{"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/knn","entry":"knn","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":17,"n_buckets":4,"n_distinct_outputs":6,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":2,"by_error":{"RecursionError":1,"ValueError":1}},"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/knn","buckets":[{"bucket":[[3,"float","float32"]],"n_implementations_compared":9,"n_papers":13,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"91458b387a78a07b","size":7,"n_papers":12,"shape":[2,8,2],"dtype":"int64","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":7,"torch_reference_conventions_with_this_digest":[],"values":[0.0,5.0,1.0,4.0,2.0,3.0,3.0,2.0,4.0,6.0,5.0,7.0,6.0,4.0,7.0,5.0,0.0,3.0,1.0,5.0,2.0,5.0,3.0,0.0,4.0,5.0,5.0,4.0,6.0,3.0,7.0,6.0],"values_recorded":32,"members":[{"code_sha256_prefix":"4e5215c55e1bf93f","path":"DeepSurrogates/DeepSurrogate_models.py","papers":["2403.08055","2406.09624","2601.22371"],"paper_pages":[{"arxiv_id":"2403.08055","page":"/paper/drivaernet-a-parametric-car-dataset-for-data"},{"arxiv_id":"2406.09624","page":"/paper/drivaernet-a-large-scale-multimodal-car"},{"arxiv_id":"2601.22371","page":"/paper/arxiv-2601-22371"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{"k":"2"},"class_bearing":false},{"code_sha256_prefix":"35d6887261f3e988","path":"taxpose/nets/transformer_flow.py","papers":["2404.13478","2309.06810"],"paper_pages":[{"arxiv_id":"2404.13478","page":"/paper/deep-se-3-equivariant-geometric-reasoning-for"},{"arxiv_id":"2309.06810","page":"/paper/leveraging-se-3-equivariance-for-learning-3d"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{"k":"2"},"class_bearing":false},{"code_sha256_prefix":"c779aa8bd2f53710","path":"Normal-Estimation/ZTEE/models/AdaFit_ms_HG.py","papers":["2303.17167","2407.02887"],"paper_pages":[{"arxiv_id":"2303.17167","page":"/paper/rethinking-the-approximation-error-in-3d"},{"arxiv_id":"2407.02887","page":"/paper/explicitly-guided-information-interaction"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{"k":"2"},"class_bearing":false},{"code_sha256_prefix":"cdd0141594039dcb","path":"model/capl.py","papers":["2309.11222","2508.15650"],"paper_pages":[{"arxiv_id":"2309.11222","page":"/paper/generalized-few-shot-point-cloud-segmentation"},{"arxiv_id":"2508.15650","page":"/paper/arxiv-2508-15650"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{"k":"2"},"class_bearing":false},{"code_sha256_prefix":"18d9a72c18f3876d","path":"attack/CW/AOF.py","papers":["2407.11011"],"paper_pages":[{"arxiv_id":"2407.11011","page":null}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{"k":"2"},"class_bearing":false},{"code_sha256_prefix":"5f563da12002f5b8","path":"networks/clnet.py","papers":["2101.00591"],"paper_pages":[{"arxiv_id":"2101.00591","page":"/paper/consensus-guided-correspondence-denoising"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{"k":"2"},"class_bearing":false},{"code_sha256_prefix":"ee7b4d081c1fd7b3","path":"models/dgcnn.py","papers":["1801.07829"],"paper_pages":[{"arxiv_id":"1801.07829","page":"/paper/dynamic-graph-cnn-for-learning-on-point"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{"k":"2","add_one_to_k":"False"},"class_bearing":false}]},{"output_sha":"970bb92b45b3804f","size":1,"n_papers":1,"shape":[2,4,2],"dtype":"int64","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,1.0,1.0,0.0,2.0,3.0,3.0,2.0,0.0,1.0,1.0,0.0,3.0,2.0,3.0,2.0],"values_recorded":16,"members":[{"code_sha256_prefix":"69f64c231bba4224","path":"models/PointDSC.py","papers":["2103.05465"],"paper_pages":[{"arxiv_id":"2103.05465","page":"/paper/pointdsc-robust-point-cloud-registration"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{"k":"2","ignore_self":"False","normalized":"True"},"class_bearing":false}]},{"output_sha":"bd6b6d736a4f819c","size":1,"n_papers":1,"shape":[2,8,3],"dtype":"int64","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,5.0,3.0,1.0,4.0,6.0,2.0,3.0,6.0,3.0,2.0,6.0,4.0,6.0,3.0,5.0,7.0,3.0,6.0,4.0,2.0,7.0,5.0,3.0,0.0,3.0,6.0,1.0,5.0,4.0,2.0,5.0,3.0,3.0,0.0,6.0,4.0,5.0,1.0,5.0,4.0,1.0,6.0,3.0,7.0,7.0,6.0,5.0],"values_recorded":48,"members":[{"code_sha256_prefix":"999b1b3194e7ace2","path":"models/dgcnn_cls.py","papers":["1801.07829"],"paper_pages":[{"arxiv_id":"1801.07829","page":"/paper/dynamic-graph-cnn-for-learning-on-point"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{"k":"3"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[1,"int","int64"],[2,"float","float32"],[1,"int","int64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"272f78036db6721f","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":[0.25],"values_recorded":1,"members":[{"code_sha256_prefix":"e016ec63c51a6da2","path":"eval_knn_torchhub.py","papers":["2402.10093"],"paper_pages":[{"arxiv_id":"2402.10093","page":"/paper/mim-refiner-a-contrastive-learning-boost-from"}],"arg_sig_recorded":[["train_x",2,"float","float32"],["train_y",1,"int","int64"],["test_x",2,"float","float32"],["test_y",1,"int","int64"]],"scalar_args":{"k":"3","tau":"0.07","batch_size":"2","eps":"1e-06"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":1,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"33cbb7f79bdb307a","size":1,"n_papers":2,"shape":[4,4],"dtype":"int64","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,2.0,1.0,3.0,1.0,3.0,0.0,2.0,2.0,0.0,3.0,1.0,3.0,1.0,0.0,2.0],"values_recorded":16,"members":[{"code_sha256_prefix":"9327cee9ffcdcc5f","path":"attack.py","papers":["1903.08333","1803.04765"],"paper_pages":[{"arxiv_id":"1903.08333","page":"/paper/on-the-robustness-of-deep-k-nearest-neighbors"},{"arxiv_id":"1803.04765","page":"/paper/deep-k-nearest-neighbors-towards-confident"}],"arg_sig_recorded":[["ori",2,"float","float32"],["adv",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[3,"float","float32"],[3,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"bd6b6d736a4f819c","size":1,"n_papers":1,"shape":[2,8,3],"dtype":"int64","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,5.0,3.0,1.0,4.0,6.0,2.0,3.0,6.0,3.0,2.0,6.0,4.0,6.0,3.0,5.0,7.0,3.0,6.0,4.0,2.0,7.0,5.0,3.0,0.0,3.0,6.0,1.0,5.0,4.0,2.0,5.0,3.0,3.0,0.0,6.0,4.0,5.0,1.0,5.0,4.0,1.0,6.0,3.0,7.0,7.0,6.0,5.0],"values_recorded":48,"members":[{"code_sha256_prefix":"edf6351fa6f2af76","path":"networks/backbone/fkaconv_network.py","papers":["2201.01831"],"paper_pages":[{"arxiv_id":"2201.01831","page":"/paper/poco-point-convolution-for-surface"}],"arg_sig_recorded":[["points",3,"float","float32"],["support_points",3,"float","float32"]],"scalar_args":{"K":"3","neighbors_indices":"None"},"class_bearing":false}]}]}]}