{"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/stable-cumsum","entry":"stable_cumsum","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":7,"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/stable-cumsum","buckets":[{"bucket":[[1,"float","float64"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"b9f4a7863363ac87","size":2,"n_papers":2,"shape":[8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":2,"torch_reference_conventions_with_this_digest":[],"values":[-0.9038889997942827,-0.746757542642969,0.1508544440222126,-0.6113410974240321,-0.7875966607005126,-0.7345649398102502,-2.3630052214259814,-2.5405385528185565],"values_recorded":8,"members":[{"code_sha256_prefix":"a7036bae17c58812","path":"srcs/ConV.py","papers":["2511.01293"],"paper_pages":[{"arxiv_id":"2511.01293","page":"/paper/arxiv-2511-01293"}],"arg_sig_recorded":[["arr",1,"float","float64"]],"scalar_args":{"rtol":"1e-05","atol":"1e-08"},"class_bearing":false},{"code_sha256_prefix":"e6809651fe876f1d","path":"evaluation.py","papers":["2104.08812"],"paper_pages":[{"arxiv_id":"2104.08812","page":"/paper/contrastive-out-of-distribution-detection-for"}],"arg_sig_recorded":[["arr",1,"float","float64"]],"scalar_args":{"rtol":"1e-05","atol":"1e-08"},"class_bearing":false}]}]},{"bucket":[[1,"float","float32"]],"n_implementations_compared":1,"n_papers":4,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"b9f4a7863363ac87","size":1,"n_papers":4,"shape":[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":[-0.903889000415802,-0.7467575371265411,0.1508544385433197,-0.6113410890102386,-0.7875966578722,-0.7345649376511574,-2.3630051985383034,-2.540538527071476],"values_recorded":8,"members":[{"code_sha256_prefix":"d4acb3120a027622","path":"utils_ood.py","papers":["2402.02949","2505.15284","2409.14750","2507.09795"],"paper_pages":[{"arxiv_id":"2402.02949","page":"/paper/kernel-pca-for-out-of-distribution-detection"},{"arxiv_id":"2505.15284","page":"/paper/kernel-pca-for-out-of-distribution-detection-1"},{"arxiv_id":"2409.14750","page":"/paper/finecops-ref-a-new-dataset-and-task-for-fine"},{"arxiv_id":"2507.09795","page":null}],"arg_sig_recorded":[["arr",1,"float","float32"]],"scalar_args":{"rtol":"1e-05","atol":"1e-08"},"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":"ec877c6400549d5f","size":1,"n_papers":1,"shape":[32],"dtype":"float64","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.8026286363601685,0.2688523530960083,0.7449055910110474,0.05401855707168579,-0.8488309383392334,-1.8793021440505981,-2.542063057422638,-1.9691738486289978,-1.4502978920936584,-0.49115222692489624,-0.8883517980575562,-2.4566999673843384,-2.7452350556850433,-0.42312631011009216,-0.9379102885723114,-0.3873817026615143,-0.3209862634539604,-1.943861834704876,-1.5117504224181175,-1.9179362878203392,-1.9405305124819279,-3.121312949806452,-3.6581812240183353,-2.6745070554316044,-3.4701198674738407,-3.036845449358225,-2.0918676890432835,-1.074349407106638,-2.300135139375925,-1.025917176157236,-2.348139051347971,-2.9422481693327427],"values_recorded":32,"members":[{"code_sha256_prefix":"500990b89c506e5c","path":"cdc/methods/calibrate_train.py","papers":["2403.02998"],"paper_pages":[{"arxiv_id":"2403.02998","page":"/paper/towards-calibrated-deep-clustering-network"}],"arg_sig_recorded":[["arr",2,"float","float32"]],"scalar_args":{"dim":"None","rtol":"1e-05","atol":"1e-08"},"class_bearing":false}]}]}]}