{"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/masked-mean","entry":"masked_mean","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":8,"n_papers":11,"n_buckets":2,"n_distinct_outputs":5,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":4,"by_error":{"RuntimeError":4}},"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/masked-mean","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":5,"n_papers":7,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"c42d56d87512c703","size":3,"n_papers":4,"shape":[],"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":[-11.017924308776855],"values_recorded":1,"members":[{"code_sha256_prefix":"514a8131ed22efc6","path":"src/verl/trainer/ppo/core_algos.py","papers":["2503.19470","2601.03715"],"paper_pages":[{"arxiv_id":"2503.19470","page":"/paper/research-learning-to-reason-with-search-for"},{"arxiv_id":"2601.03715","page":"/paper/arxiv-2601-03715"}],"arg_sig_recorded":[["values",2,"float","float32"],["mask",2,"float","float32"]],"scalar_args":{"axis":"None"},"class_bearing":false},{"code_sha256_prefix":"1ab358e6ebe32a98","path":"verl/verl/trainer/ppo/core_algos.py","papers":["2510.04474"],"paper_pages":[{"arxiv_id":"2510.04474","page":"/paper/arxiv-2510-04474"}],"arg_sig_recorded":[["values",2,"float","float32"],["mask",2,"float","float32"]],"scalar_args":{"axis":"None"},"class_bearing":false},{"code_sha256_prefix":"d0bcd263d8c97d38","path":"verl/trainer/ppo/sdar_utils.py","papers":["2605.15155"],"paper_pages":[{"arxiv_id":"2605.15155","page":"/paper/arxiv-2605-15155"}],"arg_sig_recorded":[["values",2,"float","float32"],["mask",2,"float","float32"]],"scalar_args":{"axis":"None"},"class_bearing":false}]},{"output_sha":"07e1559e97dafb5d","size":1,"n_papers":2,"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":[-4.545232772827148,6.227241516113281,-2.466170072555542,-29.79172706604004],"values_recorded":4,"members":[{"code_sha256_prefix":"698e12d1755a5461","path":"unimol_plus/inference.py","papers":["2309.15798","2406.14969"],"paper_pages":[{"arxiv_id":"2309.15798","page":"/paper/node-aligned-graph-to-graph-generation-for"},{"arxiv_id":"2406.14969","page":"/paper/uni-mol2-exploring-molecular-pretraining"}],"arg_sig_recorded":[["mask",2,"float","float32"],["value",2,"float","float32"]],"scalar_args":{"dim":"1","eps":"1e-10","keepdim":"False"},"class_bearing":false}]},{"output_sha":"570aa23768488cde","size":1,"n_papers":1,"shape":[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":[2.6101510524749756,-3.454127550125122,1.0056008100509644,-2.5106887817382812,-0.9842962026596069,6.8385844230651855,-0.9025624394416809,1.2900769710540771],"values_recorded":8,"members":[{"code_sha256_prefix":"bff9c1af0e65b23b","path":"denserlhf/trainer/ppo_utils/experience_maker.py","papers":["2306.00398"],"paper_pages":[{"arxiv_id":"2306.00398","page":"/paper/preference-grounded-token-level-guidance-for-1"}],"arg_sig_recorded":[["tensor",2,"float","float32"],["mask",2,"float","float32"]],"scalar_args":{"dim":"0"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"bool","bool"]],"n_implementations_compared":3,"n_papers":4,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"e52e77fcb901c17d","size":2,"n_papers":2,"shape":[4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":2,"torch_reference_conventions_with_this_digest":[],"values":[-0.07139140367507935,0.10019401460886002,0.20475859940052032,0.018250495195388794],"values_recorded":4,"members":[{"code_sha256_prefix":"64dbc58af5081065","path":"src/clrcmd/models.py","papers":["2202.13196"],"paper_pages":[{"arxiv_id":"2202.13196","page":"/paper/toward-interpretable-semantic-textual"}],"arg_sig_recorded":[["x",2,"float","float32"],["mask",2,"bool","bool"]],"scalar_args":{"dim":"1"},"class_bearing":false},{"code_sha256_prefix":"6f0e0c50d69a79bf","path":"pretrain/models.py","papers":["2108.13643"],"paper_pages":[{"arxiv_id":"2108.13643","page":"/paper/learning-to-synthesize-programs-as"}],"arg_sig_recorded":[["x",2,"float","float32"],["mask",2,"bool","bool"]],"scalar_args":{"dim":"-1","keepdim":"False"},"class_bearing":false}]},{"output_sha":"ba6280b80432c550","size":1,"n_papers":2,"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":[0.043201446533203125],"values_recorded":1,"members":[{"code_sha256_prefix":"e078eeed20f03838","path":"algs/rep.py","papers":["2206.06520","2607.01978"],"paper_pages":[{"arxiv_id":"2206.06520","page":"/paper/memory-based-model-editing-at-scale"},{"arxiv_id":"2607.01978","page":"/paper/arxiv-2607-01978"}],"arg_sig_recorded":[["values",2,"float","float32"],["mask",2,"bool","bool"]],"scalar_args":{},"class_bearing":false}]}]}]}