{"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/extract","entry":"extract","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":9,"n_papers":12,"n_buckets":3,"n_distinct_outputs":4,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":5,"by_error":{"AssertionError":2,"RuntimeError":2,"IndexError":1}},"no_array_argument_ran_on_own_fixture_arguments_only":{"n":1,"n_papers":1,"recorded_shared_digest_equals_own_fixture_digest":1},"output_not_digested_non_numeric":{"n":0,"by_type":{}}},"withdrawn_excluded":0,"code_page":"/code/extract","buckets":[{"bucket":[[1,"float","float32"],[1,"int","int64"]],"n_implementations_compared":7,"n_papers":10,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"28c661fe29562899","size":6,"n_papers":9,"shape":[8,1,1,1],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":6,"torch_reference_conventions_with_this_digest":[],"values":[0.8976119756698608,0.15713146328926086,-0.7621955275535583,-0.903889000415802,0.15713146328926086,0.8976119756698608,0.8976119756698608,0.8976119756698608],"values_recorded":8,"members":[{"code_sha256_prefix":"6a78f18d5b2ce056","path":"diffusion.py","papers":["2506.15933","2305.00562","2410.07679","2410.01540"],"paper_pages":[{"arxiv_id":"2506.15933","page":null},{"arxiv_id":"2305.00562","page":"/paper/class-balancing-diffusion-models"},{"arxiv_id":"2410.07679","page":"/paper/relational-diffusion-distillation-for"},{"arxiv_id":"2410.01540","page":"/paper/edge-preserving-noise-for-diffusion-models"}],"arg_sig_recorded":[["v",1,"float","float32"],["t",1,"int","int64"]],"scalar_args":{"x_shape":"torch.Size([2, 3, 4, 5])"},"class_bearing":false},{"code_sha256_prefix":"411e30457e916104","path":"ddpm.py","papers":["2207.12598"],"paper_pages":[{"arxiv_id":"2207.12598","page":"/paper/classifier-free-diffusion-guidance"}],"arg_sig_recorded":[["v",1,"float","float32"],["t",1,"int","int64"]],"scalar_args":{"x_shape":"(2, 3, 4, 5)"},"class_bearing":false},{"code_sha256_prefix":"803681ed62fd000a","path":"models/diffusion/spaced_diff.py","papers":["2105.05233"],"paper_pages":[{"arxiv_id":"2105.05233","page":"/paper/diffusion-models-beat-gans-on-image-synthesis"}],"arg_sig_recorded":[["a",1,"float","float32"],["t",1,"int","int64"]],"scalar_args":{"x_shape":"(2, 3, 4, 5)"},"class_bearing":false},{"code_sha256_prefix":"83246126c5853561","path":"diffusion/diffusion_2d.py","papers":["2010.02502"],"paper_pages":[{"arxiv_id":"2010.02502","page":"/paper/denoising-diffusion-implicit-models-1"}],"arg_sig_recorded":[["a",1,"float","float32"],["t",1,"int","int64"]],"scalar_args":{"x_shape":"(4, 3, 5)"},"class_bearing":false},{"code_sha256_prefix":"b7011ece22ccb931","path":"src/dnadiffusion/models/diffusion.py","papers":["2208.04202"],"paper_pages":[{"arxiv_id":"2208.04202","page":"/paper/analog-bits-generating-discrete-data-using"}],"arg_sig_recorded":[["a",1,"float","float32"],["t",1,"int","int64"]],"scalar_args":{"x_shape":"(2, 4, 3, 3)","device":"None"},"class_bearing":false},{"code_sha256_prefix":"f8b8b98970a788b6","path":"attack.py","papers":["2601.21628"],"paper_pages":[{"arxiv_id":"2601.21628","page":"/paper/arxiv-2601-21628"}],"arg_sig_recorded":[["v",1,"float","float32"],["t",1,"int","int64"]],"scalar_args":{"x_shape":"(2, 4, 3, 5)"},"class_bearing":false}]},{"output_sha":"1dc676d57d2cd2ce","size":1,"n_papers":1,"shape":[8,1],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.15713146328926086,-0.903889000415802,0.8976119756698608,-0.903889000415802,-0.903889000415802,0.15713146328926086,0.15713146328926086,0.15713146328926086],"values_recorded":8,"members":[{"code_sha256_prefix":"16f305eaaaa9ed73","path":"NRI_with_diffusion/diffusion_prior2.py","papers":["2606.11831"],"paper_pages":[{"arxiv_id":"2606.11831","page":"/paper/arxiv-2606-11831"}],"arg_sig_recorded":[["a",1,"float","float32"],["t",1,"int","int64"]],"scalar_args":{"x_shape":"torch.Size([3, 4])"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"int","int64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"983aef5309bcb17a","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.47605323791503906,-0.6908870339393616,0.47605323791503906,-1.5337762832641602,-1.5337762832641602,-0.6908870339393616,1.8026286363601685,-1.5337762832641602,0.9591456651687622,0.5188759565353394,0.9591456651687622,-1.5683481693267822,-1.5683481693267822,-1.5683481693267822,-1.5683481693267822,-0.3971995711326599,0.06639543920755386,0.06639543920755386,0.4321114122867584,0.06639543920755386,0.4321114122867584,0.06639543920755386,-1.6228755712509155,-1.6228755712509155,1.0175182819366455,1.0175182819366455,0.43327441811561584,1.0175182819366455,1.0175182819366455,0.9449777603149414,0.43327441811561584,0.9449777603149414],"values_recorded":32,"members":[{"code_sha256_prefix":"def41c5ed6de6a48","path":"src/metrics/main_metric.py","papers":["2104.09635"],"paper_pages":[{"arxiv_id":"2104.09635","page":"/paper/refining-targeted-syntactic-evaluation-of"}],"arg_sig_recorded":[["tensor",2,"float","float32"],["indices",2,"int","int64"]],"scalar_args":{"maxval":"1.0","minval":"0.0"},"class_bearing":false}]}]},{"bucket":[[4,"float","float32"],[4,"int","int64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"5451872222ee16d0","size":1,"n_papers":1,"shape":[2,3,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.3433533310890198,0.6530793309211731,-1.1905570030212402,0.0,1.1372957229614258,-0.19992724061012268,1.4460861682891846,0.8319791555404663,0.0,0.0,0.0,-0.012713957577943802,0.3433533310890198,0.6530793309211731,-0.2714869976043701,0.8319791555404663,-0.7250184416770935,0.12553228437900543,-2.0680742263793945,1.4335219860076904,0.0,1.184694528579712,-0.3975509703159332,1.4335219860076904,0.22366678714752197,0.12553228437900543,-0.3975509703159332,-1.463806390762329,0.0,1.1514394283294678,0.5928415060043335,-1.463806390762329,0.0,0.0,0.0,1.2173826694488525,-0.21204684674739838,-1.479430913925171,-0.7425822019577026,-1.2040232419967651,-0.21204684674739838,1.020633339881897,0.2125764787197113,1.2173826694488525,-0.4213716387748718,1.982889175415039,0.0,0.0,1.654322624206543,-0.6244865655899048,0.0,-0.21435445547103882,-1.3870023488998413,0.47569993138313293,-1.3687102794647217,-0.026417039334774017,1.0319796800613403,-0.6244865655899048,-1.3687102794647217,-0.21435445547103882,1.654322624206543,-0.6244865655899048,2.1016592979431152,-0.21435445547103882,0.4846275746822357,0.0,0.0,0.0736190527677536,0.6060231924057007,0.022118685767054558,0.5158193111419678,0.0736190527677536,0.0,0.28421318531036377,3.1044223308563232,2.0942370891571045,0.6060231924057007,0.022118685767054558,3.1044223308563232,-0.6696537733078003,0.22837327420711517,-0.08749820291996002,-1.5213911533355713,0.0,0.22837327420711517,1.2303640842437744,1.9725817441940308,1.0778614282608032,0.0,-0.08749820291996002,0.0,0.0,-2.2168080806732178,0.4391850531101227,0.16540314257144928,-1.1686570644378662],"values_recorded":96,"members":[{"code_sha256_prefix":"68a9bc5cdddf3d5f","path":"fairseq/modules/seqboat_utils.py","papers":["2306.11197"],"paper_pages":[{"arxiv_id":"2306.11197","page":"/paper/sparse-modular-activation-for-efficient-1"}],"arg_sig_recorded":[["h",4,"float","float32"],["index_q",4,"int","int64"]],"scalar_args":{},"class_bearing":false}]}]}]}