{"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/shift","entry":"shift","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":5,"n_buckets":4,"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/shift","buckets":[{"bucket":[[4,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"0606d1fe20715d64","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":[0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.7231047749519348,0.6530793309211731,1.4460861682891846,1.0985400676727295,1.1372957229614258,-0.19992724061012268,-0.2714869976043701,0.8319791555404663,0.3433533310890198,-0.13238386809825897,-1.1905570030212402,-0.012713957577943802,-0.709074079990387,-0.4362029433250427,-2.665717124938965,0.812962532043457,-0.45303258299827576,0.12553228437900543,0.5928415060043335,-1.463806390762329,-0.7250184416770935,1.1514394283294678,-0.3975509703159332,1.4335219860076904,0.22366678714752197,1.184694528579712,-2.0680742263793945,-0.16907231509685516,0.3742450773715973,0.00391392083838582,0.895301342010498,-0.4980470836162567,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0319796800613403,0.47569993138313293,2.1016592979431152,-0.01877530850470066,1.654322624206543,-0.6244865655899048,-2.408447742462158,-0.21435445547103882,-1.3870023488998413,-2.00654673576355,-1.3687102794647217,-0.026417039334774017,-2.796109437942505,-0.7385192513465881,-0.6348524689674377,0.21286723017692566,0.8440517783164978,-1.0907533168792725,0.7723703980445862,2.0942370891571045,0.4846275746822357,0.022118685767054558,3.1044223308563232,0.0736190527677536,0.6060231924057007,0.28421318531036377,0.5158193111419678,-0.6696537733078003,1.0927388668060303,0.267061322927475,0.6621701121330261,0.2371496558189392],"values_recorded":96,"members":[{"code_sha256_prefix":"f6e07e75149898e3","path":"timesformer_pytorch/timesformer_pytorch.py","papers":["2102.05095"],"paper_pages":[{"arxiv_id":"2102.05095","page":"/paper/is-space-time-attention-all-you-need-for"}],"arg_sig_recorded":[["t",4,"float","float32"]],"scalar_args":{"amt":"1"},"class_bearing":false}]},{"output_sha":"e856177d48c47374","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":[0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.7231047749519348,0.6530793309211731,1.4460861682891846,1.0985400676727295,1.1372957229614258,-0.19992724061012268,-0.2714869976043701,0.8319791555404663,0.3433533310890198,-0.13238386809825897,-1.1905570030212402,-0.012713957577943802,-0.709074079990387,-0.4362029433250427,-2.665717124938965,0.812962532043457,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0319796800613403,0.47569993138313293,2.1016592979431152,-0.01877530850470066,1.654322624206543,-0.6244865655899048,-2.408447742462158,-0.21435445547103882,-1.3870023488998413,-2.00654673576355,-1.3687102794647217,-0.026417039334774017,-2.796109437942505,-0.7385192513465881,-0.6348524689674377,0.21286723017692566],"values_recorded":96,"members":[{"code_sha256_prefix":"6ba08bb22d683e66","path":"src/model/SaTformer/SaTformer.py","papers":["2511.11090"],"paper_pages":[{"arxiv_id":"2511.11090","page":"/paper/arxiv-2511-11090"}],"arg_sig_recorded":[["t",4,"float","float32"]],"scalar_args":{"amt":"2"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"b16cf97b1a5172a0","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":[0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.8026286363601685,-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],"values_recorded":32,"members":[{"code_sha256_prefix":"2fdf59e29c6d95cc","path":"g_mlp_pytorch/g_mlp_pytorch.py","papers":["2105.08050"],"paper_pages":[{"arxiv_id":"2105.08050","page":"/paper/pay-attention-to-mlps"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{"amount":"1","mask":"None"},"class_bearing":false}]}]},{"bucket":[[2,"float","float64"],[1,"float","float64"],[1,"float","float64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"d7bd5ceec8a69dcd","size":1,"n_papers":1,"shape":[4,8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.802628679592353,-1.5337762569179567,0.47605322923618437,-0.6908870620289821,-0.9028494964356759,-1.0304712253028872,-0.6627609239992189,0.572889220601701,0.5188759529457332,0.9591456414705227,-0.39719957334668987,-1.568348179202036,-0.2885350906311486,2.3221088606181515,-0.5147839769988165,0.5505285791931418,0.06639544283095256,-1.6228755249801277,0.4321114229703758,-0.40618587814690116,-0.022594224204796676,-1.1807823902688124,-0.5368682495213899,0.9836741886099452,-0.7956127851079772,0.433274409544924,0.9449777773193271,1.01751825335816,-1.2257857707553415,1.2742179092187245,-1.3222218927282292,-0.5941090922688514],"values_recorded":32,"members":[{"code_sha256_prefix":"65975a99774a580e","path":"src/language_shift/pipeline.py","papers":["2603.22225"],"paper_pages":[{"arxiv_id":"2603.22225","page":"/paper/arxiv-2603-22225"}],"arg_sig_recorded":[["X",2,"float","float64"],["mu_src",1,"float","float64"],["mu_tgt",1,"float","float64"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[3,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"52169bbda8c0492e","size":1,"n_papers":1,"shape":[2,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.15099599957466125,-1.434759497642517,-0.34014570713043213,-0.3811257779598236,-0.7722031474113464,0.8366092443466187,-0.16943085193634033,0.15168990194797516,-0.08752579241991043,0.7744670510292053,-0.5704304575920105,1.1243221759796143,0.9237498044967651,-0.7546214461326599,-0.30625444650650024,-1.0338436365127563,0.9990944862365723,0.6304919123649597,0.044029541313648224,1.7415422201156616,-0.6859840750694275,0.9828868508338928,-0.14383146166801453,0.38964250683784485,0.7487973570823669,-0.9978419542312622,0.5280088782310486,0.18848304450511932,1.155332088470459,1.6535718441009521,-0.581495463848114,1.8763816356658936],"values_recorded":32,"members":[{"code_sha256_prefix":"fd07c4fcaa87fe04","path":"layers/transformer/ndr.py","papers":["2110.07732"],"paper_pages":[{"arxiv_id":"2110.07732","page":"/paper/the-neural-data-router-adaptive-control-flow"}],"arg_sig_recorded":[["posmat",3,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}