{"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/tanh","entry":"tanh","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":6,"n_papers":7,"n_buckets":2,"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/tanh","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":3,"n_papers":4,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"694618c88ee7c651","size":3,"n_papers":4,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":3,"torch_reference_conventions_with_this_digest":[],"values":[0.9470775723457336,-0.9110686182975769,0.4430772066116333,-0.5985515713691711,-0.7176824808120728,-0.7740972638130188,-0.5801978707313538,0.5174779891967773,0.47683200240135193,0.7438955307006836,-0.37755027413368225,-0.9167625904083252,-0.2807859480381012,0.9809491038322449,-0.473664253950119,0.5009162425994873,0.06629804521799088,-0.9250402450561523,0.4070843458175659,-0.38522934913635254,-0.022590380162000656,-0.8276981711387634,-0.4906136989593506,0.7546520233154297,-0.6615769267082214,0.4080541431903839,0.7375009059906006,0.7688537836074829,-0.8413525819778442,0.8549367189407349,-0.8673354387283325,-0.5328444838523865],"values_recorded":32,"members":[{"code_sha256_prefix":"be5af45dd86c2cc1","path":"hypcbc/model/model.py","papers":["2404.15523","2602.03264"],"paper_pages":[{"arxiv_id":"2404.15523","page":"/paper/understanding-hyperbolic-metric-learning"},{"arxiv_id":"2602.03264","page":"/paper/arxiv-2602-03264"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"clamp":"15"},"class_bearing":false},{"code_sha256_prefix":"189316d1476b8b6b","path":"hgcn/models/encoders.py","papers":["2310.10013"],"paper_pages":[{"arxiv_id":"2310.10013","page":"/paper/riemannian-residual-neural-networks"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"8e0d774d7f2805ff","path":"GIE-master/code/models.py","papers":["2206.12418"],"paper_pages":[{"arxiv_id":"2206.12418","page":"/paper/geometry-interaction-knowledge-graph"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float64"]],"n_implementations_compared":3,"n_papers":3,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"9eea1d94eaedfc19","size":3,"n_papers":3,"shape":[4,8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":1.6653345369377348e-16,"members_with_recorded_values":3,"torch_reference_conventions_with_this_digest":[],"values":[0.9470775581697828,-0.9110685964998538,0.44307721292184427,-0.5985515624220882,-0.7176825095653903,-0.7740972633357511,-0.5801978623247057,0.5174779749209147,0.47683200390111785,0.7438955366907894,-0.37755026260109725,-0.9167626182212961,-0.28078595364230624,0.9809491134635796,-0.47366425226174425,0.5009162656503734,0.06629804967444859,-0.9250402642264874,0.40708434433595403,-0.3852293615547797,-0.02259038021369411,-0.8276981576432555,-0.490613689941478,0.7546520349701765,-0.6615769246933226,0.40805414391983386,0.7375009256936467,0.7688537738924099,-0.8413525973549311,0.8549367224484156,-0.8673354185998965,-0.5328444730022242],"values_recorded":32,"members":[{"code_sha256_prefix":"27556b18fb77c49c","path":"utils.py","papers":["2302.01629"],"paper_pages":[{"arxiv_id":"2302.01629","page":"/paper/beyond-the-universal-law-of-robustness"}],"arg_sig_recorded":[["a",2,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"85adc5760af572a0","path":"main_RF.py","papers":["2410.14787"],"paper_pages":[{"arxiv_id":"2410.14787","page":"/paper/privacy-for-free-in-the-over-parameterized"}],"arg_sig_recorded":[["a",2,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"d51cc2bc73bd04cb","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}]}]}]}