{"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/reparametrize","entry":"reparametrize","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":8,"n_buckets":1,"n_distinct_outputs":1,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":1,"by_error":{"RuntimeError":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/reparametrize","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":6,"n_papers":8,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"6daa96efdfc72ba4","size":6,"n_papers":8,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":6,"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":"3188157d3b1c95e6","path":"models/simulation.py","papers":["2310.18615","2409.03142"],"paper_pages":[{"arxiv_id":"2310.18615","page":"/paper/temporally-disentangled-representation-2"},{"arxiv_id":"2409.03142","page":"/paper/causal-temporal-representation-learning-with"}],"arg_sig_recorded":[["mu",2,"float","float32"],["logvar",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"863fc64cd51264f0","path":"tracin.py","papers":["2105.14203","2406.19298"],"paper_pages":[{"arxiv_id":"2105.14203","page":"/paper/understanding-instance-based-interpretability"},{"arxiv_id":"2406.19298","page":"/paper/compositional-image-decomposition-with"}],"arg_sig_recorded":[["mu",2,"float","float32"],["logvar",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"0dac1f8de6997327","path":"motionAE/src/models.py","papers":["2203.09116"],"paper_pages":[{"arxiv_id":"2203.09116","page":"/paper/motionaug-augmentation-with-physical"}],"arg_sig_recorded":[["mu",2,"float","float32"],["log_var",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"2466d861eece0826","path":"control_tasks/control_tasks/probe.py","papers":["2003.12298"],"paper_pages":[{"arxiv_id":"2003.12298","page":"/paper/information-theoretic-probing-with-minimum"}],"arg_sig_recorded":[["mu",2,"float","float32"],["logvar",2,"float","float32"]],"scalar_args":{"sampling":"True"},"class_bearing":false},{"code_sha256_prefix":"6b6fa2df724bafc7","path":"BayesianLayers.py","papers":["1705.08665"],"paper_pages":[{"arxiv_id":"1705.08665","page":"/paper/bayesian-compression-for-deep-learning"}],"arg_sig_recorded":[["mu",2,"float","float32"],["logvar",2,"float","float32"]],"scalar_args":{"cuda":"False","sampling":"True"},"class_bearing":false},{"code_sha256_prefix":"926434dc272944d2","path":"air/models.py","papers":["2602.06741"],"paper_pages":[{"arxiv_id":"2602.06741","page":"/paper/arxiv-2602-06741"}],"arg_sig_recorded":[["mu",2,"float","float32"],["logvar",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}