{"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/normalization","entry":"normalization","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":6,"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/normalization","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"39b6e3abf587af88","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.0,0.0,0.6023938059806824,0.2526339888572693,0.18910378217697144,0.1508525162935257,0.2610640525817871,0.6314178705215454,0.5364984273910522,0.6496650576591492,0.30103111267089844,0.0,0.32896214723587036,1.0,0.27080732583999634,0.5446344017982483,0.6480869650840759,0.0,0.7883935570716858,0.46678170561790466,0.6139461994171143,0.16960854828357697,0.4166455566883087,1.0,0.20281966030597687,0.6761166453361511,0.873195469379425,0.9011340141296387,0.03714168071746826,1.0,0.0,0.28042736649513245],"values_recorded":32,"members":[{"code_sha256_prefix":"8e221d38153ae3cb","path":"cluster_clc.py","papers":["2203.01570"],"paper_pages":[{"arxiv_id":"2203.01570","page":"/paper/representing-mixtures-of-word-embeddings-with-1"}],"arg_sig_recorded":[["data",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"771dbde58a2f354c","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":[0.8683187961578369,0.022585459053516388,0.5320500135421753,0.23624643683433533,0.18251682817935944,0.15016646683216095,0.24337603151798248,0.556596577167511,0.5429049134254456,0.6545073390007019,0.3106922507286072,0.013821955770254135,0.3382371962070465,1.0,0.280886173248291,0.5509284734725952,0.42820724844932556,0.0,0.5209112763404846,0.3084143102169037,0.4056496024131775,0.11206460744142532,0.2752881348133087,0.6607249975204468,0.20969988405704498,0.5212060809135437,0.6509159803390503,0.6693039536476135,0.10065688192844391,0.7343738675117493,0.07621163129806519,0.2607783079147339],"values_recorded":32,"members":[{"code_sha256_prefix":"f1952d5b29888b39","path":"wav2vec2_xls-r300-song/generate_FSD_online.py","papers":["2309.02232"],"paper_pages":[{"arxiv_id":"2309.02232","page":"/paper/fsd-an-initial-chinese-dataset-for-fake-song"}],"arg_sig_recorded":[["orign_data",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[1,"float","float64"]],"n_implementations_compared":1,"n_papers":3,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"ebfdf9421e6b692d","size":1,"n_papers":3,"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":[0.28683146858023517,0.7068625464279104,1.0,0.3429243135808125,0.5748830840018702,0.6656521021436772,0.0,0.5743772480252599],"values_recorded":8,"members":[{"code_sha256_prefix":"86c7147edb17dd5d","path":"analysis/attention_accuracy_analysis/calc_gt.py","papers":["2306.09104","2410.02604","2601.17529"],"paper_pages":[{"arxiv_id":"2306.09104","page":"/paper/on-strengthening-and-defending-graph"},{"arxiv_id":"2410.02604","page":"/paper/long-sequence-recommendation-models-need"},{"arxiv_id":"2601.17529","page":"/paper/arxiv-2601-17529"}],"arg_sig_recorded":[["data",1,"float","float64"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[4,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"ef115a0e0c15cdc4","size":1,"n_papers":1,"shape":[2,4,4,3],"dtype":"float32","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0],"values_recorded":96,"members":[{"code_sha256_prefix":"44654289537e4ae8","path":"MAP_NN_training.py","papers":["1811.03691"],"paper_pages":[{"arxiv_id":"1811.03691","page":"/paper/can-deep-learning-outperform-modern"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"region":"'ABD'"},"class_bearing":false}]}]}]}