{"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/euclidean-dist","entry":"euclidean_dist","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":14,"n_buckets":1,"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/euclidean-dist","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":12,"n_papers":14,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"7044be76a6714ad9","size":6,"n_papers":7,"shape":[4,4],"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":[9.999999974752427e-07,4.586367130279541,2.0217483043670654,4.5794477462768555,4.586367130279541,0.001357228378765285,4.630229473114014,3.7988460063934326,2.0217483043670654,4.630229473114014,0.0005261357291601598,4.22393798828125,4.5794477462768555,3.7988460063934326,4.22393798828125,9.999999974752427e-07],"values_recorded":16,"members":[{"code_sha256_prefix":"c83d9f7fca950b77","path":"ICLR25_OT.py","papers":["2301.08915","2404.13904","2502.09122"],"paper_pages":[{"arxiv_id":"2301.08915","page":"/paper/improving-deep-regression-with-ordinal"},{"arxiv_id":"2404.13904","page":"/paper/deep-regression-representation-learning-with"},{"arxiv_id":"2502.09122","page":"/paper/improving-deep-regression-with-tightness"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"e54804982d1e6d22","path":"mmt/loss/triplet.py","papers":["2001.01526","2404.13788"],"paper_pages":[{"arxiv_id":"2001.01526","page":"/paper/mutual-mean-teaching-pseudo-label-refinery-1"},{"arxiv_id":"2404.13788","page":"/paper/anypattern-towards-in-context-image-copy"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"06851d0b47833458","path":"model/loss.py","papers":["2201.09724"],"paper_pages":[{"arxiv_id":"2201.09724","page":"/paper/hot-refresh-model-upgrades-with-regression-1"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"426c97121a63bbb6","path":"loss/ordinal_ce.py","papers":["2306.13856"],"paper_pages":[{"arxiv_id":"2306.13856","page":"/paper/learning-to-rank-meets-language-boosting-1"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"cea0110f146a2f16","path":"mmt/loss/triplet.py","papers":["2001.01526"],"paper_pages":[{"arxiv_id":"2001.01526","page":"/paper/mutual-mean-teaching-pseudo-label-refinery-1"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"e0e5458257e1f903","path":"OrdinalEntropy.py","papers":["2301.08915"],"paper_pages":[{"arxiv_id":"2301.08915","page":"/paper/improving-deep-regression-with-ordinal"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"f8b683d411a9088f","size":4,"n_papers":6,"shape":[4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":4,"torch_reference_conventions_with_this_digest":[],"values":[0.0,21.034759521484375,4.087466239929199,20.971338272094727,21.034759521484375,0.0,21.439022064208984,14.431232452392578,4.087466239929199,21.439022064208984,0.0,17.84165382385254,20.971338272094727,14.431232452392578,17.84165382385254,0.0],"values_recorded":16,"members":[{"code_sha256_prefix":"4dd319c45d372246","path":"few_shot.py","papers":["1703.05175","2011.13377","2304.00022","2406.16422"],"paper_pages":[{"arxiv_id":"1703.05175","page":"/paper/prototypical-networks-for-few-shot-learning"},{"arxiv_id":"2011.13377","page":"/paper/how-well-do-self-supervised-models-transfer"},{"arxiv_id":"2304.00022","page":"/paper/what-makes-for-effective-few-shot-point-cloud"},{"arxiv_id":"2406.16422","page":"/paper/exploring-cross-domain-few-shot"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"57bbb1c2ae467a4f","path":"OOD_Distance.py","papers":["2002.05709","2107.08976"],"paper_pages":[{"arxiv_id":"2002.05709","page":"/paper/a-simple-framework-for-contrastive-learning"},{"arxiv_id":"2107.08976","page":"/paper/oodformer-out-of-distribution-detection"}],"arg_sig_recorded":[["x",2,"float","float32"],["support_mean",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"0d9f00b53a9558f8","path":"model.py","papers":["1703.05175"],"paper_pages":[{"arxiv_id":"1703.05175","page":"/paper/prototypical-networks-for-few-shot-learning"}],"arg_sig_recorded":[["t1",2,"float","float32"],["t2",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"7ad5cda37c731a0a","path":"processor/processor_protonet.py","papers":["1703.05175"],"paper_pages":[{"arxiv_id":"1703.05175","page":"/paper/prototypical-networks-for-few-shot-learning"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"7db073e7c5081a20","size":2,"n_papers":1,"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":[0.0,4.586367130279541,2.0217483043670654,4.5794477462768555,4.586367130279541,0.001357228378765285,4.630229473114014,3.7988460063934326,2.0217483043670654,4.630229473114014,0.0005261357291601598,4.22393798828125,4.5794477462768555,3.7988460063934326,4.22393798828125,0.0],"values_recorded":16,"members":[{"code_sha256_prefix":"5b618196e0cf5c21","path":"agent.py","papers":["2110.14074"],"paper_pages":[{"arxiv_id":"2110.14074","page":"/paper/fault-tolerant-federated-reinforcement"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"b8e29986f47b118e","path":"codes/agent.py","papers":["2110.14074"],"paper_pages":[{"arxiv_id":"2110.14074","page":"/paper/fault-tolerant-federated-reinforcement"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}