{"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/relu","entry":"relu","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":8,"n_papers":11,"n_buckets":2,"n_distinct_outputs":4,"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/relu","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":6,"n_papers":9,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"62b3246ed2816d8c","size":4,"n_papers":6,"shape":[4,8],"dtype":"float32","type":"ndarray","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":4,"torch_reference_conventions_with_this_digest":[],"values":[1.8026286363601685,0.0,0.47605323791503906,0.0,0.0,0.0,0.0,0.5728892087936401,0.5188759565353394,0.9591456651687622,0.0,0.0,0.0,2.322108745574951,0.0,0.5505285859107971,0.06639543920755386,0.0,0.4321114122867584,0.0,0.0,0.0,0.0,0.983674168586731,0.0,0.43327441811561584,0.9449777603149414,1.0175182819366455,0.0,1.274217963218689,0.0,0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"1dbace35862da027","path":"convex_nn.py","papers":["2312.12657","2205.13098","2608.13628"],"paper_pages":[{"arxiv_id":"2312.12657","page":"/paper/the-convex-landscape-of-neural-networks"},{"arxiv_id":"2205.13098","page":"/paper/optimal-neural-network-approximation-of"},{"arxiv_id":"2608.13628","page":"/paper/arxiv-2608-13628"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"4c9a9cab68f5a375","path":"subsetsum.py","papers":["2111.11146"],"paper_pages":[{"arxiv_id":"2111.11146","page":"/paper/on-the-existence-of-universal-lottery-tickets-1"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"93a27674bbe152a1","path":"automate.py","papers":["2102.13037"],"paper_pages":[{"arxiv_id":"2102.13037","page":"/paper/spinn-sparse-physics-based-and-interpretable"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"94d5729d92a97933","path":"assignment-2/assignment2-bonus.py","papers":["1502.01852"],"paper_pages":[{"arxiv_id":"1502.01852","page":"/paper/delving-deep-into-rectifiers-surpassing-human"}],"arg_sig_recorded":[["X",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"c5ef78bcdf039e91","size":1,"n_papers":2,"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":[1.8026286363601685,-0.0,0.47605323791503906,-0.0,-0.0,-0.0,-0.0,0.5728892087936401,0.5188759565353394,0.9591456651687622,-0.0,-0.0,-0.0,2.322108745574951,-0.0,0.5505285859107971,0.06639543920755386,-0.0,0.4321114122867584,-0.0,-0.0,-0.0,-0.0,0.983674168586731,-0.0,0.43327441811561584,0.9449777603149414,1.0175182819366455,-0.0,1.274217963218689,-0.0,-0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"5af8fa537914ff3d","path":"theory.py","papers":["1907.10599","2401.11627"],"paper_pages":[{"arxiv_id":"1907.10599","page":"/paper/a-fine-grained-spectral-perspective-on-neural"},{"arxiv_id":"2401.11627","page":"/paper/tight-verification-of-probabilistic"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"2901616effbdcd9a","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":[1.3026286363601685,0.0,0.0,0.0,0.0,0.0,0.0,0.07288920879364014,0.018875956535339355,0.4591456651687622,0.0,0.0,0.0,1.8221087455749512,0.0,0.05052858591079712,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.48367416858673096,0.0,0.0,0.4449777603149414,0.5175182819366455,0.0,0.774217963218689,0.0,0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"d5d46e42d48015f4","path":"models/Analysis.py","papers":["2012.10424"],"paper_pages":[{"arxiv_id":"2012.10424","page":"/paper/separation-and-concentration-in-deep-networks"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"lambd":"0.5"},"class_bearing":false}]}]},{"bucket":[[2,"float","float64"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"62b3246ed2816d8c","size":2,"n_papers":2,"shape":[4,8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":2,"torch_reference_conventions_with_this_digest":[],"values":[1.802628679592353,0.0,0.47605322923618437,0.0,0.0,0.0,0.0,0.572889220601701,0.5188759529457332,0.9591456414705227,0.0,0.0,0.0,2.3221088606181515,0.0,0.5505285791931418,0.06639544283095257,0.0,0.4321114229703758,0.0,0.0,0.0,0.0,0.983674188609945,0.0,0.4332744095449241,0.9449777773193271,1.01751825335816,0.0,1.2742179092187245,0.0,0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"5778be44d14bcb09","path":"MVRSM.py","papers":["2006.04508"],"paper_pages":[{"arxiv_id":"2006.04508","page":"/paper/black-box-mixed-variable-optimisation-using-a"}],"arg_sig_recorded":[["x",2,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"b4ffc7174f63b5d9","path":"keras_pkg/grad_cam.py","papers":["1610.02391"],"paper_pages":[{"arxiv_id":"1610.02391","page":"/paper/grad-cam-visual-explanations-from-deep"}],"arg_sig_recorded":[["x",2,"float","float64"]],"scalar_args":{},"class_bearing":false}]}]}]}