{"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/denormalize","entry":"denormalize","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":9,"n_papers":11,"n_buckets":4,"n_distinct_outputs":8,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":3,"by_error":{"RuntimeError":2,"ValueError":1}},"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/denormalize","buckets":[{"bucket":[[4,"float","float32"]],"n_implementations_compared":4,"n_papers":5,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"e662d3c07bf6b494","size":2,"n_papers":2,"shape":[2,3,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":2,"torch_reference_conventions_with_this_digest":[],"values":[0.6505910158157349,0.6345551609992981,0.8161537647247314,0.7365657091140747,0.7454407215118408,0.439216673374176,0.4228294789791107,0.6755232214927673,0.5636279582977295,0.4546841084957123,0.21236246824264526,0.48208850622177124,0.32262206077575684,0.385109543800354,-0.12544924020767212,0.6711684465408325,0.354520708322525,0.4841192364692688,0.5887964963912964,0.12810736894607544,0.2935958504676819,0.7139224410057068,0.36694857478141785,0.777108907699585,0.5061013698577881,0.721371591091156,-0.007248640060424805,0.41812780499458313,0.5398309230804443,0.4568767249584198,0.656547486782074,0.34443745017051697,0.3111913800239563,0.6356424689292908,0.29717397689819336,0.2967696785926819,0.25707873702049255,0.8521500825881958,0.45382970571517944,0.1350947618484497,0.3582894504070282,0.07312804460525513,0.2389189898967743,0.6799110770225525,0.4111080765724182,0.3691348731517792,0.48082995414733887,0.12554705142974854,0.7213233709335327,0.5939353108406067,0.9662799835205078,0.48070046305656433,0.863839864730835,0.34199258685112,-0.06653451919555664,0.4359128475189209,0.16737645864486694,0.02550080418586731,0.17156535387039185,0.47895050048828125,-0.15530908107757568,0.31587910652160645,0.3396188020706177,0.533746600151062,0.645067572593689,0.21167124807834625,0.6290109753608704,0.9251091480255127,0.5645565986633301,0.46095457673072815,1.1513906717300415,0.47249066829681396,0.5917491912841797,0.5196637511253357,0.5715435147285461,0.3059975504875183,0.7007734775543213,0.5158217549324036,0.6043261289596558,0.5091215372085571,-0.09278181195259094,0.38631290197372437,0.4432156980037689,0.21728423237800598,0.5672659873962402,0.682831883430481,0.06368699669837952,0.6485188007354736,0.45738399028778076,0.5048166513442993,0.8498308658599854,0.14305216073989868,0.5179396271705627,0.43926766514778137,0.09825924038887024,0.3417292833328247],"values_recorded":96,"members":[{"code_sha256_prefix":"0a23d935ca395f43","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","papers":["2306.17253"],"paper_pages":[{"arxiv_id":"2306.17253","page":"/paper/towards-zero-shot-scale-aware-monocular-depth"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"7496518009557dce","path":"waffle_tools.py","papers":["2210.07183"],"paper_pages":[{"arxiv_id":"2210.07183","page":"/paper/visual-classification-via-description-from"}],"arg_sig_recorded":[["images",4,"float","float32"]],"scalar_args":{"means":"(0.485, 0.456, 0.406)","stds":"(0.229, 0.224, 0.225)"},"class_bearing":false}]},{"output_sha":"53994da6dabc0482","size":1,"n_papers":2,"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":[0.861552357673645,0.8265396356582642,1.0,1.0,1.0,0.40003639459609985,0.36425650119781494,0.9159895777702332,0.6716766357421875,0.4338080585002899,0.0,0.49364301562309265,0.14546296000480652,0.28189852833747864,0.0,0.9064812660217285,0.2734836935997009,0.5627661347389221,0.7964207530021667,0.0,0.13749077916145325,1.0,0.3012245297431946,1.0,0.611833393573761,1.0,0.0,0.4154638350009918,0.6871225237846375,0.5019569396972656,0.947650671005249,0.25097644329071045,0.2893141806125641,1.0,0.2581644058227539,0.25726592540740967,0.16906386613845825,1.0,0.6062882542610168,0.0,0.3939765691757202,0.0,0.12870889902114868,1.0,0.5113512873649597,0.4180775284767151,0.6662888526916504,0.0,1.0,0.7378499507904053,1.0,0.49061235785484314,1.0,0.1877567172050476,0.0,0.3928227722644806,0.0,0.0,0.0,0.4867914915084839,0.0,0.13074037432670593,0.18257376551628113,0.606433629989624,0.9220259189605713,0.0,0.8861851692199707,1.0,0.742313802242279,0.5110593438148499,1.0,0.536809504032135,0.8030115962028503,0.6421065926551819,0.7579096555709839,0.16517311334609985,1.0,0.6335306763648987,0.8310850858688354,0.618574857711792,0.0,0.4562509059906006,0.582701563835144,0.08063164353370667,0.858368992805481,1.0,0.0,1.0,0.6141866445541382,0.7195925116539001,1.0,0.0,0.7487547993659973,0.57392817735672,0.0,0.3571762144565582],"values_recorded":96,"members":[{"code_sha256_prefix":"2d094cdb029a3669","path":"inference.py","papers":["2504.12739","2605.26702"],"paper_pages":[{"arxiv_id":"2504.12739","page":"/paper/mask-image-watermarking"},{"arxiv_id":"2605.26702","page":"/paper/arxiv-2605-26702"}],"arg_sig_recorded":[["images",4,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"91893c6722f7d07b","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":[0.6757019758224487,0.6568911075592041,0.8699161410331726,0.7765550017356873,0.7869659066200256,0.42774829268455505,0.4085252285003662,0.7049488425254822,0.5736895203590393,0.44589245319366455,0.1616358757019043,0.47803932428359985,0.2909764051437378,0.3642776608467102,-0.23463571071624756,0.6998404264450073,0.3394489288330078,0.4906294345855713,0.6127385497093201,0.07533109188079834,0.2683783173561096,0.7587016224861145,0.35394641757011414,0.8324105143547058,0.516272246837616,0.7673912644386292,-0.08256566524505615,0.41364848613739014,0.5556187033653259,0.458850234746933,0.6917721033096313,0.32768651843070984,0.29200607538223267,0.6896780729293823,0.2748252749443054,0.2743297219276428,0.22568151354789734,0.9550461769104004,0.4668344557285309,0.07616868615150452,0.34973305463790894,0.00021755695343017578,0.20342355966567993,0.7439370155334473,0.4144715666770935,0.36302605271339417,0.4999280571937561,0.06446626782417297,0.7586749196052551,0.6092417240142822,1.0460224151611328,0.4764110743999481,0.9258546233177185,0.3136991262435913,-0.16552555561065674,0.4238727390766144,0.10886484384536743,-0.057563066482543945,0.11377865076065063,0.4743582606315613,-0.2696629762649536,0.2830665707588196,0.3109145164489746,0.538637101650238,0.6783804297447205,0.1728108525276184,0.6596499085426331,1.0050570964813232,0.5844619274139404,0.46360719203948975,1.2690210342407227,0.4770643711090088,0.6161829233169556,0.5320931673049927,0.5926124453544617,0.28284525871276855,0.7433630228042603,0.5276113152503967,0.6308542490005493,0.519795298576355,-0.2031342089176178,0.384080708026886,0.45382511615753174,0.17690634727478027,0.6058706045150757,0.7475169897079468,-0.011354118585586548,0.7054601907730103,0.47119084000587463,0.529327929019928,0.952203631401062,0.08592185378074646,0.5454124808311462,0.44898614287376404,0.031020253896713257,0.32943567633628845],"values_recorded":96,"members":[{"code_sha256_prefix":"59c2ebaf239e6558","path":"certify_promptsmooth_plip.py","papers":["2408.16769"],"paper_pages":[{"arxiv_id":"2408.16769","page":"/paper/promptsmooth-certifying-robustness-of-medical"}],"arg_sig_recorded":[["normalized_batch",4,"float","float32"]],"scalar_args":{"mean":"(0.48145466, 0.4578275, 0.40821073)","std":"(0.26862954, 0.26130258, 0.27577711)"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"]],"n_implementations_compared":3,"n_papers":3,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"1d3f8ee57486362b","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":[28.026287078857422,-5.337762832641602,14.76053237915039,3.091129779815674,0.9715051651000977,-0.30471229553222656,3.3723907470703125,15.72889232635498,15.188759803771973,19.59145736694336,6.028004169464111,-5.683481216430664,7.114648818969727,33.22108840942383,4.852160453796387,15.505285263061523,10.663954734802246,-6.228755950927734,14.321113586425781,5.938141345977783,9.774057388305664,-1.8078241348266602,4.631317138671875,19.836742401123047,2.0438718795776367,14.332744598388672,19.449777603149414,20.175182342529297,-2.257857322692871,22.74217987060547,-3.2222185134887695,4.058908939361572],"values_recorded":32,"members":[{"code_sha256_prefix":"b778ce8816352373","path":"magnitude.py","papers":["2409.07961"],"paper_pages":[{"arxiv_id":"2409.07961","page":"/paper/estimating-atmospheric-variables-from-digital"}],"arg_sig_recorded":[["tensor",2,"float","float32"]],"scalar_args":{"min_val":"10.0","max_val":"20.0"},"class_bearing":false}]},{"output_sha":"2dd79256ed45d1e2","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":[0.8978019952774048,0.11243408918380737,0.51311194896698,-0.6908870339393616,-0.9028494954109192,-1.0304712057113647,-0.6627609133720398,0.5728892087936401,0.6038225889205933,0.6708486080169678,0.316630095243454,-1.5683481693267822,-0.28853508830070496,2.322108745574951,-0.5147839784622192,0.5505285859107971,0.5002045631408691,0.09247586131095886,0.5032250285148621,-0.4061858654022217,-0.02259422466158867,-1.180782437324524,-0.5368682742118835,0.983674168586731,0.3028046786785126,0.5530534982681274,0.618619978427887,1.0175182819366455,-1.225785732269287,1.274217963218689,-1.3222218751907349,-0.5941091179847717],"values_recorded":32,"members":[{"code_sha256_prefix":"b6cec6dc0ac87904","path":"Branch_full_ImageNet_1k/recover/data_synthesis_without_optim.py","papers":["2306.13092"],"paper_pages":[{"arxiv_id":"2306.13092","page":"/paper/squeeze-recover-and-relabel-dataset"}],"arg_sig_recorded":[["image_tensor",2,"float","float32"]],"scalar_args":{"use_fp16":"False"},"class_bearing":false}]},{"output_sha":"94cdf28f6dc25fbd","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":[180.2628631591797,-153.37762451171875,47.605323791503906,-69.08870697021484,-90.28495025634766,-103.047119140625,-66.27609252929688,57.28892135620117,51.887596130371094,95.91456604003906,-39.71995544433594,-156.83482360839844,-28.85350799560547,232.21087646484375,-51.478397369384766,55.052860260009766,6.6395440101623535,-162.2875518798828,43.21113967895508,-40.618587493896484,-2.259422540664673,-118.0782470703125,-53.68682861328125,98.36741638183594,-79.561279296875,43.32744216918945,94.49777221679688,101.7518310546875,-122.57857513427734,127.42179870605469,-132.22218322753906,-59.410911560058594],"values_recorded":32,"members":[{"code_sha256_prefix":"600affad5e62864a","path":"src/train_energy_staged.py","papers":["2411.01578"],"paper_pages":[{"arxiv_id":"2411.01578","page":"/paper/integrating-graph-neural-networks-and-many"}],"arg_sig_recorded":[["y",2,"float","float32"]],"scalar_args":{"max_val":"100.0","min_val":"0.0"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[1,"float","float32"],[1,"float","float32"]],"n_implementations_compared":1,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"2ed5430599a9ac43","size":1,"n_papers":2,"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":[-2.5332651138305664,-0.08387304842472076,1.324923038482666,-0.23560452461242676,-0.017123311758041382,-0.0016159415245056152,-0.5491737127304077,-0.2792402505874634,-1.3728952407836914,0.3078434467315674,0.541080892086029,0.4331924319267273,-0.125399649143219,0.17617714405059814,-0.7901452779769897,-0.2752704918384552,-0.9639031291007996,-0.09787335991859436,1.2854803800582886,-0.45260247588157654,-0.1722732037305832,-0.009587205946445465,-0.7541823387145996,-0.3521682620048523,-0.18474334478378296,0.22521251440048218,1.745835304260254,-1.537743330001831,0.03979599475860596,0.12060569226741791,0.5247191190719604,-0.07205916196107864],"values_recorded":32,"members":[{"code_sha256_prefix":"60a2ef2b4904edd8","path":"cadm/dynamics/mlp_cadm_ensemble_cem_dynamics.py","papers":["2010.13303","2005.06800"],"paper_pages":[{"arxiv_id":"2010.13303","page":"/paper/trajectory-wise-multiple-choice-learning-for"},{"arxiv_id":"2005.06800","page":"/paper/context-aware-dynamics-model-for"}],"arg_sig_recorded":[["data_array",2,"float","float32"],["mean",1,"float","float32"],["std",1,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[3,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"fd6bbb4d65d3a7ec","size":1,"n_papers":1,"shape":[2,4,8],"dtype":"uint8","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[13.0,86.0,224.0,94.0,146.0,201.0,84.0,78.0,111.0,129.0,19.0,29.0,234.0,105.0,146.0,179.0,111.0,32.0,116.0,226.0,54.0,14.0,76.0,249.0,249.0,245.0,31.0,88.0,252.0,29.0,11.0,105.0,5.0,109.0,233.0,24.0,254.0,207.0,133.0,93.0,232.0,13.0,255.0,40.0,252.0,109.0,177.0,242.0,84.0,115.0,222.0,0.0,194.0,151.0,37.0,4.0,222.0,18.0,82.0,53.0,110.0,29.0,222.0,17.0],"values_recorded":64,"members":[{"code_sha256_prefix":"8a74ff00c12f2f24","path":"test_new.py","papers":["1609.04802"],"paper_pages":[{"arxiv_id":"1609.04802","page":"/paper/photo-realistic-single-image-super-resolution"}],"arg_sig_recorded":[["input_data",3,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}