{"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/droppath","entry":"DropPath","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":17,"n_papers":17,"n_buckets":3,"n_distinct_outputs":8,"n_class_bearing":17,"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/droppath","buckets":[{"bucket":[[3,"float","float32"]],"n_implementations_compared":15,"n_papers":15,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"6f3faa1240b83c45","size":6,"n_papers":6,"shape":[2,4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":6,"torch_reference_conventions_with_this_digest":[],"values":[-1.1164090633392334,2.1035664081573486,-1.5735058784484863,-0.3227573335170746,0.18874499201774597,-1.7934494018554688,-0.42518213391304016,-0.4764072299003601,-2.6740174293518066,0.014840524643659592,-1.06118643283844,-0.9652539491653442,1.0457615852355957,-0.21178856492042542,0.18961237370967865,0.5086449384689331,2.349726438522339,-0.9316235780715942,-0.10940723866224289,0.9680837988853455,-0.7130380868911743,1.405402660369873,-0.5044097304344177,1.1961461305618286,1.192887306213379,1.1546872854232788,-0.9432768225669861,-0.3828180432319641,-1.292304515838623,1.5512546300888062,-1.139289379119873,2.295790672302246,-1.1964797973632812,2.335315227508545,-1.4767911434173584,-1.0049105882644653,1.2488681077957153,0.7881149053573608,0.05503692477941513,2.1769278049468994,-1.490380883216858,-1.1218830347061157,-1.2681694030761719,-0.8574801087379456,1.22860848903656,-0.17978931963443756,0.48705312609672546,1.1303625106811523,-0.42420512437820435,-0.12189683318138123,0.9359967112541199,-1.2473024129867554,0.6600111126899719,0.23560380935668945,-0.8857372403144836,-1.2042896747589111,-1.5895508527755737,1.4441651105880737,2.066964864730835,-0.7268693447113037,2.3454771041870117,1.5510833263397217,-1.5906072854995728,-1.0749132633209229],"values_recorded":64,"members":[{"code_sha256_prefix":"15090130e3a1e904","path":"models/ocebo.py","papers":["2503.15141"],"paper_pages":[{"arxiv_id":"2503.15141","page":null}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"762514af1d1eeb94","path":"mae/modeling_pretrain.py","papers":["2111.06377"],"paper_pages":[{"arxiv_id":"2111.06377","page":"/paper/masked-autoencoders-are-scalable-vision"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"c713760d26bf0a45","path":"easycv/models/backbones/vision_transformer.py","papers":["2012.12877"],"paper_pages":[{"arxiv_id":"2012.12877","page":"/paper/training-data-efficient-image-transformers"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"cb0614ea84e3c9e8","path":"modeling/fusion_part/CRM.py","papers":["aaai_28388"],"paper_pages":[{"arxiv_id":"aaai_28388","page":null}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"e6e9f6bf7f63ce5e","path":"Codes/multimae/multimae.py","papers":["2303.09663"],"paper_pages":[{"arxiv_id":"2303.09663","page":"/paper/efficient-computation-sharing-for-multi-task"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"f4d723c4060a9c88","path":"vissl/models/trunks/beit_transformer.py","papers":["2106.08254"],"paper_pages":[{"arxiv_id":"2106.08254","page":"/paper/beit-bert-pre-training-of-image-transformers"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"00c5d9cceda3a9b2","size":5,"n_papers":5,"shape":[2,4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":5,"torch_reference_conventions_with_this_digest":[],"values":[-0.0,0.0,-0.0,-0.0,0.0,-0.0,-0.0,-0.0,-0.0,0.0,-0.0,-0.0,0.0,-0.0,0.0,0.0,0.0,-0.0,-0.0,0.0,-0.0,0.0,-0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,0.0,-0.0,0.0,-1.1964799165725708,2.335315227508545,-1.4767911434173584,-1.0049105882644653,1.2488681077957153,0.7881149053573608,0.05503692477941513,2.1769278049468994,-1.490380883216858,-1.1218831539154053,-1.2681694030761719,-0.8574801087379456,1.2286086082458496,-0.17978933453559875,0.48705312609672546,1.1303625106811523,-0.42420512437820435,-0.12189683318138123,0.9359967112541199,-1.2473024129867554,0.6600111126899719,0.23560380935668945,-0.8857372403144836,-1.2042896747589111,-1.5895508527755737,1.4441651105880737,2.066964864730835,-0.7268693447113037,2.3454771041870117,1.5510833263397217,-1.5906072854995728,-1.0749132633209229],"values_recorded":64,"members":[{"code_sha256_prefix":"59c07cf4d49e5e3c","path":"models_counting_network.py","papers":["2407.04619"],"paper_pages":[{"arxiv_id":"2407.04619","page":"/paper/countgd-multi-modal-open-world-counting"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"7bf42bf0e6458cb1","path":"codes/models/decoder_affordance.py","papers":["2505.24103"],"paper_pages":[{"arxiv_id":"2505.24103","page":"/paper/weakly-supervised-affordance-grounding-guided"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"93f0fde3bc773068","path":"models/maniqa.py","papers":["2403.15139"],"paper_pages":[{"arxiv_id":"2403.15139","page":"/paper/deep-generative-model-based-rate-distortion"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"99f368d7aea9ef52","path":"aff_block_LL.py","papers":["2307.14008"],"paper_pages":[{"arxiv_id":"2307.14008","page":"/paper/adaptive-frequency-filters-as-efficient"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"b20207e9c582c326","path":"core/gmflownet_model.py","papers":["2203.11335"],"paper_pages":[{"arxiv_id":"2203.11335","page":"/paper/global-matching-with-overlapping-attention"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"844ec428d46db9e4","size":1,"n_papers":1,"shape":[2,4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.0,0.0,-0.0,-0.0,0.0,-0.0,-0.0,-0.0,-0.0,0.0,-0.0,-0.0,0.0,-0.0,0.0,0.0,0.0,-0.0,-0.0,0.0,-0.0,0.0,-0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,0.0,-0.0,0.0,-0.0,0.0,-0.0,-0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,-0.0,0.0,-0.0,0.0,0.0,-0.0,-0.0,0.0,-0.0,0.0,0.0,-0.0,-0.0,-0.0,0.0,0.0,-0.0,0.0,0.0,-0.0,-0.0],"values_recorded":64,"members":[{"code_sha256_prefix":"7d33ccdf4bdeadbf","path":"model/s2wat.py","papers":["aaai_28529"],"paper_pages":[{"arxiv_id":"aaai_28529","page":null}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"a162a74a61f104e2","size":1,"n_papers":1,"shape":[2,4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.9923636317253113,1.8698368072509766,-1.3986718654632568,-0.28689539432525635,0.16777333617210388,-1.59417724609375,-0.3779396712779999,-0.4234730899333954,-2.3769044876098633,0.013191577978432178,-0.9432768225669861,-0.8580034971237183,0.9295658469200134,-0.18825650215148926,0.16854433715343475,0.4521288573741913,0.0,-0.0,-0.0,0.0,-0.0,0.0,-0.0,0.0,1.0603443384170532,1.0263886451721191,-0.8384683132171631,-0.34028273820877075,-1.1487151384353638,1.3788931369781494,-1.0127016305923462,2.0407028198242188,-1.0635377168655396,2.075835943222046,-1.3127033710479736,-0.8932539224624634,1.110105037689209,0.7005465626716614,0.04892171546816826,1.935046911239624,-1.3247830867767334,-0.9972294569015503,-1.127261757850647,-0.7622045278549194,1.0920965671539307,-0.15981273353099823,0.4329361319541931,1.0047667026519775,-0.0,-0.0,0.0,-0.0,0.0,0.0,-0.0,-0.0,-1.4129340648651123,1.2837023735046387,1.8373020887374878,-0.6461060643196106,2.0848684310913086,1.3787407875061035,-1.4138731956481934,-0.9554784893989563],"values_recorded":64,"members":[{"code_sha256_prefix":"eb3438f3ff649ddf","path":"VLog/model/models.py","papers":["2503.09402"],"paper_pages":[{"arxiv_id":"2503.09402","page":"/paper/vlog-video-language-models-by-generative"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"b0bc893fafe25542","size":1,"n_papers":1,"shape":[2,4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.0,0.0,-0.0,-0.0,0.0,-0.0,-0.0,-0.0,-0.0,0.0,-0.0,-0.0,0.0,-0.0,0.0,0.0,0.0,-0.0,-0.0,0.0,-0.0,0.0,-0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,0.0,-0.0,0.0,-1.9143677949905396,3.736504554748535,-2.362865924835205,-1.6078569889068604,1.9981889724731445,1.2609838247299194,0.08805908262729645,3.4830844402313232,-2.3846094608306885,-1.7950129508972168,-2.029071092605591,-1.371968150138855,1.9657737016677856,-0.28766292333602905,0.7792850136756897,1.8085800409317017,-0.6787282228469849,-0.1950349360704422,1.4975947141647339,-1.9956839084625244,1.0560177564620972,0.37696608901023865,-1.4171795845031738,-1.9268635511398315,-2.543281316757202,2.310664176940918,3.3071436882019043,-1.162990927696228,3.752763271331787,2.4817333221435547,-2.5449717044830322,-1.7198612689971924],"values_recorded":64,"members":[{"code_sha256_prefix":"511f72cb4c20504a","path":"code/model/decoder.py","papers":["2209.08956"],"paper_pages":[{"arxiv_id":"2209.08956","page":"/paper/panoramic-vision-transformer-for-saliency"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"d9503ca0a31171f2","size":1,"n_papers":1,"shape":[2,4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.9923636317253113,1.8698368072509766,-1.3986718654632568,-0.28689539432525635,0.16777333617210388,-1.59417724609375,-0.3779396712779999,-0.4234730899333954,-2.3769044876098633,0.013191577978432178,-0.9432768225669861,-0.8580034971237183,0.9295658469200134,-0.18825650215148926,0.16854433715343475,0.4521288573741913,2.0886459350585938,-0.828109860420227,-0.09725088626146317,0.8605189919471741,-0.6338116526603699,1.2492468357086182,-0.4483642280101776,1.0632410049438477,1.0603443384170532,1.0263886451721191,-0.8384683132171631,-0.34028273820877075,-1.1487151384353638,1.3788931369781494,-1.0127016305923462,2.0407028198242188,-1.0635377168655396,2.075835943222046,-1.3127033710479736,-0.8932539224624634,1.110105037689209,0.7005465626716614,0.04892171546816826,1.935046911239624,-1.3247830867767334,-0.9972294569015503,-1.127261757850647,-0.7622045278549194,1.0920965671539307,-0.15981273353099823,0.4329361319541931,1.0047667026519775,-0.37707123160362244,-0.10835274308919907,0.8319970965385437,-1.1087132692337036,0.5866765379905701,0.20942561328411102,-0.7873219847679138,-1.0704797506332397,-1.4129340648651123,1.2837023735046387,1.8373020887374878,-0.6461060643196106,2.0848684310913086,1.3787407875061035,-1.4138731956481934,-0.9554784893989563],"values_recorded":64,"members":[{"code_sha256_prefix":"938eafe395be5d19","path":"networks/RetrievalNet.py","papers":["2404.01524"],"paper_pages":[{"arxiv_id":"2404.01524","page":"/paper/on-train-test-class-overlap-and-detection-for"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]},{"bucket":[[2,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"fc21e89419f02b75","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":[0.0,-0.0,0.0,-0.0,-0.0,-0.0,-0.0,0.0,0.5765288472175598,1.0657174587249756,-0.4413328766822815,-1.7426091432571411,-0.32059454917907715,2.5801210403442383,-0.571982204914093,0.6116984486579895,0.07377271354198456,-1.8031951189041138,0.4801238179206848,-0.4513176381587982,-0.025104695931077003,-1.3119806051254272,-0.5965203046798706,1.0929713249206543,-0.0,0.0,0.0,0.0,-0.0,0.0,-0.0,-0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"f1ba368c5af15b64","path":"projects/evad/models/vit_model.py","papers":["2304.08451"],"paper_pages":[{"arxiv_id":"2304.08451","page":"/paper/efficient-video-action-detection-with-token"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]},{"bucket":[[4,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"780f05c3265726f3","size":1,"n_papers":1,"shape":[2,3,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.9038809537887573,0.8163491487503052,1.807607650756836,1.373175024986267,1.4216196537017822,-0.24990904331207275,-0.33935874700546265,1.0399739742279053,0.4291916489601135,-0.165479838848114,-1.4881962537765503,-0.015892446041107178,-0.8863425850868225,-0.5452536940574646,-3.332146406173706,1.0162031650543213,-0.5662907361984253,0.1569153517484665,0.7410518527030945,-1.8297579288482666,-0.9062730669975281,1.43929922580719,-0.49693870544433594,1.7919024229049683,0.27958348393440247,1.4808681011199951,-2.585092782974243,-0.21134039759635925,0.467806339263916,0.004892400931566954,1.1191266775131226,-0.6225588321685791,-0.526714563369751,1.2757916450500488,-0.6045889854431152,-0.606835126876831,-0.827340304851532,2.478611469268799,0.2657206058502197,-1.5050290822982788,-0.2650585472583771,-1.8492885828018188,-0.9282277226448059,1.521728277206421,0.02837824635207653,-0.20480617880821228,0.415722131729126,-1.5580719709396362,1.289974570274353,0.5946248769760132,2.6270740032196045,-0.02346913516521454,2.0679032802581787,-0.7806081771850586,-3.010559558868408,-0.26794305443763733,-1.733752965927124,-2.508183479309082,-1.7108877897262573,-0.03302129730582237,-3.4951367378234863,-0.923149049282074,-0.793565571308136,0.26608404517173767,1.0550646781921387,-1.3634415864944458,0.9654629826545715,2.6177964210510254,0.6057844758033752,0.027648357674479485,3.880527973175049,0.0920238122344017,0.7575289607048035,0.3552664816379547,0.6447741389274597,-0.837067186832428,1.365923523902893,0.3338266611099243,0.8277126550674438,0.2964370548725128,-2.771010160446167,-0.10937274992465973,0.2067539244890213,-1.0484209060668945,0.8959224224090576,1.5379550457000732,-1.9017388820648193,1.3473267555236816,0.28546658158302307,0.5489813089370728,2.4657270908355713,-1.460821270942688,0.6218869686126709,0.1848205029964447,-1.709670901298523,-0.35705944895744324],"values_recorded":96,"members":[{"code_sha256_prefix":"96592475595fbed1","path":"models/T1.py","papers":["2602.21043"],"paper_pages":[{"arxiv_id":"2602.21043","page":"/paper/arxiv-2602-21043"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]}]}