{"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/rbf","entry":"rbf","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":4,"n_papers":6,"n_buckets":3,"n_distinct_outputs":3,"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/rbf","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"6ed437a3ad9e051b","size":2,"n_papers":2,"shape":[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":[1.0,0.5539129376411438,0.8915981650352478,0.5555835962295532,0.5539129376411438,1.0,0.5474939346313477,0.667080819606781,0.8915981650352478,0.5474939346313477,1.0,0.6065306663513184,0.5555835962295532,0.667080819606781,0.6065306663513184,1.0],"values_recorded":16,"members":[{"code_sha256_prefix":"48b102488b75c27f","path":"trainers/gnndelete.py","papers":["2412.00789"],"paper_pages":[{"arxiv_id":"2412.00789","page":"/paper/a-cognac-shot-to-forget-bad-memories"}],"arg_sig_recorded":[["X",2,"float","float32"]],"scalar_args":{"sigma":"None"},"class_bearing":false},{"code_sha256_prefix":"ad1380889172ec1f","path":"models/pa.py","papers":["2103.13841"],"paper_pages":[{"arxiv_id":"2103.13841","page":"/paper/universal-representation-learning-from"}],"arg_sig_recorded":[["X",2,"float","float32"]],"scalar_args":{"sigma":"None"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"float","float32"],[0,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"26e83ea82d468c16","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":[1.0,0.005583538673818111,0.3649054765701294,0.005671564023941755,0.005583538673818111,1.0,0.005053682252764702,0.028459765017032623,0.3649054765701294,0.005053682252764702,1.0,0.01227246318012476,0.005671564023941755,0.028459765017032623,0.01227246318012476,1.0],"values_recorded":16,"members":[{"code_sha256_prefix":"78edf125fd3fb59d","path":"lsd_ica.py","papers":["2002.05616"],"paper_pages":[{"arxiv_id":"2002.05616","page":"/paper/cutting-out-the-middle-man-training-and"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"],["h",0,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float64"]],"n_implementations_compared":1,"n_papers":3,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"3b484defedfa7b7f","size":1,"n_papers":3,"shape":[4,4],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.0,0.5816120952655216,0.9000438424698266,0.582563250737199,0.5816120952655216,1.0,0.5755856650388956,0.6894821527688427,0.9000438424698266,0.5755856650388956,1.0,0.6314841190307025,0.582563250737199,0.6894821527688427,0.6314841190307025,1.0],"values_recorded":16,"members":[{"code_sha256_prefix":"0f137cab706f1953","path":"breast_cancer_histopathology/CKA.py","papers":["2110.14805","1905.00414","2406.09135"],"paper_pages":[{"arxiv_id":"2110.14805","page":"/paper/intermediate-layers-matter-in-momentum"},{"arxiv_id":"1905.00414","page":"/paper/similarity-of-neural-network-representations"},{"arxiv_id":"2406.09135","page":"/paper/adarevd-adaptive-patch-exiting-reversible-1"}],"arg_sig_recorded":[["X",2,"float","float64"]],"scalar_args":{"sigma":"None"},"class_bearing":false}]}]}]}