{"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/norm","entry":"norm","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":23,"n_papers":26,"n_buckets":6,"n_distinct_outputs":15,"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":2,"n_papers":4,"recorded_shared_digest_equals_own_fixture_digest":2},"output_not_digested_non_numeric":{"n":0,"by_type":{}}},"withdrawn_excluded":0,"code_page":"/code/norm","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":15,"n_papers":18,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"52b2d26799446195","size":4,"n_papers":5,"shape":[4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":4,"torch_reference_conventions_with_this_digest":[],"values":[2.9917142391204834,3.138503074645996,2.3749611377716064,2.8242647647857666],"values_recorded":4,"members":[{"code_sha256_prefix":"e68ef3509ca0d2e9","path":"ebm_models.py","papers":["2010.00654","2309.00073"],"paper_pages":[{"arxiv_id":"2010.00654","page":"/paper/vaebm-a-symbiosis-between-variational"},{"arxiv_id":"2309.00073","page":"/paper/diffusion-variational-autoencoder-for"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{"dim":"1"},"class_bearing":false},{"code_sha256_prefix":"3df02af32c33da5a","path":"nff/nn/models/painn.py","papers":["2102.03150"],"paper_pages":[{"arxiv_id":"2102.03150","page":"/paper/equivariant-message-passing-for-the"}],"arg_sig_recorded":[["vec",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"dac7f0e24f48b251","path":"apollo_circle.py","papers":["2205.13891"],"paper_pages":[{"arxiv_id":"2205.13891","page":"/paper/transformers-from-an-optimization-perspective"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"f5594684df370bd8","path":"heterogeneous/torchmoo/mtl.py","papers":["2206.04496"],"paper_pages":[{"arxiv_id":"2206.04496","page":"/paper/mitigating-modality-collapse-in-multimodal"}],"arg_sig_recorded":[["tensor",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"2803cfee2d9ac85e","size":4,"n_papers":4,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":4,"torch_reference_conventions_with_this_digest":[],"values":[0.6025403738021851,-0.5126747488975525,0.15912389755249023,-0.23093350231647491,-0.30178332328796387,-0.3444417119026184,-0.2215321660041809,0.191491961479187,0.16532593965530396,0.30560609698295593,-0.12655700743198395,-0.49971216917037964,-0.09193398058414459,0.7398778200149536,-0.16402213275432587,0.175411194562912,0.027956431731581688,-0.6833271980285645,0.18194462358951569,-0.17102842032909393,-0.009513513185083866,-0.49717968702316284,-0.22605349123477936,0.41418537497520447,-0.28170618414878845,0.153411403298378,0.3345924913883209,0.3602772355079651,-0.43401941657066345,0.451168030500412,-0.46816498041152954,-0.2103588581085205],"values_recorded":32,"members":[{"code_sha256_prefix":"21d247685c39adc6","path":"model.py","papers":["2302.05160","2412.06171"],"paper_pages":[{"arxiv_id":"2302.05160","page":"/paper/dual-memory-units-with-uncertainty-regulation"},{"arxiv_id":"2412.06171","page":"/paper/holmes-vau-towards-long-term-video-anomaly"}],"arg_sig_recorded":[["data",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"81e946165f36f51e","path":"coco_lm_pytorch/coco_lm_pytorch.py","papers":["2102.08473"],"paper_pages":[{"arxiv_id":"2102.08473","page":"/paper/coco-lm-correcting-and-contrasting-text"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"8774449259dd9b86","path":"coco_lm_pytorch/coco_lm_pytorch.py","papers":["2102.08473"],"paper_pages":[{"arxiv_id":"2102.08473","page":"/paper/coco-lm-correcting-and-contrasting-text"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"abb3b39c6e174088","path":"cifar_mnist/sep_clr_k-jem.py","papers":["2402.11928"],"paper_pages":[{"arxiv_id":"2402.11928","page":"/paper/separating-common-from-salient-patterns-with"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"fd3f107301960133","size":2,"n_papers":2,"shape":[4,1],"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":[8.950353622436523,9.850201606750488,5.640440940856934,7.976470947265625],"values_recorded":4,"members":[{"code_sha256_prefix":"a76b972fcaf75086","path":"forwardforward.py","papers":["2212.13345"],"paper_pages":[{"arxiv_id":"2212.13345","page":"/paper/the-forward-forward-algorithm-some-1"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"p":"2","dim":"-1","keepdims":"True"},"class_bearing":false},{"code_sha256_prefix":"cd402801e7b0ddb3","path":"py_version/transc.py","papers":["1811.04588"],"paper_pages":[{"arxiv_id":"1811.04588","page":"/paper/differentiating-concepts-and-instances-for"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"pnorm":"0"},"class_bearing":false}]},{"output_sha":"035f1e86888be1c4","size":1,"n_papers":3,"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":[1.0,0.0,0.7380266189575195,0.1545564830303192,0.048575252294540405,0.0,0.1686195433139801,0.7864446043968201,0.7594379782676697,0.9795728325843811,0.30140021443367004,0.0,0.35573244094848633,1.0,0.24260801076889038,0.7752642631530762,0.5331977009773254,0.0,0.716055691242218,0.29690706729888916,0.4887028932571411,0.0,0.23156586289405823,0.9918370842933655,0.10219359397888184,0.7166371941566467,0.9724888801574707,1.0,0.0,1.0,0.0,0.20294544100761414],"values_recorded":32,"members":[{"code_sha256_prefix":"32aa054396114d07","path":"posterior_sample.py","papers":["2502.06379","2407.01521","2605.27990"],"paper_pages":[{"arxiv_id":"2502.06379","page":"/paper/solving-linear-gaussian-bayesian-inverse"},{"arxiv_id":"2407.01521","page":"/paper/improving-diffusion-inverse-problem-solving"},{"arxiv_id":"2605.27990","page":"/paper/arxiv-2605-27990"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"8c69b6423dae0ad3","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":[1.0,-1.0,-0.047893524169921875,-1.0,-1.0,-1.0,-1.0,0.14577841758728027,0.03775191307067871,0.9182913303375244,-1.0,-1.0,-1.0,1.0,-1.0,0.10105717182159424,-0.8672091364860535,-1.0,-0.13577717542648315,-1.0,-1.0,-1.0,-1.0,0.9673483371734619,-1.0,-0.1334511637687683,0.8899555206298828,1.0,-1.0,1.0,-1.0,-1.0],"values_recorded":32,"members":[{"code_sha256_prefix":"0489bfec4716b314","path":"SinGAN/functions.py","papers":["1905.01164"],"paper_pages":[{"arxiv_id":"1905.01164","page":"/paper/singan-learning-a-generative-model-from-a"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"bc9e7bc34a68cdb3","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":[0.6025202870368958,-0.5126575827598572,0.15911859273910522,-0.2309257835149765,-0.3017732501029968,-0.34443020820617676,-0.22152476012706757,0.19148555397987366,0.16532067954540253,0.30559638142585754,-0.1265529841184616,-0.4996962547302246,-0.0919310599565506,0.7398542761802673,-0.16401691734790802,0.1754056215286255,0.027955256402492523,-0.6832984685897827,0.18193696439266205,-0.1710212379693985,-0.009513113647699356,-0.4971587657928467,-0.22604398429393768,0.41416794061660767,-0.2816962003707886,0.15340597927570343,0.334580659866333,0.36026448011398315,-0.4340040683746338,0.4511520564556122,-0.46814844012260437,-0.21035142242908478],"values_recorded":32,"members":[{"code_sha256_prefix":"b7b09d9d9a19672a","path":"model.py","papers":["2101.12446"],"paper_pages":[{"arxiv_id":"2101.12446","page":"/paper/counterfactual-state-explanations-for"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"bd1303ad1c87186e","size":1,"n_papers":1,"shape":[],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[5.693633556365967],"values_recorded":1,"members":[{"code_sha256_prefix":"e1d9c760ce9d1c42","path":"DeepKnockoffs/DeepKnockoffs/machine.py","papers":["2106.01528"],"paper_pages":[{"arxiv_id":"2106.01528","page":"/paper/normalizing-flows-for-knockoff-free"}],"arg_sig_recorded":[["X",2,"float","float32"]],"scalar_args":{"p":"2"},"class_bearing":false}]},{"output_sha":"e5506853bb513ae9","size":1,"n_papers":1,"shape":[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":[1.0390275716781616,1.523470401763916,0.36602434515953064,1.0343427658081055,0.6003627181053162,2.3679847717285156,0.6851881742477417,0.48796606063842773],"values_recorded":8,"members":[{"code_sha256_prefix":"79cfb98e536acac6","path":"optimizers/dense/MFAC.py","papers":["2107.03356"],"paper_pages":[{"arxiv_id":"2107.03356","page":"/paper/efficient-matrix-free-approximations-of"}],"arg_sig_recorded":[["v",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[1,"float","float64"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"337416622ab67fd6","size":2,"n_papers":2,"shape":[],"dtype":"float64","type":"float64","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":2,"torch_reference_conventions_with_this_digest":[],"values":[2.223863566483275],"values_recorded":1,"members":[{"code_sha256_prefix":"0c31533258db390a","path":"Code/NMF/ml_base.py","papers":["2004.05209"],"paper_pages":[{"arxiv_id":"2004.05209","page":"/paper/supervised-autoencoders-learn-robust-joint"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"8f0218f1e23e4c15","path":"deep_stable.py","papers":["2003.00394"],"paper_pages":[{"arxiv_id":"2003.00394","page":"/paper/stable-behaviour-of-infinitely-wide-deep"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float64"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"771dbde58a2f354c","size":1,"n_papers":1,"shape":[4,8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.8683188245504256,0.022585455188983854,0.532049952308746,0.236246426311217,0.1825168259659045,0.1501664497937928,0.24337602057081448,0.5565965618514935,0.5429049315745396,0.6545073222283672,0.3106922187342339,0.01382194210378917,0.33823719029666544,1.0,0.2808861682764969,0.5509284427354357,0.4282072633742231,0.0,0.5209113008032484,0.30841431243046824,0.4056495905579203,0.11206460951410568,0.2752881049221286,0.6607249760241508,0.20969987685938365,0.5212061021157185,0.6509159609538037,0.6693039871025641,0.10065686335145413,0.7343738659080881,0.07621161527266795,0.2607783281644746],"values_recorded":32,"members":[{"code_sha256_prefix":"24c29a6cb4733ecd","path":"network.py","papers":["1512.09300"],"paper_pages":[{"arxiv_id":"1512.09300","page":"/paper/autoencoding-beyond-pixels-using-a-learned"}],"arg_sig_recorded":[["X",2,"float","float64"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"bd1303ad1c87186e","size":1,"n_papers":1,"shape":[],"dtype":"float64","type":"float64","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[5.693633973942409],"values_recorded":1,"members":[{"code_sha256_prefix":"d35071d927f4e662","path":"recapp.py","papers":["2206.08627"],"paper_pages":[{"arxiv_id":"2206.08627","page":"/paper/recapp-crafting-a-more-efficient-catalyst-for"}],"arg_sig_recorded":[["M",2,"float","float64"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[4,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"48bf8b9eb7d0e4b2","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":[0.7289974093437195,0.7139336466789246,0.8845238089561462,0.8097603917121887,0.8180974125862122,0.5304363369941711,0.5150425434112549,0.7524182796478271,0.6473059058189392,0.5449662208557129,0.317333847284317,0.5707094073295593,0.4209096133708954,0.4796091616153717,0.0,0.7483274340629578,0.47598883509635925,0.6004486680030823,0.7009754180908203,0.2585529088973999,0.41747966408729553,0.8211399912834167,0.48792389035224915,0.8818211555480957,0.6215591430664062,0.8282938003540039,0.12856388092041016,0.5370737910270691,0.6539513468742371,0.5742863416671753,0.766040027141571,0.46630534529685974,0.4827996492385864,0.7930011749267578,0.4693978726863861,0.4690113067626953,0.43106356263160706,1.0,0.6191734075546265,0.31443700194358826,0.5278292298316956,0.2551918029785156,0.4137013852596283,0.8353255987167358,0.5783281326293945,0.5381982922554016,0.6449878811836243,0.30530861020088196,0.6487702131271362,0.5544939637184143,0.8300555348396301,0.4706921875476837,0.754242479801178,0.36803847551345825,0.06569945067167282,0.43754613399505615,0.23881018161773682,0.13381212949752808,0.24191026389598846,0.46939709782600403,0.0,0.348712682723999,0.36628174781799316,0.5099501013755798,0.6169208884239197,0.28901734948158264,0.6047725677490234,0.8287975788116455,0.5560069680213928,0.47762271761894226,1.0,0.4863508343696594,0.5765806436538696,0.5220415592193604,0.5612932443618774,0.3603837490081787,0.6590674519538879,0.5191347002983093,0.5860962867736816,0.5140653848648071,0.09817782044410706,0.45904529094696045,0.5019060373306274,0.3317281901836395,0.5953441858291626,0.6823916435241699,0.21603447198867798,0.6565460562705994,0.512578010559082,0.5483055710792542,0.8081798553466797,0.2758145332336426,0.5581902265548706,0.4989323019981384,0.24207524955272675,0.42546364665031433],"values_recorded":96,"members":[{"code_sha256_prefix":"2d1316f9f86a0471","path":"dre/mixuploss.py","papers":["2303.16390"],"paper_pages":[{"arxiv_id":"2303.16390","page":"/paper/are-data-driven-explanations-robust-against"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"e915b985d5de44c6","size":1,"n_papers":1,"shape":[2,1,1,1],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[6.603066921234131,8.359642028808594],"values_recorded":2,"members":[{"code_sha256_prefix":"c0bd0f11c7d847e7","path":"attack.py","papers":["1906.04392"],"paper_pages":[{"arxiv_id":"1906.04392","page":"/paper/subspace-attack-exploiting-promising"}],"arg_sig_recorded":[["t",4,"float","float32"]],"scalar_args":{"p":"2"},"class_bearing":false}]}]},{"bucket":[[1,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"ebfdf9421e6b692d","size":1,"n_papers":1,"shape":[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":[0.28683146834373474,0.7068625092506409,1.0,0.3429243266582489,0.5748831033706665,0.6656520962715149,0.0,0.5743772983551025],"values_recorded":8,"members":[{"code_sha256_prefix":"d4d831024e44fed8","path":"class_estimate.py","papers":["2304.06928"],"paper_pages":[{"arxiv_id":"2304.06928","page":"/paper/cipr-an-efficient-framework-with-cross"}],"arg_sig_recorded":[["s",1,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"int","uint8"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"e681dbad78b850b0","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":[0.6666666865348816,1.0,0.6666666865348816,0.3333333432674408,0.3333333432674408,1.0,0.0,0.3333333432674408,0.3333333432674408,0.0,0.3333333432674408,1.0,1.0,1.0,1.0,0.6666666865348816,0.0,0.0,0.6666666865348816,0.0,0.6666666865348816,0.0,0.3333333432674408,0.3333333432674408,1.0,1.0,0.3333333432674408,1.0,1.0,0.6666666865348816,0.3333333432674408,0.6666666865348816],"values_recorded":32,"members":[{"code_sha256_prefix":"8cedd657c11f6f8c","path":"ComputeDice.py","papers":["1803.06815"],"paper_pages":[{"arxiv_id":"1803.06815","page":"/paper/espnet-efficient-spatial-pyramid-of-dilated"}],"arg_sig_recorded":[["im",2,"int","uint8"]],"scalar_args":{},"class_bearing":false}]}]}]}