{"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/mean-flat","entry":"mean_flat","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":9,"n_papers":18,"n_buckets":3,"n_distinct_outputs":4,"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/mean-flat","buckets":[{"bucket":[[3,"float","float32"]],"n_implementations_compared":4,"n_papers":12,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"3823dc327eb19b5f","size":4,"n_papers":12,"shape":[2],"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":[-0.011774368584156036,0.03070831671357155],"values_recorded":2,"members":[{"code_sha256_prefix":"f6d7c009a8efb8b7","path":"diffusion/GeoTDM.py","papers":["2410.13027","2311.17042","2306.12511","2304.08577","2305.12403","2404.01717","2412.05628","2606.18209"],"paper_pages":[{"arxiv_id":"2410.13027","page":"/paper/geometric-trajectory-diffusion-models"},{"arxiv_id":"2311.17042","page":"/paper/adversarial-diffusion-distillation"},{"arxiv_id":"2306.12511","page":"/paper/semi-implicit-denoising-diffusion-models"},{"arxiv_id":"2304.08577","page":"/paper/avatars-grow-legs-generating-smooth-human"},{"arxiv_id":"2305.12403","page":"/paper/spatio-temporal-diffusion-point-processes"},{"arxiv_id":"2404.01717","page":"/paper/addsr-accelerating-diffusion-based-blind"},{"arxiv_id":"2412.05628","page":"/paper/remix-dit-mixing-diffusion-transformers-for"},{"arxiv_id":"2606.18209","page":"/paper/arxiv-2606-18209"}],"arg_sig_recorded":[["tensor",3,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"b883daa24762cb05","path":"transport/transport.py","papers":["2409.18128","2505.14502"],"paper_pages":[{"arxiv_id":"2409.18128","page":"/paper/flowturbo-towards-real-time-flow-based-image"},{"arxiv_id":"2505.14502","page":"/paper/learning-to-integrate-diffusion-odes-by"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"113e3a84f65fdd5c","path":"loss.py","papers":["2603.07276"],"paper_pages":[{"arxiv_id":"2603.07276","page":"/paper/arxiv-2603-07276"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"261b09e919a04e10","path":"src/modeling/diffusion/gaussian_diffusion.py","papers":["2402.17011"],"paper_pages":[{"arxiv_id":"2402.17011","page":"/paper/diffucomet-contextual-commonsense-knowledge"}],"arg_sig_recorded":[["tensor",3,"float","float32"]],"scalar_args":{"mask":"None"},"class_bearing":false}]}]},{"bucket":[[4,"float","float32"]],"n_implementations_compared":4,"n_papers":5,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"37b0e779863a0a02","size":3,"n_papers":4,"shape":[2],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":3,"torch_reference_conventions_with_this_digest":[],"values":[-0.014023219235241413,0.03212333843111992],"values_recorded":2,"members":[{"code_sha256_prefix":"dd96bc6c07c85dae","path":"loss.py","papers":["2410.06940","2508.10298"],"paper_pages":[{"arxiv_id":"2410.06940","page":"/paper/representation-alignment-for-generation"},{"arxiv_id":"2508.10298","page":"/paper/arxiv-2508-10298"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"7be99da802eeda95","path":"diff-QL/diffusion/diffusion.py","papers":["2310.04411"],"paper_pages":[{"arxiv_id":"2310.04411","page":"/paper/understanding-predicting-and-better-resolving-1"}],"arg_sig_recorded":[["tensor",4,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"9b73352352dc3d0e","path":"SiT-SRA_DTS_AS/loss.py","papers":["2505.02831"],"paper_pages":[{"arxiv_id":"2505.02831","page":"/paper/no-other-representation-component-is-needed"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"7d57c17ef678a8f5","size":1,"n_papers":1,"shape":[2,3],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.08927110582590103,0.013159684836864471,-0.14450044929981232,-0.42173078656196594,0.5812634825706482,-0.0631626695394516],"values_recorded":6,"members":[{"code_sha256_prefix":"158a4cd546864d47","path":"guided_diffusion/wfm.py","papers":["2608.10291"],"paper_pages":[{"arxiv_id":"2608.10291","page":"/paper/arxiv-2608-10291"}],"arg_sig_recorded":[["tensor",4,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[5,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"3b971fdb55b12450","size":1,"n_papers":1,"shape":[2],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.25509849190711975,0.11496781557798386],"values_recorded":2,"members":[{"code_sha256_prefix":"46bc9467241a8d15","path":"videosys/schedulers/scheduling_rflow_open_sora.py","papers":["2510.17858"],"paper_pages":[{"arxiv_id":"2510.17858","page":"/paper/arxiv-2510-17858"}],"arg_sig_recorded":[["tensor",5,"float","float32"]],"scalar_args":{"mask":"None"},"class_bearing":false}]}]}]}