{"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/layernorm","entry":"LayerNorm","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":5,"n_papers":5,"n_buckets":3,"n_distinct_outputs":5,"n_class_bearing":4,"not_compared":{"not_run_on_shared_input":{"n":17,"by_error":{"RuntimeError":17}},"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/layernorm","buckets":[{"bucket":[[3,"float","float32"]],"n_implementations_compared":3,"n_papers":3,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"1203b12693cfeb42","size":1,"n_papers":1,"shape":[2,4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.5387024879455566,1.324451208114624,-1.2400493621826172,-0.20818635821342468,0.42922142148017883,-1.491769790649414,0.0948239415884018,-1.3437118530273438,-1.3344566822052002,-0.49771836400032043,-0.26515498757362366,-1.1176729202270508,1.3935575485229492,-0.3302136957645416,1.400909423828125,-0.3686295449733734,1.232083797454834,-1.3233978748321533,1.5459887981414795,1.6190648078918457,-0.5854871273040771,0.8574355840682983,-0.07348926365375519,0.3119133710861206,0.6410754323005676,0.4966648817062378,-0.040784381330013275,-0.2932053804397583,-1.2372920513153076,0.964547872543335,-1.4222440719604492,1.400428056716919,-0.04666057601571083,1.267665147781372,-1.0320661067962646,-0.23676663637161255,-0.19966010749340057,0.29211679100990295,0.6655555963516235,1.3281610012054443,-0.6897168755531311,-1.308210849761963,-0.8923704624176025,0.525885820388794,-0.2328505665063858,-1.20100998878479,1.1994036436080933,0.6041635274887085,1.6430786848068237,-0.5631449222564697,0.5835638046264648,-1.4906502962112427,-1.164362907409668,-0.5602083802223206,-0.49697110056877136,-1.0109126567840576,-0.9067009091377258,0.6036904454231262,1.3408727645874023,1.2015303373336792,1.5968741178512573,1.4691016674041748,-1.367988109588623,-0.9214121103286743],"values_recorded":64,"members":[{"code_sha256_prefix":"8679d4611c936d0e","path":"vap_realtime/model.py","papers":["2603.26515"],"paper_pages":[{"arxiv_id":"2603.26515","page":"/paper/arxiv-2603-26515"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"af16283e77b9a12b","size":1,"n_papers":1,"shape":[2,4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.5387025475502014,1.324451208114624,-1.2400493621826172,-0.20818641781806946,0.4292214810848236,-1.4917696714401245,0.09482394903898239,-1.3437119722366333,-1.3344568014144897,-0.49771833419799805,-0.26515495777130127,-1.1176729202270508,1.3935577869415283,-0.33021366596221924,1.400909423828125,-0.3686296343803406,1.232083797454834,-1.3233977556228638,1.5459887981414795,1.6190648078918457,-0.5854870676994324,0.8574355244636536,-0.07348926365375519,0.31191331148147583,0.6410754323005676,0.4966649115085602,-0.040784381330013275,-0.2932054400444031,-1.2372920513153076,0.9645477533340454,-1.4222440719604492,1.4004281759262085,-0.04666073992848396,1.2676652669906616,-1.0320661067962646,-0.23676663637161255,-0.19966012239456177,0.29211682081222534,0.6655555367469788,1.3281611204147339,-0.6897170543670654,-1.3082109689712524,-0.8923704624176025,0.525885820388794,-0.2328505963087082,-1.2010101079940796,1.1994035243988037,0.6041635274887085,1.6430785655975342,-0.5631449818611145,0.5835638046264648,-1.4906502962112427,-1.1643630266189575,-0.5602084398269653,-0.496971070766449,-1.0109126567840576,-0.9067010879516602,0.603690505027771,1.3408726453781128,1.2015303373336792,1.5968742370605469,1.469101905822754,-1.3679879903793335,-0.9214119911193848],"values_recorded":64,"members":[{"code_sha256_prefix":"d6b2448718cb4aff","path":"model/impl/actionformer.py","papers":["2504.08222"],"paper_pages":[{"arxiv_id":"2504.08222","page":"/paper/f-3-set-towards-analyzing-fast-frequent-and"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"dfbbd5a3e0900846","size":1,"n_papers":1,"shape":[2,4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.43713295459747314,0.8405004739761353,-0.6185013651847839,-0.12222496420145035,0.08073075860738754,-0.7057713866233826,-0.16286544501781464,-0.18319071829319,-1.6334328651428223,0.018155833706259727,-0.6427767872810364,-0.5838517546653748,0.6513828635215759,-0.12104751914739609,0.1255066990852356,0.32146742939949036,0.16726653277873993,-0.06486412137746811,-0.006698548328131437,0.06952577829360962,-0.04940085485577583,0.10046277940273285,-0.03464198485016823,0.085659459233284,0.1274813413619995,0.12344873696565628,-0.09802369028329849,-0.03885863721370697,-0.13486893475055695,0.16531255841255188,-0.11871583759784698,0.2439097762107849,-0.4722900092601776,0.8784902691841125,-0.5794986486434937,-0.3990218937397003,0.46296462416648865,0.2867436408996582,0.006368591450154781,0.8179129362106323,-0.9051293730735779,-0.6869546175003052,-0.7735656499862671,-0.5304107666015625,0.7046896815299988,-0.1291736662387848,0.2656405568122864,0.6465216875076294,-0.03154366463422775,-0.010929512791335583,0.061207376420497894,-0.0876699909567833,0.04238814115524292,0.013448161073029041,-0.0630151554942131,-0.08473698794841766,-0.16565117239952087,0.143045574426651,0.20641875267028809,-0.0778687372803688,0.2347588688135147,0.1539250761270523,-0.16575868427753448,-0.11328406631946564],"values_recorded":64,"members":[{"code_sha256_prefix":"401ab8714b56785f","path":"core/networks.py","papers":["2002.04114"],"paper_pages":[{"arxiv_id":"2002.04114","page":"/paper/cross-modality-paired-images-generation-for"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]},{"bucket":[[2,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"61fc50e83a050a3b","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":[1.863001823425293,-1.1708731651306152,0.656714141368866,-0.40441325306892395,-0.5971559286117554,-0.7132054567337036,-0.3788374960422516,0.7447695136070251,0.27513357996940613,0.6523163914680481,-0.5096760988235474,-1.513008952140808,-0.41658228635787964,1.8199782371520996,-0.6104115843772888,0.3022506535053253,0.4173913896083832,-1.5840702056884766,0.8506945371627808,-0.14252665638923645,0.3119557499885559,-1.0602748394012451,-0.29736021161079407,1.504190444946289,-0.7143735885620117,0.437486469745636,0.9171160459518433,0.9851096868515015,-1.1175830364227295,1.2257193326950073,-1.2079745531082153,-0.5255002379417419],"values_recorded":32,"members":[{"code_sha256_prefix":"94b77cde28f21f74","path":"rb-transformer/transformer.py","papers":["1706.03762"],"paper_pages":[{"arxiv_id":"1706.03762","page":"/paper/attention-is-all-you-need"}],"arg_sig_recorded":[["x",2,"float","float32"]],"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":"80acbb50c5d8d5ec","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":[-0.8088156580924988,-1.0291118621826172,1.465644121170044,0.37228313088417053,1.230046033859253,-0.9261940717697144,-1.041582465171814,0.7377303838729858,1.0347148180007935,0.20240429043769836,-1.648888111114502,0.4117688834667206,0.03244331106543541,0.2513898015022278,-1.5375288724899292,1.2536958456039429,-0.19989576935768127,0.5539528131484985,1.1628395318984985,-1.5168966054916382,-1.1609773635864258,0.8365397453308105,-0.8123834133148193,1.136820912361145,0.36455848813056946,1.1776957511901855,-1.5745112895965576,0.03225717321038246,0.3538833260536194,-0.37261325120925903,1.376064658164978,-1.3573344945907593,-0.5113776326179504,1.7306538820266724,-0.608241081237793,-0.6110349297523499,-0.6160827279090881,1.5731807947158813,0.10776281356811523,-1.0648609399795532,0.09333125501871109,-1.190683126449585,-0.4441656470298767,1.5415173768997192,0.48190855979919434,0.16807962954044342,1.0032113790512085,-1.653199553489685,0.170419380068779,-0.5352654457092285,1.5273923873901367,-1.1625462770462036,1.4215788841247559,-0.15669433772563934,-1.392242431640625,0.12735776603221893,-0.2625442445278168,-1.1193898916244507,-0.2372458577156067,1.6191798448562622,-1.6328834295272827,0.22648940980434418,0.32016947865486145,1.0862243175506592,0.16633331775665283,-1.5357534885406494,0.10327377170324326,1.2661464214324951,-0.3429007828235626,-0.7061755657196045,1.7148011922836304,-0.6657249331474304,0.8326875567436218,0.19757790863513947,0.6546652913093567,-1.6849308013916016,1.5174497365951538,-0.8556975722312927,0.2799168825149536,-0.9416691660881042,-1.5886167287826538,0.7087628841400146,0.9816260933876038,-0.10177209228277206,0.30674558877944946,0.7689868807792664,-1.7074737548828125,0.6317411065101624,-0.12526530027389526,0.06403849273920059,1.4409911632537842,-1.3797643184661865,1.0686498880386353,0.5701178312301636,-1.5907999277114868,-0.04796786606311798],"values_recorded":96,"members":[{"code_sha256_prefix":"353587c1014cce8f","path":"networks/UXNet_3D/network_backbone.py","papers":["2209.15076"],"paper_pages":[{"arxiv_id":"2209.15076","page":"/paper/3d-ux-net-a-large-kernel-volumetric-convnet"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]}]}