{"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-divergence","entry":"kl_divergence","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":18,"n_papers":18,"n_buckets":7,"n_distinct_outputs":15,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":2,"by_error":{"RuntimeError":2}},"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-divergence","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":7,"n_papers":7,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"74999fd28ab18ccc","size":2,"n_papers":2,"shape":[],"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],"values_recorded":1,"members":[{"code_sha256_prefix":"310c696192de629c","path":"discor/algorithm/rlkit/torch/iwq/iwq.py","papers":["2006.13169"],"paper_pages":[{"arxiv_id":"2006.13169","page":"/paper/experience-replay-with-likelihood-free"}],"arg_sig_recorded":[["mu",2,"float","float32"],["std",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"79ad7949ae4becd4","path":"models/cool.py","papers":["2302.01242"],"paper_pages":[{"arxiv_id":"2302.01242","page":"/paper/neuro-symbolic-continual-learning-knowledge"}],"arg_sig_recorded":[["input",2,"float","float32"],["target",2,"float","float32"]],"scalar_args":{"dim":"2","version":"'nesy'"},"class_bearing":false}]},{"output_sha":"31ac516f930a0d57","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":[365.2886962890625],"values_recorded":1,"members":[{"code_sha256_prefix":"b7ecf10c7192ae78","path":"models.py","papers":["1807.10300"],"paper_pages":[{"arxiv_id":"1807.10300","page":"/paper/discovering-physical-concepts-with-neural"}],"arg_sig_recorded":[["means",2,"float","float32"],["log_sigma",2,"float","float32"]],"scalar_args":{"dim":"4","target_sigma":"0.1"},"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":"fc8000b231339fd0","path":"src/scripts/train_SIDDA.py","papers":["2501.14048"],"paper_pages":[{"arxiv_id":"2501.14048","page":"/paper/sidda-sinkhorn-dynamic-domain-adaptation-for"}],"arg_sig_recorded":[["p",2,"float","float32"],["q",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"947540360b0cd8d6","size":1,"n_papers":1,"shape":[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":[NaN,NaN,NaN,NaN],"values_recorded":4,"members":[{"code_sha256_prefix":"ee53047b4a3470aa","path":"src/mira_sim/metrics/kldiv/kld_metric.py","papers":["2407.14364"],"paper_pages":[{"arxiv_id":"2407.14364","page":"/paper/towards-assessing-data-replication-in-music"}],"arg_sig_recorded":[["pred_probs",2,"float","float32"],["target_probs",2,"float","float32"]],"scalar_args":{"epsilon":"1e-06"},"class_bearing":false}]},{"output_sha":"af5570f5a1810b7a","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":[0.0],"values_recorded":1,"members":[{"code_sha256_prefix":"2c199cf061f618c1","path":"lib/SHIPS/get_ships.py","papers":["2410.13708"],"paper_pages":[{"arxiv_id":"2410.13708","page":"/paper/on-the-role-of-attention-heads-in-large"}],"arg_sig_recorded":[["base_pd",2,"float","float32"],["mask_pd",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"cf3999a9f5564b9c","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":[6.661041259765625],"values_recorded":1,"members":[{"code_sha256_prefix":"7f0ddf1b30b1a8ac","path":"XOR_MNIST/models/mnistpcbmdpl.py","papers":["2306.01574"],"paper_pages":[{"arxiv_id":"2306.01574","page":"/paper/probabilistic-concept-bottleneck-models"}],"arg_sig_recorded":[["mu",2,"float","float32"],["logsigma",2,"float","float32"]],"scalar_args":{"reduction":"'mean'"},"class_bearing":false}]}]},{"bucket":[[1,"float","float64"],[1,"float","float64"]],"n_implementations_compared":5,"n_papers":5,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"9402bb655bc3b733","size":3,"n_papers":3,"shape":[],"dtype":"float64","type":"float64","finite":false,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":3,"torch_reference_conventions_with_this_digest":[],"values":[Infinity],"values_recorded":1,"members":[{"code_sha256_prefix":"5b9b7639a0244fd3","path":"mmd_dilated/mmd_dilated.py","papers":["2206.05825"],"paper_pages":[{"arxiv_id":"2206.05825","page":"/paper/a-unified-approach-to-reinforcement-learning"}],"arg_sig_recorded":[["probs1",1,"float","float64"],["probs2",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"8c91bd640a67c01c","path":"stratifiers/StratifierKullbackLeibler.py","papers":["2607.10825"],"paper_pages":[{"arxiv_id":"2607.10825","page":"/paper/arxiv-2607-10825"}],"arg_sig_recorded":[["a",1,"float","float64"],["b",1,"float","float64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"fcef7b2cb358d326","path":"tool/managed_system_cv/mape_logic/monitor.py","papers":["2601.11926"],"paper_pages":[{"arxiv_id":"2601.11926","page":"/paper/arxiv-2601-11926"}],"arg_sig_recorded":[["p",1,"float","float64"],["q",1,"float","float64"]],"scalar_args":{},"class_bearing":false}]},{"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":"08d9e207afab098a","path":"03_1_DR_Diff_matrix_generator.py","papers":["2004.07229"],"paper_pages":[{"arxiv_id":"2004.07229","page":"/paper/network-medicine-framework-for-identifying"}],"arg_sig_recorded":[["p",1,"float","float64"],["q",1,"float","float64"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"f5a5fd42d16a2030","size":1,"n_papers":1,"shape":[8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.000000082690371e-10,1.000000082690371e-10,1.000000082690371e-10,1.0000000826903712e-10,1.000000082690371e-10,1.000000082690371e-10,1.000000082690371e-10,1.000000082690371e-10],"values_recorded":8,"members":[{"code_sha256_prefix":"d326593f87383098","path":"model/method.py","papers":["2305.19158"],"paper_pages":[{"arxiv_id":"2305.19158","page":"/paper/competing-for-shareable-arms-in-multi-player"}],"arg_sig_recorded":[["a",1,"float","float64"],["b",1,"float","float64"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"float","float32"],[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"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":"9af8fadcf673cf17","path":"VDPO.py","papers":["2405.14226"],"paper_pages":[{"arxiv_id":"2405.14226","page":"/paper/variational-delayed-policy-optimization"}],"arg_sig_recorded":[["mu1",2,"float","float32"],["sigma1",2,"float","float32"],["mu2",2,"float","float32"],["sigma2",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":"cb955692fef4dc97","path":"ebmdg_main.py","papers":["2302.11215"],"paper_pages":[{"arxiv_id":"2302.11215","page":"/paper/energy-based-test-sample-adaptation-for"}],"arg_sig_recorded":[["mu_q",2,"float","float32"],["sigma_q",2,"float","float32"],["mu_p",2,"float","float32"],["sigma_p",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[1,"float","float32"],[1,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"ed5f4528b943ebe1","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":[0.43175384402275085],"values_recorded":1,"members":[{"code_sha256_prefix":"04d7f678f5b3f532","path":"openrlhf/models/model_inform.py","papers":["2402.09345"],"paper_pages":[{"arxiv_id":"2402.09345","page":"/paper/mitigating-reward-hacking-via-information"}],"arg_sig_recorded":[["mu",1,"float","float32"],["logvar",1,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[1,"float","float32"],[1,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"74999fd28ab18ccc","size":1,"n_papers":1,"shape":[],"dtype":"float64","type":"float","finite":false,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[NaN],"values_recorded":1,"members":[{"code_sha256_prefix":"652cccb37631b811","path":"generation/group_sampling.py","papers":["2505.18399"],"paper_pages":[{"arxiv_id":"2505.18399","page":"/paper/taming-diffusion-for-dataset-distillation"}],"arg_sig_recorded":[["selected_points",2,"float","float32"],["mean",1,"float","float32"],["std",1,"float","float32"]],"scalar_args":{"device":"device(type='cpu')"},"class_bearing":false}]}]},{"bucket":[[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":"af5570f5a1810b7a","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":[0.0],"values_recorded":1,"members":[{"code_sha256_prefix":"6a0687b01242a053","path":"src/models/custom_loss.py","papers":["1704.03976"],"paper_pages":[{"arxiv_id":"1704.03976","page":"/paper/virtual-adversarial-training-a-regularization"}],"arg_sig_recorded":[["reference",2,"float","float32"],["pred",2,"float","float32"],["mask",2,"float","float32"]],"scalar_args":{"is_gt":"False"},"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":"af5570f5a1810b7a","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":[0.0],"values_recorded":1,"members":[{"code_sha256_prefix":"84501014a71e038e","path":"src/sami/trainers/sami_trainer.py","papers":["2404.14313"],"paper_pages":[{"arxiv_id":"2404.14313","page":"/paper/self-supervised-alignment-with-mutual"}],"arg_sig_recorded":[["policy_logits",3,"float","float32"],["ref_logits",3,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}