{"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/swish","entry":"swish","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":14,"n_papers":37,"n_buckets":1,"n_distinct_outputs":2,"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":0,"n_papers":0,"recorded_shared_digest_equals_own_fixture_digest":0},"output_not_digested_non_numeric":{"n":0,"by_type":{}}},"withdrawn_excluded":0,"code_page":"/code/swish","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":14,"n_papers":37,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"457319fe226e9e7e","size":12,"n_papers":35,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":12,"torch_reference_conventions_with_this_digest":[],"values":[1.5475001335144043,-0.27215608954429626,0.2936370074748993,-0.23064281046390533,-0.26044073700904846,-0.2710064649581909,-0.22541801631450653,0.3663223385810852,0.3252754807472229,0.6934150457382202,-0.15966840088367462,-0.27046477794647217,-0.12359761446714401,2.11472487449646,-0.1925666481256485,0.3491772711277008,0.03429940342903137,-0.2674639821052551,0.2620227634906769,-0.16240409016609192,-0.0111694922670722,-0.27737942337989807,-0.19805951416492462,0.715954065322876,-0.24740755558013916,0.26284822821617126,0.6804823279380798,0.7473558783531189,-0.278155118227005,0.9957553744316101,-0.27826008200645447,-0.2113201916217804],"values_recorded":32,"members":[{"code_sha256_prefix":"0f786c407fb1ee4c","path":"models/modeling.py","papers":["2010.11929","2102.05013","2210.10246","2510.01022","1810.04805","1810.12162","1910.09796","2004.05234","2202.09729","2103.07976","2012.15701","1909.00252","1902.01069","2312.10376","2305.16986","2401.00793","2110.07592","2304.08382","2104.06468","2411.01948","2608.19529"],"paper_pages":[{"arxiv_id":"2010.11929","page":"/paper/an-image-is-worth-16x16-words-transformers-1"},{"arxiv_id":"2102.05013","page":"/paper/spherical-message-passing-for-3d-graph"},{"arxiv_id":"2210.10246","page":"/paper/tempo-accelerating-transformer-based-model"},{"arxiv_id":"2510.01022","page":"/paper/arxiv-2510-01022"},{"arxiv_id":"1810.04805","page":"/paper/bert-pre-training-of-deep-bidirectional"},{"arxiv_id":"1810.12162","page":"/paper/model-based-active-exploration"},{"arxiv_id":"1910.09796","page":"/paper/kernel-graph-attention-network-for-fact"},{"arxiv_id":"2004.05234","page":"/paper/attend-and-decode-4d-fmri-task-state-decoding"},{"arxiv_id":"2202.09729","page":"/paper/it-s-raw-audio-generation-with-state-space"},{"arxiv_id":"2103.07976","page":"/paper/transfg-a-transformer-architecture-for-fine"},{"arxiv_id":"2012.15701","page":"/paper/binarybert-pushing-the-limit-of-bert"},{"arxiv_id":"1909.00252","page":"/paper/humor-detection-a-transformer-gets-the-last"},{"arxiv_id":"1902.01069","page":"/paper/a-comprehensive-exploration-on-wikisql-with"},{"arxiv_id":"2312.10376","page":"/paper/sa-2-vp-spatially-aligned-and-adapted-visual"},{"arxiv_id":"2305.16986","page":"/paper/navgpt-explicit-reasoning-in-vision-and"},{"arxiv_id":"2401.00793","page":"/paper/secformer-towards-fast-and-accurate-privacy"},{"arxiv_id":"2110.07592","page":"/paper/speech-toxicity-analysis-a-new-spoken"},{"arxiv_id":"2304.08382","page":"/paper/melt-mutual-enhancement-of-long-tailed-user"},{"arxiv_id":"2104.06468","page":"/paper/vit-v-net-vision-transformer-for-unsupervised"},{"arxiv_id":"2411.01948","page":"/paper/learning-where-to-edit-vision-transformers"},{"arxiv_id":"2608.19529","page":"/paper/arxiv-2608-19529"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"5fb036462ae82f9f","path":"uno/flux/pipeline.py","papers":["2504.02160","2606.08063","2512.07778"],"paper_pages":[{"arxiv_id":"2504.02160","page":"/paper/less-to-more-generalization-unlocking-more"},{"arxiv_id":"2606.08063","page":"/paper/arxiv-2606-08063"},{"arxiv_id":"2512.07778","page":"/paper/arxiv-2512-07778"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"107bf3b7b61a9085","path":"models.py","papers":["2302.14182","2509.22583"],"paper_pages":[{"arxiv_id":"2302.14182","page":null},{"arxiv_id":"2509.22583","page":"/paper/arxiv-2509-22583"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"31117990d4f24fdf","path":"models.py","papers":["1710.05941","1609.04802"],"paper_pages":[{"arxiv_id":"1710.05941","page":"/paper/searching-for-activation-functions"},{"arxiv_id":"1609.04802","page":"/paper/photo-realistic-single-image-super-resolution"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"0444419acc5bad7c","path":"models/graddae/mlp.py","papers":["2006.05164"],"paper_pages":[{"arxiv_id":"2006.05164","page":"/paper/ar-dae-towards-unbiased-neural-entropy"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"0aeebcafcf0c595f","path":"classy_vision/models/efficientnet.py","papers":["1905.11946"],"paper_pages":[{"arxiv_id":"1905.11946","page":"/paper/efficientnet-rethinking-model-scaling-for"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"20fb7a08507b85ec","path":"efficientnet/model.py","papers":["1905.11946"],"paper_pages":[{"arxiv_id":"1905.11946","page":"/paper/efficientnet-rethinking-model-scaling-for"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"3a4a478be185334b","path":"models/model.py","papers":["2310.00149"],"paper_pages":[{"arxiv_id":"2310.00149","page":"/paper/one-for-all-towards-training-one-graph-model"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"84b2a92d3f7d7df9","path":"flows.py","papers":["2002.07101"],"paper_pages":[{"arxiv_id":"2002.07101","page":"/paper/augmented-normalizing-flows-bridging-the-gap"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"8efb92cd06aefbfb","path":"labml_nn/diffusion/stable_diffusion/model/autoencoder.py","papers":["2112.10752"],"paper_pages":[{"arxiv_id":"2112.10752","page":"/paper/high-resolution-image-synthesis-with-latent"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"bb3da06612c6f802","path":"model.py","papers":["1912.11160"],"paper_pages":[{"arxiv_id":"1912.11160","page":"/paper/recvae-a-new-variational-autoencoder-for-top"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"d09ef21d2b294028","path":"transformer/modeling_bert_quant.py","papers":["2205.13016"],"paper_pages":[{"arxiv_id":"2205.13016","page":"/paper/bit-robustly-binarized-multi-distilled"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"72ecfcef5a0f933c","size":2,"n_papers":3,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":2,"torch_reference_conventions_with_this_digest":[],"values":[1.28206467628479,-0.4864412248134613,0.2662219703197479,-0.28636425733566284,-0.35122841596603394,-0.3853622078895569,-0.2769709527492523,0.32719165086746216,0.29290449619293213,0.5924134254455566,-0.1789434254169464,-0.4915531873703003,-0.13387899100780487,1.7683420181274414,-0.22444836795330048,0.31291210651397705,0.03374871611595154,-0.49917086958885193,0.23930537700653076,-0.182540163397789,-0.011233300901949406,-0.42100220918655396,-0.232620507478714,0.6104083061218262,-0.31970861554145813,0.24001169204711914,0.5820804834365845,0.6354560256004333,-0.4307405948638916,0.8334655165672302,-0.45020344853401184,-0.2532554566860199],"values_recorded":32,"members":[{"code_sha256_prefix":"5f094438dfb16a0d","path":"svp/model/models_mamba.py","papers":["2203.12119","2412.08947"],"paper_pages":[{"arxiv_id":"2203.12119","page":"/paper/visual-prompt-tuning"},{"arxiv_id":"2412.08947","page":"/paper/selective-visual-prompting-in-vision-mamba"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"beta":"0.5"},"class_bearing":false},{"code_sha256_prefix":"919aae7a4c5d1c1a","path":"src/neuron/activation_functions.py","papers":["1710.05941"],"paper_pages":[{"arxiv_id":"1710.05941","page":"/paper/searching-for-activation-functions"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{"beta":"0.5"},"class_bearing":false}]}]}]}