{"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/sigmoid-ce-loss","entry":"sigmoid_ce_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":4,"n_papers":8,"n_buckets":2,"n_distinct_outputs":3,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":1,"by_error":{"RuntimeError":1}},"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/sigmoid-ce-loss","buckets":[{"bucket":[[3,"float","float32"],[3,"float","float32"]],"n_implementations_compared":3,"n_papers":7,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"8e235d1ee97d4540","size":2,"n_papers":6,"shape":[],"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":[-0.19282576441764832],"values_recorded":1,"members":[{"code_sha256_prefix":"a9292f5d89194794","path":"model/PixelLM.py","papers":["2312.02228","2409.19603","2404.05673","2412.04292","2406.20076"],"paper_pages":[{"arxiv_id":"2312.02228","page":"/paper/pixellm-pixel-reasoning-with-large-multimodal"},{"arxiv_id":"2409.19603","page":"/paper/one-token-to-seg-them-all-language-instructed"},{"arxiv_id":"2404.05673","page":"/paper/cores-orchestrating-the-dance-of-reasoning"},{"arxiv_id":"2412.04292","page":"/paper/sida-social-media-image-deepfake-detection"},{"arxiv_id":"2406.20076","page":"/paper/evf-sam-early-vision-language-fusion-for-text"}],"arg_sig_recorded":[["inputs",3,"float","float32"],["targets",3,"float","float32"]],"scalar_args":{"num_masks":"2.0"},"class_bearing":false},{"code_sha256_prefix":"bf7e8883d6ce76b4","path":"model/VISA.py","papers":["2407.11325"],"paper_pages":[{"arxiv_id":"2407.11325","page":"/paper/visa-reasoning-video-object-segmentation-via"}],"arg_sig_recorded":[["inputs",3,"float","float32"],["targets",3,"float","float32"]],"scalar_args":{"num_masks":"2.0"},"class_bearing":false}]},{"output_sha":"bb5a2393b0ed8da6","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":[-0.1710728257894516,-0.21457868814468384],"values_recorded":2,"members":[{"code_sha256_prefix":"1033e9116b1e2573","path":"model/IVM.py","papers":["2405.19783"],"paper_pages":[{"arxiv_id":"2405.19783","page":"/paper/instruction-guided-visual-masking"}],"arg_sig_recorded":[["inputs",3,"float","float32"],["targets",3,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"056423f1a2563b3d","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":[0.8585387468338013],"values_recorded":1,"members":[{"code_sha256_prefix":"b9e60254a36a3fb8","path":"model/PIXAR.py","papers":["2603.20193"],"paper_pages":[{"arxiv_id":"2603.20193","page":"/paper/arxiv-2603-20193"}],"arg_sig_recorded":[["inputs",2,"float","float32"],["targets",2,"float","float32"]],"scalar_args":{"num_masks":"2.0"},"class_bearing":false}]}]}]}