agreement on those inputs, not a statement about the whole domain and not a substitution claim.","n_implementations_compared":36,"n_papers":56,"n_buckets":3,"n_distinct_outputs":7,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":0,"by_error":{}},"no_array_argument_ran_on_own_fixture_arguments_only":{"n":5,"n_papers":7,"recorded_shared_digest_equals_own_fixture_digest":5},"output_not_digested_non_numeric":{"n":0,"by_type":{}}},"withdrawn_excluded":0,"code_page":"/code/sigmoid","buckets":[{"bucket":[[1,"float","float64"]],"n_implementations_compared":18,"n_papers":36,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"2091c6f76edebb04","size":15,"n_papers":33,"shape":[8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":5.551115123125783e-17,"members_with_recorded_values":15,"torch_reference_conventions_with_this_digest":[],"values":[0.2882519628322799,0.5392022378925179,0.7104585180504956,0.31816978031374316,0.4560498300643325,0.5132548239196687,0.16404413905099488,0.4557328740372635],"values_recorded":8,"members":[{"code_sha256_prefix":"b8e95809ca2c17c9","path":"Model/MuSeGNN_all_tissues.py","papers":["2010.01823","2310.02275","2410.01692","1809.10765","2011.12379","2204.04606","2403.12729","2107.02363","2210.04563","2505.11532","2602.12113"],"paper_pages":[{"arxiv_id":"2010.01823","page":"/paper/quantifying-statistical-significance-of-1"},{"arxiv_id":"2310.02275","page":"/paper/muse-gnn-learning-unified-gene-representation"},{"arxiv_id":"2410.01692","page":"/paper/u-shaped-and-inverted-u-scaling-behind"},{"arxiv_id":"1809.10765","page":"/paper/auto-encoding-knockoff-generator-for-fdr"},{"arxiv_id":"2011.12379","page":"/paper/invariant-representation-learning-for"},{"arxiv_id":"2204.04606","page":"/paper/towards-efficient-representation"},{"arxiv_id":"2403.12729","page":"/paper/posterior-uncertainty-quantification-in"},{"arxiv_id":"2107.02363","page":"/paper/asymptotics-of-network-embeddings-learned-via"},{"arxiv_id":"2210.04563","page":"/paper/towards-robust-visual-question-answering"},{"arxiv_id":"2505.11532","page":"/paper/revisiting-adversarial-perception-attacks-and"},{"arxiv_id":"2602.12113","page":"/paper/arxiv-2602-12113"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"f35babe3912ec8b1","path":"scripts/metrics/calculate_AR_RPR.py","papers":["2309.03020","1506.02640","2212.13345","2310.17488","2606.03432"],"paper_pages":[{"arxiv_id":"2309.03020","page":"/paper/seal-a-framework-for-systematic-evaluation-of"},{"arxiv_id":"1506.02640","page":"/paper/you-only-look-once-unified-real-time-object"},{"arxiv_id":"2212.13345","page":"/paper/the-forward-forward-algorithm-some-1"},{"arxiv_id":"2310.17488","page":"/paper/lightlm-a-lightweight-deep-and-narrow"},{"arxiv_id":"2606.03432","page":"/paper/arxiv-2606-03432"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"152398a541d26c5a","path":"algos/dps.py","papers":["2209.14687","2401.02683"],"paper_pages":[{"arxiv_id":"2209.14687","page":"/paper/diffusion-posterior-sampling-for-general"},{"arxiv_id":"2401.02683","page":"/paper/geometric-facilitated-denoising-diffusion"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"a911f9cacbc9faf4","path":"svm_logreg/logreg.py","papers":["2402.14992","2506.05454"],"paper_pages":[{"arxiv_id":"2402.14992","page":"/paper/tinybenchmarks-evaluating-llms-with-fewer"},{"arxiv_id":"2506.05454","page":"/paper/zeroth-order-optimization-finds-flat-minima"}],"arg_sig_recorded":[["z",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"b30dd0f0a1d1fde8","path":"logistic.py","papers":["2404.19620","1906.01827"],"paper_pages":[{"arxiv_id":"2404.19620","page":"/paper/be-aware-of-the-neighborhood-effect-modeling"},{"arxiv_id":"1906.01827","page":"/paper/data-sketching-for-faster-training-of-machine"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"b7880bde365e8087","path":"test_iteration_conf_gnn.py","papers":["2001.06807","2403.09346"],"paper_pages":[{"arxiv_id":"2001.06807","page":"/paper/zero-shot-video-object-segmentation-via-1"},{"arxiv_id":"2403.09346","page":"/paper/avibench-towards-evaluating-the-robustness-of"}],"arg_sig_recorded":[["inX",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"1846a09dc0fdcb18","path":"zero-shot/zero_shot.py","papers":["2305.19894"],"paper_pages":[{"arxiv_id":"2305.19894","page":"/paper/med-unic-unifying-cross-lingual-medical-1"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"1a3c174f69eae69e","path":"RVFL.py","papers":["2608.13628"],"paper_pages":[{"arxiv_id":"2608.13628","page":"/paper/arxiv-2608-13628"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"2d3e248be1323d2c","path":"main_1d_20190924.py","papers":["1901.06523"],"paper_pages":[{"arxiv_id":"1901.06523","page":"/paper/frequency-principle-fourier-analysis-sheds"}],"arg_sig_recorded":[["xx",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"2f53c83eaf660d6a","path":"random_mutation_search.py","papers":["2103.15692"],"paper_pages":[{"arxiv_id":"2103.15692","page":"/paper/self-constructing-neural-networks-through"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"4adb351c2e3a7b3f","path":"disentanglement_lib/visualize/visualize_model.py","papers":["1811.12359"],"paper_pages":[{"arxiv_id":"1811.12359","page":"/paper/challenging-common-assumptions-in-the"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"549a2707b6d65eb6","path":"algorithms.py","papers":["2402.11338"],"paper_pages":[{"arxiv_id":"2402.11338","page":"/paper/fair-classification-with-partial-feedback-an"}],"arg_sig_recorded":[["inx",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"6c965eb305670ea0","path":"glad.py","papers":["2403.16883"],"paper_pages":[{"arxiv_id":"2403.16883","page":"/paper/discrete-latent-graph-generative-modeling"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"ea4aa57fb84c5048","path":"hierarchical/mixed_level1.py","papers":["2007.01162"],"paper_pages":[{"arxiv_id":"2007.01162","page":"/paper/tilted-empirical-risk-minimization"}],"arg_sig_recorded":[["z",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"f082a972a9ba05d6","path":"PeerLoss.py","papers":["2011.00379"],"paper_pages":[{"arxiv_id":"2011.00379","page":"/paper/fair-classification-with-group-dependent"}],"arg_sig_recorded":[["z",1,"float","float64"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"a95d9807cc1ee100","size":1,"n_papers":1,"shape":[8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.03217414468038876,0.08763429039561701,0.1676481216405795,0.03689112197637966,0.06438908539205362,0.07966053593821808,0.01585262927181038,0.06431215147258919],"values_recorded":8,"members":[{"code_sha256_prefix":"0ed3188ebf111362","path":"dataset.py","papers":["2203.09175"],"paper_pages":[{"arxiv_id":"2203.09175","page":"/paper/generalized-classification-of-satellite-image"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{"L":"1.0","x0":"2.5","k":"1.0","b":"0.0"},"class_bearing":false}]},{"output_sha":"cb4c711ae1bf4621","size":1,"n_papers":1,"shape":[8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.42349607433544023,0.07840447578503573,0.4209170361009913,-0.3636604393725137,-0.08790033987133505,0.026509647839337402,-0.6719117218980102,-0.08853425192547304],"values_recorded":8,"members":[{"code_sha256_prefix":"697dfbb9c3926b6f","path":"evosoro/tools/utils.py","papers":["1706.07296"],"paper_pages":[{"arxiv_id":"1706.07296","page":"/paper/a-minimal-developmental-model-can-increase"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"cc60658c28a2d0b6","size":1,"n_papers":1,"shape":[8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.32670824378485114,0.5313849740831288,0.6721861929752942,0.3521147608108879,0.46480717742147837,0.5106047535899763,0.21370218634034574,0.4645528990161512],"values_recorded":8,"members":[{"code_sha256_prefix":"c4ae0f426946c27a","path":"imagenet.py","papers":["2201.12826"],"paper_pages":[{"arxiv_id":"2201.12826","page":"/paper/optimizing-gradient-driven-criteria-in"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{"beta":"0.8"},"class_bearing":false}]}]},{"bucket":[[2,"float","float64"]],"n_implementations_compared":13,"n_papers":13,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"cac27aad11ab81b7","size":12,"n_papers":12,"shape":[4,8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":8.293591302610537e-08,"members_with_recorded_values":12,"torch_reference_conventions_with_this_digest":[],"values":[0.858468621376573,0.17744184601589594,0.6168154702259908,0.3338357709433185,0.28846527715346565,0.26299275751235635,0.3401196812506377,0.6394295800875605,0.6268848889747983,0.7229507157094218,0.4019853580442092,0.17245199936194505,0.42836253890044174,0.9106916079843409,0.37407272098405303,0.6342582167264833,0.5165927655890226,0.16480868184208033,0.6063777438705528,0.3998270276655192,0.49435168423503684,0.234911549545933,0.36891640750867927,0.7278366470220043,0.3109647679974984,0.6066552955283155,0.7201040477475936,0.7344889034902604,0.2269198654303603,0.7814639293605683,0.21044886594945497,0.35569259414527093],"values_recorded":32,"members":[{"code_sha256_prefix":"19ed4e8df05cecee","path":"image_classification/assistant.py","papers":["1905.03381"],"paper_pages":[{"arxiv_id":"1905.03381","page":"/paper/190503381"}],"arg_sig_recorded":[["x",2,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"1f96ec62dab33fe2","path":"transformer.py","papers":["1706.03762"],"paper_pages":[{"arxiv_id":"1706.03762","page":"/paper/attention-is-all-you-need"}],"arg_sig_recorded":[["hs",2,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"58eb8e19abd6d694","path":"DP_FL_MNIST_logistic_FINAL.py","papers":["2106.09779"],"paper_pages":[{"arxiv_id":"2106.09779","page":"/paper/locally-differentially-private-federated"}],"arg_sig_recorded":[["z",2,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"5f33cd0434b7657c","path":"predict.py","papers":["1804.02767"],"paper_pages":[{"arxiv_id":"1804.02767","page":"/paper/yolov3-an-incremental-improvement"}],"arg_sig_recorded":[["z",2,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"604c5823be725722","path":"nmodel.py","papers":["2306.01896"],"paper_pages":[{"arxiv_id":"2306.01896","page":"/paper/tackling-unbounded-state-spaces-in-continuing"}],"arg_sig_recorded":[["x",2,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"6bb3881c24f66b23","path":"train_lottery.py","papers":["1905.01067"],"paper_pages":[{"arxiv_id":"1905.01067","page":"/paper/deconstructing-lottery-tickets-zeros-signs"}],"arg_sig_recorded":[["x",2,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"78fdd4365700a723","path":"maxoutCNN.py","papers":["1511.02583"],"paper_pages":[{"arxiv_id":"1511.02583","page":"/paper/batch-normalized-maxout-network-in-network"}],"arg_sig_recorded":[["array",2,"float","float64"]],"scalar_args":{"deriv":"False"},"class_bearing":false},{"code_sha256_prefix":"c803a6bd4c1c93ac","path":"mll_sgd.py","papers":["2007.13819"],"paper_pages":[{"arxiv_id":"2007.13819","page":"/paper/multi-level-local-sgd-for-heterogeneous"}],"arg_sig_recorded":[["z",2,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"d05c71a4b943dde3","path":"src/oxonfair/learners/fair_frontier.py","papers":["2203.04913"],"paper_pages":[{"arxiv_id":"2203.04913","page":"/paper/leveling-down-in-computer-vision-pareto"}],"arg_sig_recorded":[["x",2,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"d3cb240d60e1166a","path":"src/ppi_aipw/_api.py","papers":["2604.21260"],"paper_pages":[{"arxiv_id":"2604.21260","page":"/paper/arxiv-2604-21260"}],"arg_sig_recorded":[["z",2,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"d4621865e9ec9367","path":"prompteval/methods.py","papers":["2405.17202"],"paper_pages":[{"arxiv_id":"2405.17202","page":"/paper/efficient-multi-prompt-evaluation-of-llms"}],"arg_sig_recorded":[["x",2,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"e21f85087b040589","path":"RBM_ICML.py","papers":["2302.12431"],"paper_pages":[{"arxiv_id":"2302.12431","page":"/paper/flexible-phase-dynamics-for-bio-plausible"}],"arg_sig_recorded":[["x",2,"float","float64"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"886b5e96fd4d7034","size":1,"n_papers":1,"shape":[4,8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.9985183902396595,3.834372649535252e-05,0.4701022463511252,0.0025875953802529396,0.0008981746144578504,0.00047469838355624114,0.0029771577217111663,0.590116282539495,0.5235774423622994,0.9085226324869213,0.011140139497871298,3.225707517199952e-05,0.019027195237289785,0.9998895176514663,0.006218924930122754,0.5628269004039411,0.10265903167605493,2.4559736466391214e-05,0.4159448132671749,0.010655890282118781,0.06830827219204305,0.0002239392125158183,0.005572401145867029,0.9182174952449208,0.0015344250489936458,0.4173581492100772,0.9024623827469747,0.9300586924008427,0.0001788241398649616,0.9795896082477679,0.00011041993280257101,0.004191294829488244],"values_recorded":32,"members":[{"code_sha256_prefix":"8716af66856e8e15","path":"dev/model_validation_experiment.py","papers":["2205.13600"],"paper_pages":[{"arxiv_id":"2205.13600","page":"/paper/myosuite-a-contact-rich-simulation-suite-for"}],"arg_sig_recorded":[["x",2,"float","float64"]],"scalar_args":{"k":"5.0","x0":"0.5"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"]],"n_implementations_compared":5,"n_papers":7,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"c774619a31ae147c","size":5,"n_papers":7,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":5,"torch_reference_conventions_with_this_digest":["torch"],"values":[0.8584686517715454,0.17744185030460358,0.6168155074119568,0.33383578062057495,0.288465291261673,0.2629927694797516,0.3401196599006653,0.6394296288490295,0.6268848776817322,0.7229506969451904,0.4019853472709656,0.17245200276374817,0.42836251854896545,0.9106916189193726,0.37407273054122925,0.6342582106590271,0.5165927410125732,0.16480867564678192,0.6063777804374695,0.3998270332813263,0.49435165524482727,0.23491153120994568,0.368916392326355,0.7278366088867188,0.31096476316452026,0.6066552996635437,0.7201040387153625,0.7344889044761658,0.22691985964775085,0.7814639210700989,0.21044886112213135,0.3556925654411316],"values_recorded":32,"members":[{"code_sha256_prefix":"1ab2898fd19b53d9","path":"muxnet.py","papers":["2003.13880","2309.16108"],"paper_pages":[{"arxiv_id":"2003.13880","page":"/paper/muxconv-information-multiplexing-in"},{"arxiv_id":"2309.16108","page":"/paper/channel-vision-transformers-an-image-is-worth"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"inplace":"False"},"class_bearing":false},{"code_sha256_prefix":"4b3a13b8aba7b6dc","path":"src/Smooth_AP_loss.py","papers":["2411.19458","2007.12163"],"paper_pages":[{"arxiv_id":"2411.19458","page":"/paper/multiview-equivariance-improves-3d"},{"arxiv_id":"2007.12163","page":"/paper/smooth-ap-smoothing-the-path-towards-large"}],"arg_sig_recorded":[["tensor",2,"float","float32"]],"scalar_args":{"temp":"1.0"},"class_bearing":false},{"code_sha256_prefix":"6ed27939405d77df","path":"models/sparsefunc.py","papers":["2011.07439"],"paper_pages":[{"arxiv_id":"2011.07439","page":"/paper/efficient-variational-inference-for-sparse-1"}],"arg_sig_recorded":[["z",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"a74710dfd4798a0f","path":"models/common.py","papers":["2304.05552"],"paper_pages":[{"arxiv_id":"2304.05552","page":"/paper/dynamicdet-a-unified-dynamic-architecture-for"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"hard":"False","threshold":"0.5"},"class_bearing":false},{"code_sha256_prefix":"f8558288ee058a68","path":"Online Platt Scaling with Calibeating/calibration.py","papers":["2305.00070"],"paper_pages":[{"arxiv_id":"2305.00070","page":"/paper/online-platt-scaling-with-calibeating"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}