{"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/mu","entry":"mu","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":4,"n_papers":5,"n_buckets":3,"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/mu","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":2,"n_papers":3,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"159b38dc62350309","size":1,"n_papers":2,"shape":[8],"dtype":"float32","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.12718985974788666,0.2843804955482483,-1.4544068574905396,-0.14546644687652588,-1.476943016052246,0.8100777864456177,-2.217634916305542,-1.0645112991333008],"values_recorded":8,"members":[{"code_sha256_prefix":"db1200b166ffcce8","path":"causal_bald/library/acquisitions.py","papers":["2111.02275","2302.08981"],"paper_pages":[{"arxiv_id":"2111.02275","page":"/paper/causal-bald-deep-bayesian-active-learning-of"},{"arxiv_id":"2302.08981","page":"/paper/black-box-batch-active-learning-for"}],"arg_sig_recorded":[["mu_0",2,"float","float32"],["mu_1",2,"float","float32"]],"scalar_args":{"t":"0.5","pt":"0.3","temperature":"1.0"},"class_bearing":false}]},{"output_sha":"8e7c594ab6a20aff","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":[-0.21184004843235016,2.123643398284912,0.7167627215385437,1.533620834350586,1.6819945573806763,1.7713298797607422,1.513932704925537,0.648977518081665,0.6867868304252625,0.37859803438186646,1.3280397653579712,2.147843599319458,1.2519745826721191,-0.5754761099815369,1.410348653793335,0.6646299958229065,1.0035232305526733,2.1860129833221436,0.7475219964981079,1.3343300819396973,1.0658159255981445,1.8765475749969482,1.4258078336715698,0.36142808198928833,1.6069289445877075,0.7467079162597656,0.38851556181907654,0.33773720264434814,1.9080499410629272,0.15804742276668549,1.975555181503296,1.4658763408660889],"values_recorded":32,"members":[{"code_sha256_prefix":"73c560f3f8fd01ed","path":"euler_maruyama_simulation.py","papers":["2008.10546"],"paper_pages":[{"arxiv_id":"2008.10546","page":"/paper/sde-net-equipping-deep-neural-networks-with"}],"arg_sig_recorded":[["y",2,"float","float32"],["t",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[1,"float","float64"]],"n_implementations_compared":1,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"2091c6f76edebb04","size":1,"n_papers":2,"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":[0.2882519628322799,0.5392022378925179,0.7104585180504956,0.31816978031374316,0.4560498300643325,0.5132548239196687,0.16404413905099488,0.4557328740372635],"values_recorded":8,"members":[{"code_sha256_prefix":"c3f0f3af4e86bef6","path":"logbexp/algorithms/ofuglb.py","papers":["2404.06831","2407.13977"],"paper_pages":[{"arxiv_id":"2404.06831","page":"/paper/optimal-regret-with-limited-adaptivity-for"},{"arxiv_id":"2407.13977","page":"/paper/a-unified-confidence-sequence-for-generalized"}],"arg_sig_recorded":[["z",1,"float","float64"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float64"],[2,"float","float64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"159b38dc62350309","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":[-0.12718978149687615,0.28438043767160914,-1.4544067708552435,-0.1454664057481627,-1.4769430039682125,0.8100778896908848,-2.217634893307083,-1.0645113509742237],"values_recorded":8,"members":[{"code_sha256_prefix":"fe199cc2a1fe1289","path":"causal_bald/library/acquisitions.py","papers":["2111.02275"],"paper_pages":[{"arxiv_id":"2111.02275","page":"/paper/causal-bald-deep-bayesian-active-learning-of"}],"arg_sig_recorded":[["mu_0",2,"float","float64"],["mu_1",2,"float","float64"]],"scalar_args":{"t":"0.3","pt":"None","temperature":"1.0"},"class_bearing":false}]}]}]}