{"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/convblock","entry":"ConvBlock","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":8,"n_buckets":2,"n_distinct_outputs":6,"n_class_bearing":8,"not_compared":{"not_run_on_shared_input":{"n":4,"by_error":{"RuntimeError":4}},"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/convblock","buckets":[{"bucket":[[4,"float","float32"]],"n_implementations_compared":5,"n_papers":5,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"46a3163ddd909512","size":1,"n_papers":1,"shape":[2,4,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.11325619369745255,0.06666646897792816,0.04992370679974556,0.0,0.0016771784285083413,0.0,0.15882335603237152,0.05561090633273125,0.02442106045782566,0.0009026068146340549,0.23144972324371338,0.0,0.0,0.0,0.2907417416572571,0.0,0.0,0.13257083296775818,0.0,0.0,0.0,0.0034253352787345648,0.0,0.0,0.0,0.19304150342941284,0.0,0.09762319922447205,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.232308030128479,0.10261163115501404,0.0,0.0,0.08829046040773392,0.0,0.0,0.10969416797161102,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.016814665868878365,0.0,0.0,0.0,0.0,0.04514604061841965,0.13777273893356323,0.0,0.0,0.0,0.06000674515962601,0.0,0.0,0.19820326566696167,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0876990333199501,0.0,0.022795524448156357,0.0,0.14747264981269836,0.0,0.14748556911945343,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.14302434027194977,0.0,0.13486163318157196,0.0,0.10042653977870941,0.15045365691184998,0.02443964034318924,0.0015825922600924969],"values_recorded":128,"members":[{"code_sha256_prefix":"2755db4bf67cd3ae","path":"Networks/network.py","papers":["2601.17271"],"paper_pages":[{"arxiv_id":"2601.17271","page":"/paper/arxiv-2601-17271"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"4ba22e89b53e0e8f","size":1,"n_papers":1,"shape":[2,4,2,2],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.70352303981781,0.0,0.0,0.0,0.0,0.49592289328575134,0.0,0.0,0.0,0.03162287920713425,0.5995511412620544,0.0,0.0,0.0,1.7379834651947021,0.3832031190395355,1.2257707118988037,0.0,0.0977756679058075,0.0,0.0,0.0,1.6118777990341187,1.4141552448272705,0.0,0.0,0.33368879556655884,2.223862886428833,0.0,0.0,1.1015044450759888,0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"cf9b257c7a9fd0fc","path":"models/dave.py","papers":["2404.16622"],"paper_pages":[{"arxiv_id":"2404.16622","page":"/paper/dave-a-detect-and-verify-paradigm-for-low"}],"arg_sig_recorded":[["input",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"8f76e1a5cdd06f2a","size":1,"n_papers":1,"shape":[2,4,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.6275879144668579,-0.07753758877515793,-0.1081477627158165,-0.0427691712975502,0.17216312885284424,-0.2944231629371643,-0.14714235067367554,0.20135217905044556,-0.07163163274526596,-0.11289874464273453,-0.3023538589477539,0.390103816986084,-0.07775937020778656,0.13053295016288757,0.2917030453681946,0.13831058144569397,0.020473778247833252,-0.18790461122989655,0.19253039360046387,-0.11710172146558762,-0.01819547824561596,0.03873084858059883,-0.2787232995033264,-0.2304248809814453,-0.05401293933391571,1.0731390714645386,-5.296100425766781e-05,0.1714760959148407,-0.07801377773284912,0.05818714573979378,-0.2666560113430023,0.9312462210655212,-0.23994192481040955,-0.2759823203086853,-0.07097051292657852,-0.2677484452724457,-0.13105113804340363,0.20772963762283325,0.7376395463943481,-0.29485344886779785,0.1554071009159088,0.4383859634399414,-0.2735632658004761,0.02921658381819725,-0.11909826099872589,0.15507596731185913,0.2727677822113037,0.03159894421696663,-0.15900182723999023,-0.1696290522813797,0.05320776253938675,0.654736340045929,-0.0682840347290039,0.7019246220588684,-0.13442465662956238,-0.1005312129855156,0.5238202810287476,1.225242018699646,0.17088690400123596,0.3265029788017273,0.08922435343265533,-0.09753606468439102,0.08282018452882767,0.07554124295711517,0.3958701491355896,-0.20463739335536957,-0.20170597732067108,-0.24281658232212067,0.0668918788433075,-0.2373061329126358,-0.09932301938533783,-0.2658832371234894,-0.031740911304950714,0.03637392818927765,-0.1597212851047516,0.7354146838188171,0.09011586755514145,0.04636300355195999,-0.18623629212379456,-0.18564511835575104,0.09617921710014343,0.07201162725687027,-0.031923115253448486,0.04637129604816437,0.4460960030555725,-0.04422657564282417,0.2663215696811676,0.7665175795555115,0.40607649087905884,0.5100667476654053,0.3658771514892578,0.08509399741888046,0.07880217581987381,0.716620922088623,0.3818451762199402,0.022025326266884804,-0.24874772131443024,-0.21718108654022217,-0.2652744948863983,-0.06482745707035065,-0.2889891266822815,0.148892343044281,-0.0729653611779213,0.6451547145843506,0.0393824428319931,0.473862886428833,1.137215256690979,0.29760417342185974,0.5561014413833618,1.28123140335083,0.21568623185157776,-0.21834079921245575,0.05512610450387001,0.07013507187366486,-0.10554734617471695,0.1476350575685501,-0.2653581202030182,-0.005410844460129738,0.04601197689771652,0.93653804063797,0.3478448987007141,1.0993287563323975,0.030288705602288246,0.3394981622695923,0.2191973179578781,0.27895113825798035,-0.16399651765823364,-0.21524572372436523],"values_recorded":128,"members":[{"code_sha256_prefix":"7a279b81d71aae4b","path":"music_diffusion/networks/diffusion.py","papers":["2006.11239"],"paper_pages":[{"arxiv_id":"2006.11239","page":"/paper/denoising-diffusion-probabilistic-models"}],"arg_sig_recorded":[["input",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"ca9c0e6998de16f8","size":1,"n_papers":1,"shape":[2,4,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.9594464302062988,0.0,0.0,0.02361832559108734,0.7769346237182617,0.0,0.0,0.8644130825996399,0.0,0.0,0.0,1.3821874856948853,0.0,0.6475303173065186,1.121242642402649,0.6721562743186951,0.0,0.0,0.2377621829509735,0.0,0.0,0.0,0.0,0.0,0.0,2.2427825927734375,0.0,0.17737317085266113,0.0,0.0,0.0,1.9519116878509521,0.0,0.0,0.0,0.0,0.0,0.4552158713340759,1.414292573928833,0.0,0.34130409359931946,0.9042575359344482,0.0,0.036344014108181,0.0,0.34056356549263,0.5894339084625244,0.042611055076122284,0.0,0.0,0.0,1.2617672681808472,0.0,1.3598401546478271,0.0,0.0,0.981756329536438,2.3938653469085693,0.1252085566520691,0.527766227722168,0.0,0.0,0.0,0.0,1.3969895839691162,0.0,0.0,0.0,0.43701863288879395,0.0,0.0,0.0,0.06900341063737869,0.32943183183670044,0.0,2.2055916786193848,0.5158321857452393,0.36518552899360657,0.0,0.0,0.0,0.0,0.0,0.0,0.8910266757011414,0.0,0.44044843316078186,1.6068084239959717,0.794908344745636,1.040799617767334,0.6961943507194519,0.0,0.0,1.4999994039535522,0.735682487487793,0.0,0.0,0.0,0.0,0.0,0.0,0.3266894519329071,0.0,1.2621817588806152,0.06292352080345154,0.9679047465324402,2.0420968532562256,0.6388688087463379,1.1115888357162476,2.262692451477051,0.47204262018203735,0.0,0.0,0.0,0.0,0.06001022085547447,0.0,0.0,0.0,1.8322092294692993,0.5793481469154358,2.150455951690674,0.0,0.5592603087425232,0.2559303045272827,0.4100726544857025,0.0,0.0],"values_recorded":128,"members":[{"code_sha256_prefix":"0f7a94821f315ab4","path":"models/models.py","papers":["2403.09124"],"paper_pages":[{"arxiv_id":"2403.09124","page":"/paper/single-domain-generalization-for-crowd"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"f44376283dae62c3","size":1,"n_papers":1,"shape":[2,4,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,2.1946566104888916,1.9460337162017822,0.9135919213294983,1.9869762659072876,0.0,1.0342133045196533,0.0,1.406519889831543,0.6406194567680359,0.0,0.0,0.0,0.16641990840435028,0.0,1.3464781045913696,0.0,1.759207010269165,0.0,1.2415794134140015,0.029787510633468628,0.7311146259307861,0.0,0.0,0.7203588485717773,0.0,0.285011887550354,0.0,0.3527040481567383,1.4355517625808716,0.6562255024909973,0.0,0.8262795209884644,0.0,0.0,0.4007524251937866,0.9773152470588684,0.0,0.0,0.14217329025268555,0.0,0.0,3.4216673374176025,0.0,1.373889446258545,2.1709282398223877,2.3652420043945312,1.5882657766342163,0.05682267248630524,0.24440538883209229,1.2434524297714233,0.0,0.5396113395690918,0.2571505308151245,0.20093798637390137,0.2800556719303131,0.0,0.0,0.05230426788330078,1.675096035003662,0.0,0.02000558376312256,0.5989710092544556,0.0,0.541429877281189,1.4046813249588013,0.7608749866485596,0.2379847913980484,0.519077479839325,0.7219001650810242,0.0,0.0,0.6089755892753601,0.0,0.0,0.0,0.0,0.0,0.0,0.028996050357818604,0.0,1.3588833808898926,0.0,0.0,0.0,2.2100374698638916,0.0,0.0,1.2457102537155151,0.7514816522598267,0.0,1.292459487915039,1.292844295501709,0.278521865606308,0.0,0.0,0.44200974702835083,0.9512078762054443,0.0,0.0,0.0,0.0,0.0,0.0,0.19129540026187897,0.0,0.0,2.901747703552246,0.1223439872264862,1.01015305519104,3.0159151554107666,0.0,0.0,0.11982941627502441,3.031184673309326,1.0637023448944092,1.9374651908874512,0.0,0.0,0.49500659108161926,0.17844942212104797,0.028680860996246338,2.8227505683898926,0.0,0.0,0.0,0.0,0.13739217817783356],"values_recorded":128,"members":[{"code_sha256_prefix":"66261d499d347197","path":"src/models/UNet.py","papers":["1505.04597"],"paper_pages":[{"arxiv_id":"1505.04597","page":"/paper/u-net-convolutional-networks-for-biomedical"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]},{"bucket":[[3,"float","float32"]],"n_implementations_compared":3,"n_papers":3,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"53414f5197e716b4","size":3,"n_papers":3,"shape":[2,8,8],"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":[1.4248713254928589,0.9155221581459045,0.5519489049911499,0.8021745085716248,-0.11909051984548569,0.8402886390686035,0.1922711431980133,0.7087292671203613,-0.5206825137138367,0.7902899980545044,0.1645151525735855,-0.025679439306259155,0.6021676659584045,-0.49561840295791626,0.3798801898956299,-0.27644360065460205,1.5542997121810913,0.923422634601593,0.2299683392047882,0.7360377311706543,-0.05591611564159393,0.8157578110694885,0.14658629894256592,1.114911675453186,0.9938642382621765,-0.337585985660553,0.496773898601532,0.6567912101745605,0.12923568487167358,0.9282722473144531,0.21604575216770172,0.6386550664901733,-1.14265775680542,-0.07628953456878662,-0.281363844871521,-0.4732814431190491,-0.11277751624584198,-0.6915345191955566,-0.22284100949764252,-0.6166223287582397,-0.7571732401847839,0.3925183415412903,-1.001706838607788,-0.4535362422466278,-0.020914213731884956,-0.3114439845085144,-0.4020080268383026,0.2505069971084595,-0.5174179077148438,0.5782811045646667,0.6194425821304321,0.37006905674934387,0.9352284669876099,-0.9741171598434448,0.9204620122909546,-0.9761199951171875,-1.1885442733764648,1.560316801071167,-0.8781274557113647,-0.3552703857421875,0.7178115248680115,-0.6842712163925171,0.2844083607196808,0.22666767239570618,0.53323894739151,1.2985036373138428,1.408564567565918,0.37169861793518066,0.52802973985672,1.0737273693084717,-0.035918671637773514,0.10237795114517212,0.6476322412490845,0.7144081592559814,-0.37117546796798706,0.6392972469329834,0.03672380745410919,0.2002040445804596,0.8460224866867065,1.1939561367034912,-0.005235872231423855,1.4812008142471313,0.992461621761322,0.2998981177806854,1.2465695142745972,1.0268816947937012,0.045254722237586975,0.16418695449829102,0.496560275554657,-0.30188849568367004,0.7244899868965149,0.229970321059227,0.01959538459777832,0.03457567095756531,0.04000912606716156,-0.5229306221008301,-0.3327494263648987,-0.22011733055114746,-0.5993652939796448,0.027552783489227295,-0.5019763708114624,-0.47777092456817627,-0.03244028985500336,0.20936870574951172,-1.3218637704849243,0.38707971572875977,-0.5653703212738037,-1.2347395420074463,1.091199517250061,0.31068724393844604,-0.32304802536964417,0.5289730429649353,1.0392296314239502,0.509199321269989,-0.6678352355957031,1.1392418146133423,-0.5285964012145996,0.12361632287502289,1.2359400987625122,1.2807948589324951,-0.5410417318344116,1.1660863161087036,-0.7265582084655762,0.12092326581478119,1.2163265943527222,0.7367268204689026,0.4971846640110016,1.6440212726593018],"values_recorded":128,"members":[{"code_sha256_prefix":"032b67e962be8a73","path":"models/REBAR/REBAR_SSLModel.py","papers":["2311.00519"],"paper_pages":[{"arxiv_id":"2311.00519","page":"/paper/retrieval-based-reconstruction-for-time"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"0e30f1c230eef5dc","path":"ts2vec.py","papers":["2310.14017"],"paper_pages":[{"arxiv_id":"2310.14017","page":"/paper/contrast-everything-a-hierarchical"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"e4d4c00eca81ac32","path":"trep.py","papers":["2310.04486"],"paper_pages":[{"arxiv_id":"2310.04486","page":"/paper/t-rep-representation-learning-for-time-series"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]}]}