{"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/drop-path","entry":"drop_path","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":27,"n_papers":61,"n_buckets":2,"n_distinct_outputs":5,"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/drop-path","buckets":[{"bucket":[[4,"float","float32"]],"n_implementations_compared":18,"n_papers":36,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"a8c38328240cb5f9","size":7,"n_papers":16,"shape":[2,3,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":7,"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,-0.0,0.0,0.0,-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":96,"members":[{"code_sha256_prefix":"971ae8d2d8313e30","path":"src/models/dwiseneuro.py","papers":["2407.09100","2011.10566","2112.14000","2604.21450","2601.07293"],"paper_pages":[{"arxiv_id":"2407.09100","page":"/paper/retrospective-for-the-dynamic-sensorium"},{"arxiv_id":"2011.10566","page":"/paper/exploring-simple-siamese-representation"},{"arxiv_id":"2112.14000","page":"/paper/pale-transformer-a-general-vision-transformer"},{"arxiv_id":"2604.21450","page":"/paper/arxiv-2604-21450"},{"arxiv_id":"2601.07293","page":"/paper/arxiv-2601-07293"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True","scale_by_keep":"True"},"class_bearing":false},{"code_sha256_prefix":"c157f5b112b3a392","path":"mono/model/backbones/ViT_DINO.py","papers":["2304.07193","2404.15506","2601.05246"],"paper_pages":[{"arxiv_id":"2304.07193","page":"/paper/dinov2-learning-robust-visual-features"},{"arxiv_id":"2404.15506","page":"/paper/metric3d-v2-a-versatile-monocular-geometric-1"},{"arxiv_id":"2601.05246","page":"/paper/arxiv-2601-05246"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"87577b3ff9d32712","path":"pypots/nn/modules/tslanet/backbone.py","papers":["2404.08472","2608.31029"],"paper_pages":[{"arxiv_id":"2404.08472","page":"/paper/tslanet-rethinking-transformers-for-time"},{"arxiv_id":"2608.31029","page":"/paper/arxiv-2608-31029"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True","scale_by_keep":"True"},"class_bearing":false},{"code_sha256_prefix":"e3aa4e8e74369506","path":"networks.py","papers":["2303.04249","2411.15867"],"paper_pages":[{"arxiv_id":"2303.04249","page":"/paper/where-we-are-and-what-we-re-looking-at-query"},{"arxiv_id":"2411.15867","page":"/paper/panollama-generating-endless-and-coherent"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True","scale_by_keep":"True"},"class_bearing":false},{"code_sha256_prefix":"f9a1900525331e0f","path":"models/croco.py","papers":["2210.10716","2506.13750"],"paper_pages":[{"arxiv_id":"2210.10716","page":"/paper/croco-self-supervised-pre-training-for-3d"},{"arxiv_id":"2506.13750","page":"/paper/test3r-learning-to-reconstruct-3d-at-test"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True","scale_by_keep":"True"},"class_bearing":false},{"code_sha256_prefix":"aea279a2d78d1352","path":"src/dust3r/model.py","papers":["2603.18493"],"paper_pages":[{"arxiv_id":"2603.18493","page":"/paper/arxiv-2603-18493"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True","scale_by_keep":"True"},"class_bearing":false},{"code_sha256_prefix":"b1286732acea8936","path":"nas_ood_single/search/models/model_search.py","papers":["2109.02038"],"paper_pages":[{"arxiv_id":"2109.02038","page":"/paper/nas-ood-neural-architecture-search-for-out-of"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.5"},"class_bearing":false}]},{"output_sha":"fae90c40e4854c2d","size":7,"n_papers":10,"shape":[2,3,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":7,"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,-0.0,2.0639593601226807,0.9513998627662659,4.2033185958862305,-0.03755061700940132,3.308645248413086,-1.2489731311798096,-4.816895484924316,-0.42870891094207764,-2.7740046977996826,-4.0130934715271,-2.7374205589294434,-0.052834078669548035,-5.59221887588501,-1.4770385026931763,-1.2697049379348755,0.4257344603538513,1.6881035566329956,-2.181506633758545,1.5447407960891724,4.188474178314209,0.9692551493644714,0.044237371534109116,6.2088446617126465,0.1472381055355072,1.2120463848114014,0.5684263706207275,1.0316386222839355,-1.3393075466156006,2.1854777336120605,0.53412264585495,1.3243402242660522,0.4742993116378784,-4.4336161613464355,-0.17499640583992004,0.33080628514289856,-1.6774734258651733,1.4334758520126343,2.460728168487549,-3.0427823066711426,2.1557228565216064,0.45674654841423035,0.8783701062202454,3.9451634883880615,-2.3373141288757324,0.9950191974639893,0.29571279883384705,-2.735473394393921,-0.5712951421737671],"values_recorded":96,"members":[{"code_sha256_prefix":"39eace7e2822504f","path":"towhee/models/uniformer/uniformer.py","papers":["2201.04676","2411.11471"],"paper_pages":[{"arxiv_id":"2201.04676","page":"/paper/uniformer-unified-transformer-for-efficient-1"},{"arxiv_id":"2411.11471","page":"/paper/generalizable-person-re-identification-via-2"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"9bdf2492c6e0a8de","path":"model/OpenCity/OpenCity.py","papers":["2408.10269","2602.19113"],"paper_pages":[{"arxiv_id":"2408.10269","page":"/paper/opencity-open-spatio-temporal-foundation"},{"arxiv_id":"2602.19113","page":"/paper/arxiv-2602-19113"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"a34c005ba2203f35","path":"model/impl/actionformer.py","papers":["2504.08222","2412.09032"],"paper_pages":[{"arxiv_id":"2504.08222","page":"/paper/f-3-set-towards-analyzing-fast-frequent-and"},{"arxiv_id":"2412.09032","page":"/paper/speech-forensics-towards-comprehensive"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"2ec78252af199d14","path":"src/model/backbones/swin.py","papers":["2103.14030"],"paper_pages":[{"arxiv_id":"2103.14030","page":"/paper/swin-transformer-hierarchical-vision"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"3c83cad222232ac6","path":"network/RerankTransformer.py","papers":["2110.13430"],"paper_pages":[{"arxiv_id":"2110.13430","page":"/paper/contextual-similarity-aggregation-with-self"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"68b7ffb36f0515ff","path":"networks/embedding_translation.py","papers":["2608.22619"],"paper_pages":[{"arxiv_id":"2608.22619","page":"/paper/arxiv-2608-22619"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"p":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"e37b79debce8d027","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",4,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false}]},{"output_sha":"780f05c3265726f3","size":4,"n_papers":10,"shape":[2,3,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":4,"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":"52d96aa31ed74a56","path":"basicsr/archs/swinir_arch.py","papers":["2108.10257","2404.00722","2411.15922","2203.11589"],"paper_pages":[{"arxiv_id":"2108.10257","page":"/paper/swinir-image-restoration-using-swin"},{"arxiv_id":"2404.00722","page":"/paper/drct-saving-image-super-resolution-away-from"},{"arxiv_id":"2411.15922","page":"/paper/prompthsi-universal-hyperspectral-image"},{"arxiv_id":"2203.11589","page":"/paper/adaptive-patch-exiting-for-scalable-single"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.2","training":"True"},"class_bearing":false},{"code_sha256_prefix":"fe7d4321dbeef661","path":"net.py","papers":["2411.02840","2211.14461","2603.05116","2503.10252"],"paper_pages":[{"arxiv_id":"2411.02840","page":"/paper/test-time-dynamic-image-fusion"},{"arxiv_id":"2211.14461","page":"/paper/cddfuse-correlation-driven-dual-branch"},{"arxiv_id":"2603.05116","page":"/paper/arxiv-2603-05116"},{"arxiv_id":"2503.10252","page":"/paper/svip-semantically-contextualized-visual"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.2","training":"True"},"class_bearing":false},{"code_sha256_prefix":"9ea4d5b8b4d5ef2f","path":"models/network_vrt.py","papers":["2201.12288"],"paper_pages":[{"arxiv_id":"2201.12288","page":"/paper/vrt-a-video-restoration-transformer"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"drop_prob":"0.2","training":"True"},"class_bearing":false},{"code_sha256_prefix":"a86440e38234fea6","path":"dyn_slim/models/dyn_slim_net.py","papers":["2103.13258"],"paper_pages":[{"arxiv_id":"2103.13258","page":"/paper/dynamic-slimmable-network"}],"arg_sig_recorded":[["inputs",4,"float","float32"]],"scalar_args":{"training":"True","drop_path_rate":"0.2"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"]],"n_implementations_compared":9,"n_papers":25,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"9913fdcbb25629ad","size":8,"n_papers":23,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":8,"torch_reference_conventions_with_this_digest":[],"values":[0.0,-0.0,0.0,-0.0,-0.0,-0.0,-0.0,0.0,1.0377519130706787,1.9182913303375244,-0.7943991422653198,-3.1366963386535645,-0.5770701766014099,4.644217491149902,-1.0295679569244385,1.1010571718215942,0.0,-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":32,"members":[{"code_sha256_prefix":"55120f2026b56aa2","path":"basicsr/models/archs/Xformer_arch.py","papers":["2301.12246","2303.06440","2509.24693","2104.12533","2206.05184","2206.13188","2512.16202","2605.12138"],"paper_pages":[{"arxiv_id":"2301.12246","page":"/paper/a-closer-look-at-few-shot-classification"},{"arxiv_id":"2303.06440","page":"/paper/xformer-hybrid-x-shaped-transformer-for-image"},{"arxiv_id":"2509.24693","page":"/paper/arxiv-2509-24693"},{"arxiv_id":"2104.12533","page":"/paper/visformer-the-vision-friendly-transformer"},{"arxiv_id":"2206.05184","page":"/paper/exploring-feature-self-relation-for-self"},{"arxiv_id":"2206.13188","page":"/paper/self-supervised-learning-in-remote-sensing-a"},{"arxiv_id":"2512.16202","page":"/paper/arxiv-2512-16202"},{"arxiv_id":"2605.12138","page":"/paper/arxiv-2605-12138"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"3ac6b7d76e8e3584","path":"seaformer-cls/seaformer.py","papers":["2105.14432","2301.13156","2305.13311","2606.15751","2601.12079"],"paper_pages":[{"arxiv_id":"2105.14432","page":"/paper/transformer-based-deep-image-matching-for"},{"arxiv_id":"2301.13156","page":"/paper/seaformer-squeeze-enhanced-axial-transformer"},{"arxiv_id":"2305.13311","page":"/paper/vdt-an-empirical-study-on-video-diffusion"},{"arxiv_id":"2606.15751","page":"/paper/arxiv-2606-15751"},{"arxiv_id":"2601.12079","page":"/paper/arxiv-2601-12079"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"6bb7492655ecbda4","path":"src/vit.py","papers":["2010.11929","2112.05425","2310.05184"],"paper_pages":[{"arxiv_id":"2010.11929","page":"/paper/an-image-is-worth-16x16-words-transformers-1"},{"arxiv_id":"2112.05425","page":"/paper/couplformer-rethinking-vision-transformer"},{"arxiv_id":"2310.05184","page":"/paper/aanet-aggregation-and-alignment-network-with"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"10e67144852e5fce","path":"VLog/model/models.py","papers":["2307.16715","2503.09402"],"paper_pages":[{"arxiv_id":"2307.16715","page":"/paper/univtg-towards-unified-video-language"},{"arxiv_id":"2503.09402","page":"/paper/vlog-video-language-models-by-generative"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"314973a77b15948e","path":"models/base_model_ts.py","papers":["2407.02309","2402.11301"],"paper_pages":[{"arxiv_id":"2407.02309","page":"/paper/semantically-guided-representation-learning"},{"arxiv_id":"2402.11301","page":"/paper/revit-enhancing-vision-transformers-with"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"0233d6e8a07784ae","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",2,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"04e8544d3f2fd61b","path":"look2hear/models/TDANet.py","papers":["2209.15200"],"paper_pages":[{"arxiv_id":"2209.15200","page":"/paper/an-efficient-encoder-decoder-architecture"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false},{"code_sha256_prefix":"e60d6e23233f6f4b","path":"fourm/models/fm.py","papers":["2312.06647"],"paper_pages":[{"arxiv_id":"2312.06647","page":"/paper/4m-massively-multimodal-masked-modeling-1"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True"},"class_bearing":false}]},{"output_sha":"3159ee4a76838806","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":[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,-0.0,0.0,0.13279087841510773,-3.245751142501831,0.8642228245735168,-0.8123717308044434,-0.04518844932317734,-2.361564874649048,-1.073736548423767,1.967348337173462,-0.0,0.0,0.0,0.0,-0.0,0.0,-0.0,-0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"f5ab76486eeab7b9","path":"units/models/model.py","papers":["2304.03435","2407.14142"],"paper_pages":[{"arxiv_id":"2304.03435","page":"/paper/towards-unified-scene-text-spotting-based-on"},{"arxiv_id":"2407.14142","page":"/paper/early-preparation-pays-off-new-classifier-pre"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"drop_prob":"0.5","training":"True","scale_by_keep":"True"},"class_bearing":false}]}]}]}