{"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/top-k","entry":"top_k","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":7,"n_papers":9,"n_buckets":1,"n_distinct_outputs":5,"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/top-k","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":7,"n_papers":9,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"0ce351e0126582e7","size":2,"n_papers":3,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":2,"torch_reference_conventions_with_this_digest":[],"values":[1.8026286363601685,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,2.322108745574951,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,0.983674168586731,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,1.274217963218689,-Infinity,-Infinity],"values_recorded":32,"members":[{"code_sha256_prefix":"39f3cec3c6be459f","path":"block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","papers":["2203.07852","2407.09099"],"paper_pages":[{"arxiv_id":"2203.07852","page":"/paper/block-recurrent-transformers"},{"arxiv_id":"2407.09099","page":"/paper/music-proofreading-with-refinpaint-where-and"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"thres":"0.9"},"class_bearing":false},{"code_sha256_prefix":"3c61d89a5e42a3d3","path":"speculative_decoding/speculative_decoding.py","papers":["2211.17192"],"paper_pages":[{"arxiv_id":"2211.17192","page":"/paper/fast-inference-from-transformers-via"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"thres":"0.9"},"class_bearing":false}]},{"output_sha":"2a1eb671fb1d4cde","size":2,"n_papers":3,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":2,"torch_reference_conventions_with_this_digest":[],"values":[-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity],"values_recorded":32,"members":[{"code_sha256_prefix":"3b65d5d77510c964","path":"marge_pytorch/marge_pytorch.py","papers":["2006.15020","2406.18051"],"paper_pages":[{"arxiv_id":"2006.15020","page":"/paper/pre-training-via-paraphrasing"},{"arxiv_id":"2406.18051","page":"/paper/vit-1-58b-mobile-vision-transformers-in-the-1"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"thres":"0.9"},"class_bearing":false},{"code_sha256_prefix":"5d77a7df8b8103e4","path":"autoregressive_wrapper.py","papers":["2406.07368"],"paper_pages":[{"arxiv_id":"2406.07368","page":"/paper/when-linear-attention-meets-autoregressive"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"thres":"0.9"},"class_bearing":false}]},{"output_sha":"8c8e8216c02adb67","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.8026286363601685,-Infinity,0.47605323791503906,-Infinity,-Infinity,-Infinity,-0.6627609133720398,0.5728892087936401,0.5188759565353394,0.9591456651687622,-Infinity,-Infinity,-Infinity,2.322108745574951,-Infinity,0.5505285859107971,0.06639543920755386,-Infinity,0.4321114122867584,-Infinity,-0.02259422466158867,-Infinity,-Infinity,0.983674168586731,-Infinity,0.43327441811561584,0.9449777603149414,1.0175182819366455,-Infinity,1.274217963218689,-Infinity,-Infinity],"values_recorded":32,"members":[{"code_sha256_prefix":"fc2efb619b6ee2c4","path":"vqvae.py","papers":["2210.16484"],"paper_pages":[{"arxiv_id":"2210.16484","page":"/paper/a-systematic-survey-of-molecular-pre-trained"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"thres":"0.5"},"class_bearing":false}]},{"output_sha":"b6b3eb1fb73903e1","size":1,"n_papers":1,"shape":[4,3],"dtype":"int64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[2.0,7.0,0.0,7.0,1.0,5.0,0.0,2.0,7.0,2.0,3.0,5.0],"values_recorded":12,"members":[{"code_sha256_prefix":"4c46154099e4d408","path":"evaluate_model.py","papers":["1804.09170"],"paper_pages":[{"arxiv_id":"1804.09170","page":"/paper/realistic-evaluation-of-deep-semi-supervised"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"k":"3"},"class_bearing":false}]},{"output_sha":"e84b62b578f630b9","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.8026286363601685,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,0.5728892087936401,-Infinity,0.9591456651687622,-Infinity,-Infinity,-Infinity,2.322108745574951,-Infinity,-Infinity,-Infinity,-Infinity,0.4321114122867584,-Infinity,-Infinity,-Infinity,-Infinity,0.983674168586731,-Infinity,-Infinity,-Infinity,1.0175182819366455,-Infinity,1.274217963218689,-Infinity,-Infinity],"values_recorded":32,"members":[{"code_sha256_prefix":"72827010274936db","path":"utils/generate.py","papers":["2212.11134"],"paper_pages":[{"arxiv_id":"2212.11134","page":"/paper/generating-music-with-sentiment-using"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"k":"2"},"class_bearing":false}]}]}]}