{"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/kl-div","entry":"kl_div","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":6,"n_papers":6,"n_buckets":4,"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/kl-div","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":3,"n_papers":3,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"947540360b0cd8d6","size":2,"n_papers":2,"shape":[4],"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":[NaN,NaN,NaN,NaN],"values_recorded":4,"members":[{"code_sha256_prefix":"978e6ebd9602e13a","path":"src/model_nll.py","papers":["2005.01634"],"paper_pages":[{"arxiv_id":"2005.01634","page":"/paper/code-and-named-entity-recognition-in"}],"arg_sig_recorded":[["p",2,"float","float32"],["q",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"a963c3a665b84f82","path":"cifar/utils.py","papers":["2208.03207"],"paper_pages":[{"arxiv_id":"2208.03207","page":"/paper/neighborhood-collective-estimation-for-noisy"}],"arg_sig_recorded":[["p",2,"float","float32"],["q",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"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":"e14a27c300c7ad9e","path":"BernoulliDiffusion/diffusion_model.py","papers":["1503.03585"],"paper_pages":[{"arxiv_id":"1503.03585","page":"/paper/deep-unsupervised-learning-using"}],"arg_sig_recorded":[["q",2,"float","float32"],["p",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[1,"float","float64"],[1,"float","float64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"af5570f5a1810b7a","size":1,"n_papers":1,"shape":[],"dtype":"float64","type":"float64","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0],"values_recorded":1,"members":[{"code_sha256_prefix":"545fcc23b912f1c1","path":"Drive/sarsa.py","papers":["1712.04172"],"paper_pages":[{"arxiv_id":"1712.04172","page":"/paper/a-low-cost-ethics-shaping-approach-for"}],"arg_sig_recorded":[["p1",1,"float","float64"],["p2",1,"float","float64"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"float","float32"],[1,"int","int64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"5341e6b2646979a7","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"b12eccceaa04cfd8","path":"editor/horse.py","papers":["2601.11441"],"paper_pages":[{"arxiv_id":"2601.11441","page":"/paper/arxiv-2601-11441"}],"arg_sig_recorded":[["refer_logits",2,"float","float32"],["logits",2,"float","float32"],["labels",1,"int","int64"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"float","float32"],[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"145436cecd5bcfb3","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":[14.0],"values_recorded":1,"members":[{"code_sha256_prefix":"8ff7ce810790dda0","path":"cbn.py","papers":["2305.10309"],"paper_pages":[{"arxiv_id":"2305.10309","page":"/paper/metamodulation-learning-variational-feature"}],"arg_sig_recorded":[["m",2,"float","float32"],["log_v",2,"float","float32"],["m0",2,"float","float32"],["log_v0",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}