{"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/resblock","entry":"ResBlock","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":6,"n_papers":5,"n_buckets":2,"n_distinct_outputs":6,"n_class_bearing":6,"not_compared":{"not_run_on_shared_input":{"n":18,"by_error":{"RuntimeError":18}},"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/resblock","buckets":[{"bucket":[[3,"float","float32"]],"n_implementations_compared":3,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"3a4892cf5d6ba798","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":[-0.4895937144756317,1.9265090227127075,-0.7445900440216064,0.31996893882751465,0.7100772261619568,-1.4005149602890015,0.4037742018699646,-0.3610650897026062,-1.9175794124603271,0.14350928366184235,-0.6529565453529358,-0.4854874014854431,1.0161168575286865,-0.17175519466400146,0.19845589995384216,0.5556168556213379,1.200197458267212,-1.0983526706695557,0.13034850358963013,0.5854164361953735,-0.486162394285202,1.4441312551498413,-0.9007039070129395,0.8073232173919678,1.8368481397628784,1.6589515209197998,0.11678430438041687,0.16337771713733673,-0.5668512582778931,1.6775267124176025,-0.5474191904067993,2.456331253051758,-0.5199816226959229,1.9787331819534302,-0.9368953704833984,0.08977001905441284,1.1142034530639648,1.0483506917953491,0.8558620810508728,1.7094347476959229,-0.9565215110778809,-1.0649967193603516,-1.2087838649749756,-0.7533677816390991,0.8389948606491089,-0.3959941864013672,0.5685808658599854,0.8690837621688843,-1.0276975631713867,-0.3671260476112366,1.1639387607574463,-1.0915194749832153,0.5628317594528198,0.8166384696960449,-0.8079288601875305,-1.0561619997024536,-0.41146376729011536,1.769059658050537,2.1730313301086426,-0.17329096794128418,2.3493237495422363,1.6027415990829468,-0.606535792350769,-0.18605342507362366],"values_recorded":64,"members":[{"code_sha256_prefix":"48c9333c7884fee0","path":"models/models.py","papers":["2301.07173"],"paper_pages":[{"arxiv_id":"2301.07173","page":"/paper/towards-voice-reconstruction-from-eeg-during"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"624fffa1389dbfb2","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":[-1.1432690620422363,1.6489776372909546,-1.7504072189331055,-0.4035401940345764,0.37771129608154297,-1.182906150817871,-0.19710637629032135,0.07127013802528381,-2.5915298461914062,-0.16610220074653625,0.002715170383453369,-0.5947822332382202,1.0728901624679565,-0.0730612650513649,0.40405482053756714,0.4566938579082489,1.4697940349578857,0.2800792455673218,0.5480522513389587,0.5326830148696899,-0.20524874329566956,0.9401317834854126,-0.4474548101425171,1.573864459991455,0.7678837776184082,0.451358824968338,-0.32875505089759827,-0.37071770429611206,-0.9317349195480347,0.8275435566902161,-0.7960370779037476,1.4233431816101074,-1.373892903327942,2.2257323265075684,-1.5595862865447998,-0.6384134292602539,1.503793478012085,0.6221626996994019,-0.25636744499206543,1.7674245834350586,-1.5124757289886475,-0.8639923334121704,-0.4114181399345398,-0.18215155601501465,1.0932908058166504,0.11960428953170776,0.384293794631958,0.6460511684417725,-0.564384937286377,0.7457287311553955,0.9021008610725403,-0.7321770191192627,1.1538628339767456,-0.01834331452846527,-1.2273356914520264,-0.5064728260040283,-1.5280494689941406,1.2640223503112793,1.5032827854156494,-0.23651403188705444,1.5177180767059326,1.3596220016479492,-1.3536937236785889,-1.2373478412628174],"values_recorded":64,"members":[{"code_sha256_prefix":"485d1239c223cc52","path":"models.py","papers":["1512.03385"],"paper_pages":[{"arxiv_id":"1512.03385","page":"/paper/deep-residual-learning-for-image-recognition"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"a28a5b15fd8a96ee","size":1,"n_papers":1,"shape":[2,3,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.802334189414978,1.0765964984893799,0.019885167479515076,0.9271877408027649,-0.4879736602306366,0.8825724720954895,-0.12195029854774475,1.1594456434249878,0.5016123652458191,-0.9672439098358154,0.09976011514663696,-0.14586657285690308,-0.5933159589767456,0.2623120844364166,-0.2954334020614624,-0.21399088203907013,-0.9586474299430847,-0.34214287996292114,-0.43072789907455444,-0.3805798888206482,0.12084399163722992,-0.7688292264938354,-0.09665541350841522,-0.6811204552650452,-0.2743012011051178,1.499255895614624,1.1318870782852173,-0.03586587309837341,1.2530124187469482,0.9781127572059631,-0.4212866425514221,-0.082889124751091,-0.01681961491703987,-0.8995087146759033,0.2822904884815216,-0.1202225536108017,-0.8149518966674805,-0.6327930092811584,-0.6554923057556152,-1.4109313488006592,-0.23138652741909027,-0.4898759126663208,-1.0165083408355713,-0.4143099784851074,-0.4269736409187317,-0.546889066696167,0.07454025745391846,0.2685432434082031],"values_recorded":48,"members":[{"code_sha256_prefix":"8e38abf13e08c596","path":"src/nbi/nn/resnet.py","papers":["1512.03385"],"paper_pages":[{"arxiv_id":"1512.03385","page":"/paper/deep-residual-learning-for-image-recognition"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]},{"bucket":[[4,"float","float32"]],"n_implementations_compared":3,"n_papers":3,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"115d141ca4be1065","size":1,"n_papers":1,"shape":[2,5,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.6365618109703064,0.09630918502807617,-0.207174152135849,-0.06017795205116272,-0.11586818844079971,-0.2125820517539978,-0.0862119197845459,-0.147659569978714,0.33007684350013733,0.15387918055057526,-0.0367758646607399,-0.4901040196418762,-0.013638816773891449,0.06504550576210022,-0.2557615637779236,-0.07624707370996475,-0.30583998560905457,-0.06824074685573578,0.10991431772708893,0.05304202437400818,-0.1320030391216278,-0.4095631241798401,-0.4783730208873749,0.5201342105865479,0.12081028521060944,-0.13091860711574554,-0.4950001537799835,-0.30572670698165894,0.14461718499660492,-0.2380921095609665,-0.13440212607383728,0.08385387063026428,0.021934635937213898,0.22963806986808777,-0.16191977262496948,-0.3032533526420593,-0.13450555503368378,0.4479519724845886,-0.1277741938829422,-0.2726753354072571,-0.2650710642337799,-0.41653624176979065,0.01625513844192028,0.1968124508857727,0.18267521262168884,0.2553473114967346,-0.03898754343390465,-0.019356705248355865,-0.31154027581214905,-0.8000866174697876,-0.41758835315704346,-0.5120925903320312,-0.6896283626556396,-0.4680063724517822,-0.18451926112174988,-0.25549009442329407,-0.5808110237121582,-0.07409663498401642,0.13296830654144287,-0.4377184212207794,-0.2787543535232544,0.01693996973335743,0.04693704843521118,-0.6074917316436768,-0.7103314995765686,-0.8656167984008789,-0.5729196667671204,-0.13627198338508606,-0.7445003390312195,-0.16803434491157532,0.06507083028554916,-0.13897812366485596,-0.3085401654243469,0.02850741147994995,-0.2095712125301361,-0.2485477775335312,-0.2491389513015747,-0.011671984568238258,-0.34509503841400146,-0.28156110644340515,-0.4451543688774109,0.06861867755651474,-0.5575852394104004,0.046204857528209686,-0.6601521372795105,-0.039213985204696655,0.23591259121894836,-0.24563954770565033,-0.03628282994031906,0.18467682600021362,-0.1998416781425476,-0.2673199772834778,-0.0356934517621994,-0.0019272342324256897,-0.3999554216861725,-0.2844386100769043,0.021826833486557007,-0.15865951776504517,0.21854376792907715,0.3463791608810425,-0.07101458311080933,-0.2751394212245941,0.027372419834136963,-0.5313296318054199,0.07265593111515045,-0.238689124584198,-0.8016214966773987,-0.03826509416103363,-0.010964617133140564,-0.22986532747745514,0.00863693654537201,-0.3765292763710022,-0.3349701762199402,-0.08219188451766968,-0.42611163854599,-0.8286880254745483,0.11101534962654114,0.13917064666748047,-1.670961856842041,0.108767569065094,-0.010053670033812523,0.06154116988182068,0.4438919723033905,0.14620235562324524,-0.10168302804231644,0.2686172127723694,0.3587726950645447,-0.02274318039417267,-0.19810965657234192,-0.1524379551410675,-0.5220928192138672,0.5084071159362793,-0.7094660997390747,-0.3938175439834595,0.7420612573623657,-0.47576016187667847,-0.1582372486591339,-0.0030417367815971375,-0.42587441205978394,-0.5953513383865356,-0.15790632367134094,-0.6066023111343384,-0.12378813326358795,-0.16820621490478516,-0.30098438262939453,-0.3544504642486572,-0.43652063608169556,0.07805491983890533,-1.003763198852539,-0.059791505336761475,0.16418948769569397,-0.37263602018356323,-0.10109773278236389,-0.3325503468513489,-0.7987506985664368,0.23336583375930786,-0.4671882390975952,-0.04758521914482117,-0.4763867259025574,-0.3368126451969147],"values_recorded":160,"members":[{"code_sha256_prefix":"c844437a798458b7","path":"network/resnet38d.py","papers":["1606.00915"],"paper_pages":[{"arxiv_id":"1606.00915","page":"/paper/deeplab-semantic-image-segmentation-with-deep"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"get_x_bn_relu":"False"},"class_bearing":true}]},{"output_sha":"3db878bafbe0f0df","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":[0.6281334757804871,1.2190171480178833,0.7654322385787964,1.1570183038711548,0.7716355323791504,0.9407086968421936,0.46175333857536316,-0.003409236902371049,0.14924488961696625,-0.012889440171420574,-0.000676891126204282,1.15243399143219,-0.0025009186938405037,-0.0025713283102959394,-0.014845959842205048,0.06631280481815338,0.5471373200416565,0.8417580723762512,1.339333176612854,0.9305760860443115,0.803977370262146,0.4870685636997223,0.2742899954319,0.7308274507522583,0.23400430381298065,-0.0036966886837035418,-0.006161445751786232,0.4705753028392792,-0.003871976165100932,-0.005026618018746376,-0.020091237500309944,0.6301578879356384,-0.0044484431855380535,-0.00722259096801281,0.4911951720714569,-0.012223279103636742,-0.005617446731775999,-0.004446099512279034,-0.0064602927304804325,1.4799389839172363,-0.0002566575421951711,1.4244303703308105,-0.017766423523426056,-0.009618006646633148,0.06594482064247131,-0.0026893680915236473,0.32085177302360535,0.006663601845502853,-0.0037329443730413914,-0.012357057072222233,-0.002677412237972021,-0.009490417316555977,-0.005195373669266701,-0.01139913685619831,-0.005161148961633444,0.8678504824638367,-0.002158768940716982,1.2363938093185425,0.19346190989017487,-0.012464337050914764,0.10765465348958969,-0.0007491408614441752,0.8877602815628052,-0.0005937060341238976,-0.006263473071157932,0.8446356654167175,1.3552541732788086,-0.007788862567394972,1.5443581342697144,0.5739310383796692,-0.03033047914505005,0.7323197722434998,-0.007072132546454668,-0.007440538611263037,0.4301438629627228,-0.003348514437675476,-0.01386943832039833,-0.0040865931659936905,-0.012495987117290497,0.16664612293243408,0.5398019552230835,0.42083990573883057,1.9758920669555664,0.05025933310389519,1.7015657424926758,-0.00031463068444281816,-0.02227388322353363,0.17449916899204254,-0.010628770105540752,-0.0160226933658123,-0.0029756047297269106,-0.00157525937538594,-0.021207217127084732,-0.005138057749718428,-0.005405424162745476,0.286387175321579,1.562899112701416,-0.011927294544875622,0.27569901943206787,1.933982491493225,-0.001934337429702282,-0.009945384226739407,2.9601407051086426,-0.008467068895697594,-0.00044636710663326085,-0.004421773832291365,-0.008462783880531788,-0.0017141987336799502,0.34666845202445984,-0.0011927393497899175,0.9211267828941345,0.1365129053592682,1.3538416624069214,-0.007421575486660004,-0.010322332382202148,1.2900534868240356,-0.01358107291162014,-0.0076347277499735355,3.243976354598999,-0.008978521451354027,0.5681303143501282,0.5769798159599304,-0.009594555012881756,0.20239242911338806,1.0592142343521118,-0.0019559012725949287,1.0664541721343994,-0.0010735023533925414],"values_recorded":128,"members":[{"code_sha256_prefix":"50500d4a79d3faf1","path":"models/networks/conditional_nets/resnet_conditional.py","papers":["2306.01630"],"paper_pages":[{"arxiv_id":"2306.01630","page":"/paper/a-conditional-normalizing-flow-for"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"db880c8d8a6c11cd","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":[-0.19456899166107178,0.8685619235038757,-0.7067421674728394,0.3382916748523712,-0.3580598831176758,1.3879276514053345,0.5579254627227783,-1.6569890975952148,-0.261585533618927,-1.8703479766845703,0.23361028730869293,1.243234634399414,-0.19143208861351013,-0.1790943592786789,0.03392219543457031,-0.7494663596153259,1.2872254848480225,-0.5533132553100586,0.6982517242431641,2.285330295562744,2.1489522457122803,-2.5841310024261475,0.23615893721580505,0.6594239473342896,0.4344730079174042,-0.06611265242099762,0.7019133567810059,-0.9415742754936218,-0.9651506543159485,-0.1500694751739502,-3.2728993892669678,1.9197838306427002,-0.37412551045417786,-0.5504134297370911,-1.0659524202346802,-0.5727688670158386,-0.7595768570899963,-0.7304290533065796,-0.25794246792793274,-0.29985445737838745,-0.22690698504447937,0.08819663524627686,1.000540018081665,-0.25531888008117676,0.41452646255493164,0.20179376006126404,1.6385130882263184,-0.3510235846042633,-0.0760425329208374,-0.11878082156181335,-0.9819112420082092,-0.01802869141101837,-0.6461188793182373,-0.01012963056564331,0.48971229791641235,-1.2478455305099487,-0.3241371810436249,-0.1736350953578949,1.5099252462387085,0.3059675395488739,0.3083227872848511,0.1337633728981018,1.4229564666748047,-0.17929667234420776,-2.233961582183838,0.4846208989620209,0.3269743323326111,-1.7303805351257324,0.4034602642059326,1.1572387218475342,-2.124588966369629,1.2720011472702026,0.2526412606239319,0.5763702392578125,1.599184274673462,-0.7444931268692017,0.01678997464478016,0.09605849534273148,-1.624213457107544,-0.19102981686592102,1.564530611038208,0.8667535185813904,1.011976957321167,-1.1849159002304077,0.83326256275177,-1.341288447380066,-3.4488985538482666,-1.0727920532226562,-1.9977725744247437,-2.704719305038452,-3.276519298553467,1.4173091650009155,-3.616321563720703,-0.98317950963974,-0.061985790729522705,0.26691141724586487,-0.234771728515625,-0.40477755665779114,-1.2984977960586548,0.372211754322052,-1.8532708883285522,-0.16277290880680084,1.9028160572052002,-0.1252313107252121,1.0418732166290283,1.473210334777832,-0.149898499250412,0.3871418237686157,1.7315669059753418,0.3474445939064026,0.3835119307041168,-0.13232088088989258,-1.0691083669662476,0.6803115010261536,-1.2751120328903198,-0.8820368051528931,-1.2288202047348022,0.05753237009048462,0.8526010513305664,1.1273163557052612,1.0203566551208496,1.5401835441589355,1.347246766090393,0.26591914892196655,1.399040699005127,0.5513603687286377,-0.03992615267634392,-0.16912630200386047],"values_recorded":128,"members":[{"code_sha256_prefix":"3633e85d48e9359c","path":"src/models/DCVC_net.py","papers":["2109.15047"],"paper_pages":[{"arxiv_id":"2109.15047","page":"/paper/deep-contextual-video-compression"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]}]}