{"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/reparameterize","entry":"reparameterize","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":12,"n_papers":17,"n_buckets":4,"n_distinct_outputs":5,"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":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/reparameterize","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":9,"n_papers":13,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"6daa96efdfc72ba4","size":8,"n_papers":12,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":8,"torch_reference_conventions_with_this_digest":[],"values":[-0.9701324701309204,-2.0689969062805176,0.15813344717025757,-0.9980325698852539,-0.36245834827423096,-0.6170927286148071,-0.8896365761756897,-2.243915557861328,0.936609148979187,-1.0816253423690796,-0.11025607585906982,-1.427686095237732,-0.18479356169700623,6.274319648742676,0.3485575318336487,0.22489392757415771,-1.3319170475006104,-2.3762402534484863,1.135421872138977,0.2414776086807251,0.5695181488990784,-2.0424768924713135,-0.7978640794754028,4.013927936553955,-0.2916414737701416,-0.29385069012641907,0.6668521761894226,1.322683572769165,-0.47305309772491455,4.273985862731934,-0.8336693048477173,-1.220963954925537],"values_recorded":32,"members":[{"code_sha256_prefix":"3cd91116c815d020","path":"model.py","papers":["2112.00976","2503.09496","2605.09400"],"paper_pages":[{"arxiv_id":"2112.00976","page":"/paper/gaussian-mixture-variational-autoencoder-with"},{"arxiv_id":"2503.09496","page":"/paper/robust-multimodal-survival-prediction-with"},{"arxiv_id":"2605.09400","page":"/paper/arxiv-2605-09400"}],"arg_sig_recorded":[["mu",2,"float","float32"],["logvar",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"dadec7f7cc09688a","path":"models/kovae.py","papers":["2305.15924","2310.02619","2605.17804"],"paper_pages":[{"arxiv_id":"2305.15924","page":"/paper/sample-and-predict-your-latent-modality-free"},{"arxiv_id":"2310.02619","page":"/paper/generative-modeling-of-regular-and-irregular"},{"arxiv_id":"2605.17804","page":"/paper/arxiv-2605-17804"}],"arg_sig_recorded":[["mean",2,"float","float32"],["logvar",2,"float","float32"]],"scalar_args":{"random_sampling":"True"},"class_bearing":false},{"code_sha256_prefix":"26ebad4d064f2bf8","path":"Models.py","papers":["1903.07291"],"paper_pages":[{"arxiv_id":"1903.07291","page":"/paper/semantic-image-synthesis-with-spatially"}],"arg_sig_recorded":[["mu",2,"float","float32"],["logvar",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"2f6aa7a616eabb09","path":"model/crvae_model.py","papers":["2309.02968"],"paper_pages":[{"arxiv_id":"2309.02968","page":"/paper/cr-vae-contrastive-regularization-on"}],"arg_sig_recorded":[["mu",2,"float","float32"],["log_var",2,"float","float32"]],"scalar_args":{"sampling_distribution":"Normal(loc: 0.0, scale: 1.0)"},"class_bearing":false},{"code_sha256_prefix":"447585e6fedec167","path":"model.py","papers":["2205.02309"],"paper_pages":[{"arxiv_id":"2205.02309","page":"/paper/towards-robust-and-semantically-organised"}],"arg_sig_recorded":[["mu",2,"float","float32"],["logvar",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"588fadd7be65d6de","path":"model.py","papers":["2102.05714"],"paper_pages":[{"arxiv_id":"2102.05714","page":"/paper/domain-adaptation-in-reinforcement-learning"}],"arg_sig_recorded":[["mu",2,"float","float32"],["logsigma",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"8425038dea1085de","path":"src/pgmc/vae_models.py","papers":["2603.09288"],"paper_pages":[{"arxiv_id":"2603.09288","page":"/paper/arxiv-2603-09288"}],"arg_sig_recorded":[["mu",2,"float","float32"],["logvar",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"c28f74f4a6577670","path":"pgvae/pgvae.py","papers":["2305.13650"],"paper_pages":[{"arxiv_id":"2305.13650","page":"/paper/property-guided-generative-modelling-for"}],"arg_sig_recorded":[["mu",2,"float","float32"],["logvar",2,"float","float32"]],"scalar_args":{"batch_rng":"<fx_c28f74f4a6577670__reparameterize.BatchRNG object at 0xff"},"class_bearing":false}]},{"output_sha":"32bde78b50576325","size":1,"n_papers":1,"shape":[3,4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.9701324701309204,-2.0689969062805176,0.15813344717025757,-0.9980325698852539,-0.36245834827423096,-0.6170927286148071,-0.8896365761756897,-2.243915557861328,0.936609148979187,-1.0816253423690796,-0.11025607585906982,-1.427686095237732,-0.18479356169700623,6.274319648742676,0.3485575318336487,0.22489392757415771,-1.3319170475006104,-2.3762402534484863,1.135421872138977,0.2414776086807251,0.5695181488990784,-2.0424768924713135,-0.7978640794754028,4.013927936553955,-0.2916414737701416,-0.29385069012641907,0.6668521761894226,1.322683572769165,-0.47305309772491455,4.273985862731934,-0.8336693048477173,-1.220963954925537,0.2914729118347168,-1.5191028118133545,-0.1490272879600525,-0.5150326490402222,-0.6228861808776855,-0.9633212685585022,-0.20271557569503784,1.160370111465454,0.38626205921173096,2.2392473220825195,-0.634691596031189,-1.544378638267517,0.16408222913742065,9.673736572265625,-1.6503345966339111,-1.5389480590820312,-0.6294145584106445,-1.235147476196289,1.7419911623001099,-0.26102906465530396,-0.2503422200679779,-1.397857666015625,-0.12147831916809082,0.33746612071990967,-1.095378041267395,1.3572689294815063,3.3846006393432617,6.689955711364746,-2.0553526878356934,-1.059538722038269,-0.3827386498451233,-1.0038968324661255,0.40066301822662354,-1.106489896774292,1.8853933811187744,0.22222280502319336,-1.8440332412719727,0.5030906200408936,-1.0024287700653076,1.019736886024475,-1.593058466911316,0.0710984468460083,-0.7906051278114319,-1.7964513301849365,-1.2121728658676147,5.882443428039551,-0.6235321760177612,1.6116082668304443,-0.03010375052690506,-1.3176748752593994,-0.6083817481994629,-0.4054579436779022,0.8098424077033997,-1.4024457931518555,0.25787919759750366,1.5693683624267578,-0.9608743190765381,3.292754888534546,-2.073216676712036,0.934810996055603,-1.791935682296753,-0.5345302820205688,-1.3049101829528809,-0.06651228666305542],"values_recorded":96,"members":[{"code_sha256_prefix":"d7b93d9b79b19888","path":"models/mnist.py","papers":["2006.10102"],"paper_pages":[{"arxiv_id":"2006.10102","page":"/paper/rethinking-semi-supervised-learning-in-vaes"}],"arg_sig_recorded":[["mu",2,"float","float32"],["logvar",2,"float","float32"]],"scalar_args":{"n_samples":"3"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"float","float32"],[2,"float","float32"],[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"b2d13af9d0503a4b","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":[6.065570831298828,0.21571950614452362,1.6097086668014526,0.5011313557624817,0.40541279315948486,0.35683876276016235,0.5154263377189636,1.773383378982544,1.6801379919052124,2.609466075897217,0.6721998453140259,0.20838911831378937,0.7493605017662048,10.197154998779297,0.5976296663284302,1.7341694831848145,1.068649172782898,0.19733044505119324,1.5405067205429077,0.6661863327026367,0.9776591062545776,0.30703839659690857,0.5845761299133301,2.6742639541625977,0.4513045847415924,1.5422993898391724,2.572756052017212,2.7663209438323975,0.2935269773006439,3.57590389251709,0.2665424048900604,0.5520541667938232],"values_recorded":32,"members":[{"code_sha256_prefix":"d71a61ef4305cdc5","path":"modules/layers.py","papers":["2406.01345"],"paper_pages":[{"arxiv_id":"2406.01345","page":"/paper/bmrs-bayesian-model-reduction-for-structured"}],"arg_sig_recorded":[["mu",2,"float","float32"],["sigma",2,"float","float32"],["a",2,"float","float32"],["b",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{"eps":"1e-05"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":1,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"c3a1cab1d3de942f","size":1,"n_papers":2,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[4.222874164581299,NaN,0.8045138716697693,NaN,NaN,NaN,NaN,1.0065059661865234,0.8926381468772888,1.8984944820404053,NaN,NaN,NaN,5.8606462478637695,NaN,0.9590076804161072,0.08350377529859543,NaN,0.7161606550216675,NaN,NaN,NaN,NaN,1.9592857360839844,NaN,0.7184711694717407,1.8635903596878052,2.043910503387451,NaN,2.712571382522583,NaN,NaN],"values_recorded":32,"members":[{"code_sha256_prefix":"2a8846306c2df5bf","path":"src/dvip.py","papers":["2206.06720","2606.13818"],"paper_pages":[{"arxiv_id":"2206.06720","page":"/paper/deep-variational-implicit-processes"},{"arxiv_id":"2606.13818","page":"/paper/arxiv-2606-13818"}],"arg_sig_recorded":[["mean",2,"float","float32"],["var",2,"float","float32"],["z",2,"float","float32"]],"scalar_args":{"full_cov":"False"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"a28edada04cb0f0c","size":1,"n_papers":1,"shape":[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":[1.0857834815979004,-2.2221498489379883,0.29615485668182373,-1.2686767578125,1.2535672187805176,3.1689376831054688,-0.6414980292320251,-4.3538360595703125,0.38505005836486816,-2.3229026794433594,0.699700117111206,0.09771096706390381,-0.7306849360466003,2.773693084716797,1.5215446949005127,0.833790123462677],"values_recorded":16,"members":[{"code_sha256_prefix":"efc66d6033ca6f88","path":"models/mmali/factor2.py","papers":["aaai_20580"],"paper_pages":[{"arxiv_id":"aaai_20580","page":null}],"arg_sig_recorded":[["z",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}