{"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/pairwise-distances","entry":"pairwise_distances","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":14,"n_papers":13,"n_buckets":2,"n_distinct_outputs":7,"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/pairwise-distances","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":10,"n_papers":8,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"bd5ec630d2df19d7","size":3,"n_papers":3,"shape":[4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":3,"torch_reference_conventions_with_this_digest":[],"values":[0.0,21.037433624267578,4.086263656616211,20.9755916595459,21.037433624267578,0.0,21.454721450805664,14.414592742919922,4.086263656616211,21.454721450805664,0.0,17.845966339111328,20.9755916595459,14.414592742919922,17.845966339111328,0.012969970703125],"values_recorded":16,"members":[{"code_sha256_prefix":"13c5bcb77cfacbd2","path":"run_joint_finetune.py","papers":["2005.00559"],"paper_pages":[{"arxiv_id":"2005.00559","page":"/paper/rignet-neural-rigging-for-articulated"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"449fa3a7ae8a84ad","path":"toy_gnn.py","papers":["2108.01099"],"paper_pages":[{"arxiv_id":"2108.01099","page":"/paper/shift-robust-gnns-overcoming-the-limitations"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"70fa9d2ca12c8bc3","path":"model/PMF.py","papers":["2407.16168"],"paper_pages":[{"arxiv_id":"2407.16168","page":"/paper/progressively-modality-freezing-for-multi"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"f8b683d411a9088f","size":3,"n_papers":2,"shape":[4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":3,"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":"264452c073b536a8","path":"few_shot/proto.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":{"matching_fn":"'l2'"},"class_bearing":false},{"code_sha256_prefix":"276c42468f5e8af0","path":"Utils/protonet_calculations.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},{"code_sha256_prefix":"a34f75316e245682","path":"qinco/model/qinco_base.py","papers":["2401.14732"],"paper_pages":[{"arxiv_id":"2401.14732","page":"/paper/residual-quantization-with-implicit-neural"}],"arg_sig_recorded":[["a",2,"float","float32"],["b",2,"float","float32"]],"scalar_args":{"approx":"'auto'"},"class_bearing":false}]},{"output_sha":"59d3d79b83ca53cc","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":[-0.009662628173828125,21.037433624267578,4.086263656616211,20.9755916595459,21.037433624267578,-0.07829093933105469,21.454721450805664,14.414592742919922,4.086263656616211,21.454721450805664,-0.007010459899902344,17.845966339111328,20.9755916595459,14.414592742919922,17.845966339111328,0.012969970703125],"values_recorded":16,"members":[{"code_sha256_prefix":"4e2d3ab42299ec07","path":"GP.py","papers":["2009.13075"],"paper_pages":[{"arxiv_id":"2009.13075","page":"/paper/semi-supervised-image-deraining-using"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"53bf28d5c23929a5","path":"model_rqmoe.py","papers":["2605.14359"],"paper_pages":[{"arxiv_id":"2605.14359","page":"/paper/arxiv-2605-14359"}],"arg_sig_recorded":[["a",2,"float","float32"],["b",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"cfb0c26ed4e3cf52","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":[0.0022220611572265625,1.1175861358642578,0.26172780990600586,1.2374095916748047,1.1175861358642578,0.0025091171264648438,1.398309588432312,0.80889892578125,0.26172780990600586,1.398309588432312,-0.0007596015930175781,1.3151922225952148,1.2374095916748047,0.80889892578125,1.3151922225952148,0.0013256072998046875],"values_recorded":16,"members":[{"code_sha256_prefix":"732d646a00f52bf8","path":"keyword_detr/keyword_attention.py","papers":["2501.02504"],"paper_pages":[{"arxiv_id":"2501.02504","page":"/paper/watch-video-catch-keyword-context-aware"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{"metric":"'cosine'"},"class_bearing":false}]},{"output_sha":"db2fd13e171d99ff","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":[0.0,42.06951904296875,8.174932479858398,41.94267654418945,42.06951904296875,0.0,42.87804412841797,28.862464904785156,8.174932479858398,42.87804412841797,0.0,35.68330764770508,41.94267654418945,28.862464904785156,35.68330764770508,0.0],"values_recorded":16,"members":[{"code_sha256_prefix":"9c31448b2eee894f","path":"few_shot/proto.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":{"matching_fn":"'l2'","model":"MinimalModel()"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"]],"n_implementations_compared":4,"n_papers":5,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"9851ab143a7be739","size":3,"n_papers":4,"shape":[4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":3,"torch_reference_conventions_with_this_digest":[],"values":[-0.009662628173828125,21.037433624267578,4.086263656616211,20.9755916595459,21.037433624267578,-0.07829093933105469,21.454721450805664,14.414593696594238,4.086263656616211,21.454721450805664,-0.007010459899902344,17.845966339111328,20.9755916595459,14.414593696594238,17.845966339111328,0.012969970703125],"values_recorded":16,"members":[{"code_sha256_prefix":"21bf8deeec959d90","path":"domainbed/hsic.py","papers":["2308.11158","2403.08649"],"paper_pages":[{"arxiv_id":"2308.11158","page":"/paper/domain-generalization-via-rationale"},{"arxiv_id":"2403.08649","page":"/paper/a-causal-inspired-early-branching-structure"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"92723afcb622bb4d","path":"src/RQR-O/losses.py","papers":["2406.03258"],"paper_pages":[{"arxiv_id":"2406.03258","page":"/paper/relaxed-quantile-regression-prediction"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"e39cf7830c5e50d5","path":"conformal.py","papers":["2202.11091"],"paper_pages":[{"arxiv_id":"2202.11091","page":"/paper/efficient-and-differentiable-conformal-1"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"aaf4a4aa87dd8598","size":1,"n_papers":1,"shape":[4,4],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[Infinity,4.591449737548828,2.0235118865966797,4.579730987548828,4.591449737548828,Infinity,4.636525630950928,3.8009543418884277,2.0235118865966797,4.636525630950928,Infinity,4.224095821380615,4.579730987548828,3.8009543418884277,4.224095821380615,Infinity],"values_recorded":16,"members":[{"code_sha256_prefix":"881d32a340b4337a","path":"hcsmoe/merging/clustering.py","papers":["2410.08589"],"paper_pages":[{"arxiv_id":"2410.08589","page":"/paper/retraining-free-merging-of-sparse-mixture-of"}],"arg_sig_recorded":[["X",2,"float","float32"]],"scalar_args":{"method":"'single'"},"class_bearing":false}]}]}]}