{"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/distance-wb","entry":"distance_wb","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":5,"n_papers":7,"n_buckets":2,"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/distance-wb","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":3,"n_papers":5,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"af5570f5a1810b7a","size":2,"n_papers":4,"shape":[],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":4.76837158203125e-07,"members_with_recorded_values":2,"torch_reference_conventions_with_this_digest":[],"values":[0.0],"values_recorded":1,"members":[{"code_sha256_prefix":"6e9c65aaa7c1b5da","path":"utils.py","papers":["2202.02916","2412.09945","2605.00185"],"paper_pages":[{"arxiv_id":"2202.02916","page":"/paper/dataset-condensation-with-contrastive-signals"},{"arxiv_id":"2412.09945","page":"/paper/going-beyond-feature-similarity-effective"},{"arxiv_id":"2605.00185","page":"/paper/arxiv-2605-00185"}],"arg_sig_recorded":[["gwr",2,"float","float32"],["gws",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"40305d496ad82775","path":"training/loss.py","papers":["2211.03003"],"paper_pages":[{"arxiv_id":"2211.03003","page":"/paper/learning-to-annotate-part-segmentation-with-1"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{"metric":"'cosine'","reduction":"'sum'"},"class_bearing":false}]},{"output_sha":"0a204ddca4cbe595","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":[2.682209014892578e-06],"values_recorded":1,"members":[{"code_sha256_prefix":"33fb56403fa7b11d","path":"GCAL.py","papers":["2505.16860"],"paper_pages":[{"arxiv_id":"2505.16860","page":"/paper/gcal-adapting-graph-models-to-evolving-domain"}],"arg_sig_recorded":[["gwr",2,"float","float32"],["gws",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[4,"float","float32"],[4,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"e6ad6c9a3a3b7658","size":2,"n_papers":2,"shape":[],"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":[-5.960464477539063e-08],"values_recorded":1,"members":[{"code_sha256_prefix":"10e34c46038f259b","path":"Dataset/Gradient_matching_loss.py","papers":["2204.13399"],"paper_pages":[{"arxiv_id":"2204.13399","page":"/paper/federated-learning-on-heterogeneous-and-long"}],"arg_sig_recorded":[["gwr",4,"float","float32"],["gws",4,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"50da380b9332efe9","path":"utils.py","papers":["2312.00362"],"paper_pages":[{"arxiv_id":"2312.00362","page":"/paper/dancing-with-images-video-distillation-via"}],"arg_sig_recorded":[["gwr",4,"float","float32"],["gws",4,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}