{"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/compute-baseline-loss","entry":"compute_baseline_loss","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":2,"n_papers":8,"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/compute-baseline-loss","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":2,"n_papers":8,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"6b6a5f6fb7586ce2","size":1,"n_papers":4,"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":[16.20873260498047],"values_recorded":1,"members":[{"code_sha256_prefix":"e9123707cba84b2c","path":"atari/torchbeast/monobeast.py","papers":["2201.03544","1708.04782","1809.04474","1910.03552"],"paper_pages":[{"arxiv_id":"2201.03544","page":"/paper/the-effects-of-reward-misspecification-1"},{"arxiv_id":"1708.04782","page":"/paper/starcraft-ii-a-new-challenge-for"},{"arxiv_id":"1809.04474","page":"/paper/multi-task-deep-reinforcement-learning-with"},{"arxiv_id":"1910.03552","page":"/paper/torchbeast-a-pytorch-platform-for-distributed"}],"arg_sig_recorded":[["advantages",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"ee171fe70dd6f53d","size":1,"n_papers":4,"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":[2.0260918140411377],"values_recorded":1,"members":[{"code_sha256_prefix":"dde95c495d2752d6","path":"monobeast/minigrid/monobeast_amigo.py","papers":["2110.10661","2111.13119","1910.08210","2006.12122"],"paper_pages":[{"arxiv_id":"2110.10661","page":"/paper/silg-the-multi-environment-symbolic"},{"arxiv_id":"2111.13119","page":"/paper/interesting-object-curious-agent-learning-1"},{"arxiv_id":"1910.08210","page":"/paper/rtfm-generalising-to-novel-environment"},{"arxiv_id":"2006.12122","page":"/paper/learning-with-amigo-adversarially-motivated"}],"arg_sig_recorded":[["advantages",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}