{"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/mask-logits","entry":"mask_logits","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":7,"n_papers":10,"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/mask-logits","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":5,"n_papers":8,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"40df34f4f8e18633","size":3,"n_papers":5,"shape":[4,8],"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":[8026286592.0,-25337763840.0,-5239467520.0,-16908869632.0,-19028494336.0,-20304713728.0,-16627609600.0,-4271107840.0,-4811240448.0,-408543360.0,-13971996672.0,-25683482624.0,-12885351424.0,13221087232.0,-15147839488.0,-4494714368.0,-9336045568.0,-26228756480.0,-5678886400.0,-14061858816.0,-10225942528.0,-21807822848.0,-15368683520.0,-163258320.0,-17956128768.0,-5667256320.0,-550222400.0,175182816.0,-22257856512.0,2742179584.0,-23222216704.0,-15941090304.0],"values_recorded":32,"members":[{"code_sha256_prefix":"1c17153fb5488283","path":"Models/gmmformer/model.py","papers":["2005.06409","2504.10920","2507.17402"],"paper_pages":[{"arxiv_id":"2005.06409","page":"/paper/dense-caption-matching-and-frame-selection"},{"arxiv_id":"2504.10920","page":"/paper/towards-efficient-partially-relevant-video"},{"arxiv_id":"2507.17402","page":null}],"arg_sig_recorded":[["target",2,"float","float32"],["mask",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"1a5542dee1f0295c","path":"baselines/mxml/model_xml_shared.py","papers":["2108.00061"],"paper_pages":[{"arxiv_id":"2108.00061","page":"/paper/mtvr-multilingual-moment-retrieval-in-videos"}],"arg_sig_recorded":[["target",2,"float","float32"],["mask",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"e47b0e22eeee3414","path":"model/squidnet.py","papers":["2210.08714"],"paper_pages":[{"arxiv_id":"2210.08714","page":"/paper/selective-query-guided-debiasing-network-for"}],"arg_sig_recorded":[["target",2,"float","float32"],["mask",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"c88b32d9ccbf7c2d","size":2,"n_papers":3,"shape":[4,8],"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":[8.026286701169975e+29,-2.5337762916507424e+30,-5.239467879479783e+29,-1.6908870671945738e+30,-1.9028493911891538e+30,-2.030471307609774e+30,-1.662760954654057e+30,-4.271108097656862e+29,-4.811240664498615e+29,-4.0854335255994155e+28,-1.397199695521043e+30,-2.5683480944299894e+30,-1.288535095993527e+30,1.3221087793929547e+30,-1.5147840519771304e+30,-4.494714039567333e+29,-9.336045245505474e+29,-2.6228757868293425e+30,-5.6788863474467154e+29,-1.4061859433696933e+30,-1.0225942341531538e+30,-2.1807823438129217e+30,-1.5368684066183955e+30,-1.6325831297148274e+28,-1.7956128352860577e+30,-5.667256103272704e+29,-5.502224222927166e+28,1.7518281960695792e+28,-2.225785816373896e+30,2.7421796135902407e+29,-2.322221829004555e+30,-1.5941090796726913e+30],"values_recorded":32,"members":[{"code_sha256_prefix":"60df4d5a1eee1b92","path":"tr_detr/model.py","papers":["2307.16715","2401.02309"],"paper_pages":[{"arxiv_id":"2307.16715","page":"/paper/univtg-towards-unified-video-language"},{"arxiv_id":"2401.02309","page":"/paper/tr-detr-task-reciprocal-transformer-for-joint"}],"arg_sig_recorded":[["inputs",2,"float","float32"],["mask",2,"float","float32"]],"scalar_args":{"mask_value":"-1e+30"},"class_bearing":false},{"code_sha256_prefix":"bf59110e6f5ddc08","path":"model.py","papers":["2004.12362"],"paper_pages":[{"arxiv_id":"2004.12362","page":"/paper/relational-graph-attention-network-for-aspect"}],"arg_sig_recorded":[["target",2,"float","float32"],["mask",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"int","int32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"de878bf8d9bfbe06","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.0000000150474662e+30,2.0000000300949324e+30,1.0000000150474662e+30,-0.6908870339393616,-0.9028494954109192,2.0000000300949324e+30,-1.0000000150474662e+30,0.5728892087936401,0.5188759565353394,-1.0000000150474662e+30,-0.3971995711326599,2.0000000300949324e+30,2.0000000300949324e+30,2.0000000300949324e+30,2.0000000300949324e+30,1.0000000150474662e+30,-1.0000000150474662e+30,-1.0000000150474662e+30,1.0000000150474662e+30,-1.0000000150474662e+30,1.0000000150474662e+30,-1.0000000150474662e+30,-0.5368682742118835,0.983674168586731,2.0000000300949324e+30,2.0000000300949324e+30,0.9449777603149414,2.0000000300949324e+30,2.0000000300949324e+30,1.0000000150474662e+30,-1.3222218751907349,1.0000000150474662e+30],"values_recorded":32,"members":[{"code_sha256_prefix":"dea46bb8718e5def","path":"models.py","papers":["1804.09541"],"paper_pages":[{"arxiv_id":"1804.09541","page":"/paper/qanet-combining-local-convolution-with-global"}],"arg_sig_recorded":[["inputs",2,"float","float32"],["mask",2,"int","int32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"int","int64"]],"n_implementations_compared":1,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"de878bf8d9bfbe06","size":1,"n_papers":2,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.0000000150474662e+30,2.0000000300949324e+30,1.0000000150474662e+30,-0.6908870339393616,-0.9028494954109192,2.0000000300949324e+30,-1.0000000150474662e+30,0.5728892087936401,0.5188759565353394,-1.0000000150474662e+30,-0.3971995711326599,2.0000000300949324e+30,2.0000000300949324e+30,2.0000000300949324e+30,2.0000000300949324e+30,1.0000000150474662e+30,-1.0000000150474662e+30,-1.0000000150474662e+30,1.0000000150474662e+30,-1.0000000150474662e+30,1.0000000150474662e+30,-1.0000000150474662e+30,-0.5368682742118835,0.983674168586731,2.0000000300949324e+30,2.0000000300949324e+30,0.9449777603149414,2.0000000300949324e+30,2.0000000300949324e+30,1.0000000150474662e+30,-1.3222218751907349,1.0000000150474662e+30],"values_recorded":32,"members":[{"code_sha256_prefix":"9dc49f46edd7a69d","path":"qa/model/qanet.py","papers":["1804.09541","2109.12662"],"paper_pages":[{"arxiv_id":"1804.09541","page":"/paper/qanet-combining-local-convolution-with-global"},{"arxiv_id":"2109.12662","page":"/paper/improving-question-answering-performance"}],"arg_sig_recorded":[["target",2,"float","float32"],["mask",2,"int","int64"]],"scalar_args":{},"class_bearing":false}]}]}]}