{"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/square-distance","entry":"square_distance","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":11,"n_papers":18,"n_buckets":2,"n_distinct_outputs":4,"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/square-distance","buckets":[{"bucket":[[3,"float","float32"],[3,"float","float32"]],"n_implementations_compared":10,"n_papers":17,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"4bbeb81094d52295","size":7,"n_papers":12,"shape":[2,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":7,"torch_reference_conventions_with_this_digest":[],"values":[9.5367431640625e-07,7.711119174957275,24.886981964111328,18.05414581298828,7.711119174957275,0.0,23.961910247802734,19.289653778076172,24.886981964111328,23.961912155151367,0.0,6.51542854309082,18.05414581298828,19.289653778076172,6.51542854309082,1.9073486328125e-06,0.0,9.166748046875,16.30995750427246,18.336931228637695,9.166748046875,0.0,9.585933685302734,19.941020965576172,16.30995750427246,9.585933685302734,0.0,6.6850433349609375,18.336931228637695,19.941020965576172,6.6850433349609375,0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"3bfe172e686075cd","path":"models/GAPrompt.py","papers":["2202.07123","2505.04119","2509.09785"],"paper_pages":[{"arxiv_id":"2202.07123","page":"/paper/rethinking-network-design-and-local-geometry-1"},{"arxiv_id":"2505.04119","page":"/paper/gaprompt-geometry-aware-point-cloud-prompt"},{"arxiv_id":"2509.09785","page":"/paper/arxiv-2509-09785"}],"arg_sig_recorded":[["src",3,"float","float32"],["dst",3,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"4db73dd57b5d6162","path":"models/Net_noais.py","papers":["2310.17359","2103.04256"],"paper_pages":[{"arxiv_id":"2310.17359","page":"/paper/se-3-diffusion-model-based-point-cloud"},{"arxiv_id":"2103.04256","page":"/paper/robust-point-cloud-registration-framework"}],"arg_sig_recorded":[["src",3,"float","float32"],["dst",3,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"580dee6761649b29","path":"merger/merger_net.py","papers":["2103.10814","2609.13991"],"paper_pages":[{"arxiv_id":"2103.10814","page":"/paper/skeleton-merger-an-unsupervised-aligned"},{"arxiv_id":"2609.13991","page":"/paper/arxiv-2609-13991"}],"arg_sig_recorded":[["src",3,"float","float32"],["dst",3,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"bba5dc7caf857cd2","path":"models/risurconv_utils.py","papers":["2408.06110","2409.00353"],"paper_pages":[{"arxiv_id":"2408.06110","page":"/paper/risurconv-rotation-invariant-surface"},{"arxiv_id":"2409.00353","page":"/paper/ri-mae-rotation-invariant-masked-autoencoders"}],"arg_sig_recorded":[["src",3,"float","float32"],["dst",3,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"3f5fbb460e98663b","path":"r3pm_net/model.py","papers":["2604.05060"],"paper_pages":[{"arxiv_id":"2604.05060","page":"/paper/arxiv-2604-05060"}],"arg_sig_recorded":[["src",3,"float","float32"],["dst",3,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"4b492b12ea1918b8","path":"model/IAGNet.py","papers":["2303.10437"],"paper_pages":[{"arxiv_id":"2303.10437","page":"/paper/grounding-3d-object-affordance-from-2d"}],"arg_sig_recorded":[["src",3,"float","float32"],["dst",3,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"cb46d51170c75900","path":"models/point_transformer.py","papers":["2206.04670"],"paper_pages":[{"arxiv_id":"2206.04670","page":"/paper/pointnext-revisiting-pointnet-with-improved"}],"arg_sig_recorded":[["src",3,"float","float32"],["dst",3,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"4c5885bd7debace9","size":2,"n_papers":4,"shape":[2,4,4],"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":[0.0,7.711117744445801,24.886980056762695,18.054141998291016,7.711117744445801,0.0,23.9619140625,19.289655685424805,24.886980056762695,23.9619140625,0.0,6.51542854309082,18.054141998291016,19.289655685424805,6.51542854309082,0.0,0.0,9.166749000549316,16.30995750427246,18.336933135986328,9.166749000549316,0.0,9.585933685302734,19.941022872924805,16.30995750427246,9.585933685302734,0.0,6.685044765472412,18.336933135986328,19.941022872924805,6.685044765472412,0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"74c3fe06cea2f553","path":"models/MOS/model.py","papers":["2402.14380","2509.01250"],"paper_pages":[{"arxiv_id":"2402.14380","page":"/paper/radarmoseve-a-spatial-temporal-transformer"},{"arxiv_id":"2509.01250","page":"/paper/arxiv-2509-01250"}],"arg_sig_recorded":[["src",3,"float","float32"],["dst",3,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"b1776b6ece5471d2","path":"models/AIRnet.py","papers":["2307.09112","2110.11860"],"paper_pages":[{"arxiv_id":"2307.09112","page":"/paper/nu-mcc-multiview-compressive-coding-with-1"},{"arxiv_id":"2110.11860","page":"/paper/air-nets-an-attention-based-framework-for"}],"arg_sig_recorded":[["src",3,"float","float32"],["dst",3,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"0effecf918aab63d","size":1,"n_papers":1,"shape":[2,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,7.711118221282959,24.886980056762695,18.05414390563965,7.711118221282959,0.0,23.961912155151367,19.289657592773438,24.886980056762695,23.961912155151367,0.0,6.5154290199279785,18.05414390563965,19.289657592773438,6.5154290199279785,0.0,0.0,9.166749000549316,16.309959411621094,18.336933135986328,9.166749000549316,0.0,9.585933685302734,19.941020965576172,16.309959411621094,9.585933685302734,0.0,6.685044288635254,18.336933135986328,19.941020965576172,6.685044288635254,0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"24896468cac00905","path":"mars/models/mffp.py","papers":["2407.01191"],"paper_pages":[{"arxiv_id":"2407.01191","page":"/paper/mars-multimodal-active-robotic-sensing-for"}],"arg_sig_recorded":[["src",3,"float","float32"],["dst",3,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"66687aadf862bd77","size":1,"n_papers":1,"shape":[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":[0.0,0.0,0.0,0.0],"values_recorded":4,"members":[{"code_sha256_prefix":"74d612788fd916bc","path":"edit_distance/models/pair_encoder.py","papers":["2109.09740"],"paper_pages":[{"arxiv_id":"2109.09740","page":"/paper/neural-distance-embeddings-for-biological"}],"arg_sig_recorded":[["t1_emb",2,"float","float32"],["t2_emb",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}