{"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/reduce-tensor","entry":"reduce_tensor","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":5,"n_papers":6,"n_buckets":1,"n_distinct_outputs":3,"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/reduce-tensor","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":5,"n_papers":6,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"e473fcc30bcc5270","size":3,"n_papers":3,"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":[0.4506571590900421,-0.38344407081604004,0.11901330947875977,-0.1727217584848404,-0.2257123738527298,-0.2576178014278412,-0.16569022834300995,0.14322230219841003,0.12971898913383484,0.23978641629219055,-0.09929989278316498,-0.39208704233169556,-0.07213377207517624,0.5805271863937378,-0.1286959946155548,0.13763214647769928,0.016598859801888466,-0.4057188928127289,0.1080278530716896,-0.10154646635055542,-0.005648556165397167,-0.295195609331131,-0.1342170685529709,0.24591854214668274,-0.19890320301055908,0.10831860452890396,0.23624444007873535,0.2543795704841614,-0.3064464330673218,0.31855449080467224,-0.3305554687976837,-0.14852727949619293],"values_recorded":32,"members":[{"code_sha256_prefix":"06724a1cdbc6af8c","path":"evaluate.py","papers":["2211.09078"],"paper_pages":[{"arxiv_id":"2211.09078","page":"/paper/learning-dense-and-continuous-optical-flow"}],"arg_sig_recorded":[["tensor",2,"float","float32"]],"scalar_args":{"nprocs":"4"},"class_bearing":false},{"code_sha256_prefix":"a25acbda57ff74c2","path":"flow/models.py","papers":["2105.07239"],"paper_pages":[{"arxiv_id":"2105.07239","page":"/paper/ageflow-conditional-age-progression-and"}],"arg_sig_recorded":[["tensor",2,"float","float32"]],"scalar_args":{"world_size":"4"},"class_bearing":false},{"code_sha256_prefix":"b57663499e3c25d8","path":"ImageNet/train_dkd.py","papers":["2305.17007"],"paper_pages":[{"arxiv_id":"2305.17007","page":"/paper/improving-knowledge-distillation-via-1"}],"arg_sig_recorded":[["tensor",2,"float","float32"]],"scalar_args":{"args":"<fx_b57663499e3c25d8__reduce_tensor.Args object at 0xffff3c6"},"class_bearing":false}]},{"output_sha":"d7bd5ceec8a69dcd","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":[1.8026286363601685,-1.5337762832641602,0.47605323791503906,-0.6908870339393616,-0.9028494954109192,-1.0304712057113647,-0.6627609133720398,0.5728892087936401,0.5188759565353394,0.9591456651687622,-0.3971995711326599,-1.5683481693267822,-0.28853508830070496,2.322108745574951,-0.5147839784622192,0.5505285859107971,0.06639543920755386,-1.6228755712509155,0.4321114122867584,-0.4061858654022217,-0.02259422466158867,-1.180782437324524,-0.5368682742118835,0.983674168586731,-0.7956128120422363,0.43327441811561584,0.9449777603149414,1.0175182819366455,-1.225785732269287,1.274217963218689,-1.3222218751907349,-0.5941091179847717],"values_recorded":32,"members":[{"code_sha256_prefix":"65e1c0ed365fa761","path":"main_bench_mark.py","papers":["2201.01102","2110.09903"],"paper_pages":[{"arxiv_id":"2201.01102","page":"/paper/towards-transferable-unrestricted-adversarial"},{"arxiv_id":"2110.09903","page":"/paper/unrestricted-adversarial-attacks-on-imagenet"}],"arg_sig_recorded":[["tensor",2,"float","float32"]],"scalar_args":{"n":"1"},"class_bearing":false}]},{"output_sha":"cecc3732fc6a0e74","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":[0.9013143181800842,-0.7668881416320801,0.23802661895751953,-0.3454435169696808,-0.4514247477054596,-0.5152356028556824,-0.3313804566860199,0.28644460439682007,0.2594379782676697,0.4795728325843811,-0.19859978556632996,-0.7841740846633911,-0.14426754415035248,1.1610543727874756,-0.2573919892311096,0.27526429295539856,0.03319771960377693,-0.8114377856254578,0.2160557061433792,-0.20309293270111084,-0.011297112330794334,-0.590391218662262,-0.2684341371059418,0.4918370842933655,-0.39780640602111816,0.21663720905780792,0.4724888801574707,0.5087591409683228,-0.6128928661346436,0.6371089816093445,-0.6611109375953674,-0.29705455899238586],"values_recorded":32,"members":[{"code_sha256_prefix":"11965d5ebfe77481","path":"models/cnf_edge/cnf.py","papers":["2102.10240"],"paper_pages":[{"arxiv_id":"2102.10240","page":"/paper/learning-neural-generative-dynamics-for-1"}],"arg_sig_recorded":[["tensor",2,"float","float32"]],"scalar_args":{"world_size":"None"},"class_bearing":false}]}]}]}