{"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/normal-kl","entry":"normal_kl","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":14,"n_papers":24,"n_buckets":1,"n_distinct_outputs":2,"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/normal-kl","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"],[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":14,"n_papers":24,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"bcf4c54db9a318da","size":10,"n_papers":20,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":10,"torch_reference_conventions_with_this_digest":[],"values":[0.0,0.0,0.0,2.9802322387695312e-08,2.9802322387695312e-08,-5.960464477539063e-08,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-5.960464477539063e-08,0.0,0.0,0.0,5.960464477539063e-08,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,5.960464477539063e-08,2.9802322387695312e-08],"values_recorded":32,"members":[{"code_sha256_prefix":"8afbfc42c6ea0448","path":"diffusion/diffusion_utils.py","papers":["2510.21003","2305.13311","2412.05628","2606.18209"],"paper_pages":[{"arxiv_id":"2510.21003","page":"/paper/arxiv-2510-21003"},{"arxiv_id":"2305.13311","page":"/paper/vdt-an-empirical-study-on-video-diffusion"},{"arxiv_id":"2412.05628","page":"/paper/remix-dit-mixing-diffusion-transformers-for"},{"arxiv_id":"2606.18209","page":"/paper/arxiv-2606-18209"}],"arg_sig_recorded":[["mean1",2,"float","float32"],["logvar1",2,"float","float32"],["mean2",2,"float","float32"],["logvar2",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"4707efa98ac6b989","path":"ddpm.py","papers":["2410.23905","2006.11239","2601.22816"],"paper_pages":[{"arxiv_id":"2410.23905","page":"/paper/text-difuse-an-interactive-multi-modal-image"},{"arxiv_id":"2006.11239","page":"/paper/denoising-diffusion-probabilistic-models"},{"arxiv_id":"2601.22816","page":"/paper/arxiv-2601-22816"}],"arg_sig_recorded":[["mean1",2,"float","float32"],["logvar1",2,"float","float32"],["mean2",2,"float","float32"],["logvar2",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"cf2798b666b231ca","path":"diffusion/gaussian_diffusion.py","papers":["2304.08577","2608.00716","2606.13022"],"paper_pages":[{"arxiv_id":"2304.08577","page":"/paper/avatars-grow-legs-generating-smooth-human"},{"arxiv_id":"2608.00716","page":"/paper/arxiv-2608-00716"},{"arxiv_id":"2606.13022","page":"/paper/arxiv-2606-13022"}],"arg_sig_recorded":[["mean1",2,"float","float32"],["logvar1",2,"float","float32"],["mean2",2,"float","float32"],["logvar2",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"52471728865056fc","path":"turbdiff/models/ddpm.py","papers":["2306.01776","2401.08815"],"paper_pages":[{"arxiv_id":"2306.01776","page":"/paper/generative-diffusion-for-3d-turbulent-flows"},{"arxiv_id":"2401.08815","page":"/paper/adversarial-supervision-makes-layout-to-image"}],"arg_sig_recorded":[["mean1",2,"float","float32"],["logvar1",2,"float","float32"],["mean2",2,"float","float32"],["logvar2",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"c3bf3f13d5f63d5b","path":"DSTPP/DiffusionModel.py","papers":["2305.12403","2404.00491"],"paper_pages":[{"arxiv_id":"2305.12403","page":"/paper/spatio-temporal-diffusion-point-processes"},{"arxiv_id":"2404.00491","page":"/paper/denoising-monte-carlo-renders-with-diffusion"}],"arg_sig_recorded":[["mean1",2,"float","float32"],["logvar1",2,"float","float32"],["mean2",2,"float","float32"],["logvar2",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"ec4a40e4187ccdac","path":"train_generation.py","papers":["2104.03670","2405.21066"],"paper_pages":[{"arxiv_id":"2104.03670","page":"/paper/3d-shape-generation-and-completion-through"},{"arxiv_id":"2405.21066","page":"/paper/mixed-diffusion-for-3d-indoor-scene-synthesis"}],"arg_sig_recorded":[["mean1",2,"float","float32"],["logvar1",2,"float","float32"],["mean2",2,"float","float32"],["logvar2",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"3f37a54ade181a61","path":"MoH-DiT/diffusion/diffusion_utils.py","papers":["2410.11842"],"paper_pages":[{"arxiv_id":"2410.11842","page":"/paper/moh-multi-head-attention-as-mixture-of-head"}],"arg_sig_recorded":[["mean1",2,"float","float32"],["logvar1",2,"float","float32"],["mean2",2,"float","float32"],["logvar2",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"75cca24835775136","path":"models/losses.py","papers":["2502.01441"],"paper_pages":[{"arxiv_id":"2502.01441","page":"/paper/improved-training-technique-for-latent"}],"arg_sig_recorded":[["mean1",2,"float","float32"],["logvar1",2,"float","float32"],["mean2",2,"float","float32"],["logvar2",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"97ca6069815d378e","path":"DSTPP/DiffusionModel.py","papers":["2606.01273"],"paper_pages":[{"arxiv_id":"2606.01273","page":"/paper/arxiv-2606-01273"}],"arg_sig_recorded":[["mean1",2,"float","float32"],["logvar1",2,"float","float32"],["mean2",2,"float","float32"],["logvar2",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"a9f45d5b9f695246","path":"improved_diffusion/respace.py","papers":["2010.02502"],"paper_pages":[{"arxiv_id":"2010.02502","page":"/paper/denoising-diffusion-implicit-models-1"}],"arg_sig_recorded":[["mean1",2,"float","float32"],["logvar1",2,"float","float32"],["mean2",2,"float","float32"],["logvar2",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"5341e6b2646979a7","size":4,"n_papers":5,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":4,"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":"01efe1f42dca1548","path":"src/vae_models.py","papers":["2107.11350","2602.08182"],"paper_pages":[{"arxiv_id":"2107.11350","page":"/paper/heteroscedastic-temporal-variational"},{"arxiv_id":"2602.08182","page":"/paper/arxiv-2602-08182"}],"arg_sig_recorded":[["mu1",2,"float","float32"],["lv1",2,"float","float32"],["mu2",2,"float","float32"],["lv2",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"5a9b90e8d2981ca2","path":"VKS_node.py","papers":["2102.02248"],"paper_pages":[{"arxiv_id":"2102.02248","page":"/paper/reduced-order-model-for-fluid-flows-via"}],"arg_sig_recorded":[["mu1",2,"float","float32"],["lv1",2,"float","float32"],["mu2",2,"float","float32"],["lv2",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"9537f40a55715a66","path":"ddpm_torch/diffusion.py","papers":["2006.11239"],"paper_pages":[{"arxiv_id":"2006.11239","page":"/paper/denoising-diffusion-probabilistic-models"}],"arg_sig_recorded":[["mean1",2,"float","float32"],["logvar1",2,"float","float32"],["mean2",2,"float","float32"],["logvar2",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"ef202a31135044d3","path":"examples/latent_ode.py","papers":["2312.06015"],"paper_pages":[{"arxiv_id":"2312.06015","page":"/paper/speeding-up-astrochemical-reaction-networks"}],"arg_sig_recorded":[["mu1",2,"float","float32"],["lv1",2,"float","float32"],["mu2",2,"float","float32"],["lv2",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}