{"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/positionalencoding","entry":"PositionalEncoding","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":13,"n_papers":9,"n_buckets":5,"n_distinct_outputs":9,"n_class_bearing":13,"not_compared":{"not_run_on_shared_input":{"n":15,"by_error":{"RuntimeError":15}},"no_array_argument_ran_on_own_fixture_arguments_only":{"n":2,"n_papers":4,"recorded_shared_digest_equals_own_fixture_digest":2},"output_not_digested_non_numeric":{"n":0,"by_type":{}}},"withdrawn_excluded":0,"code_page":"/code/positionalencoding","buckets":[{"bucket":[[3,"float","float32"]],"n_implementations_compared":9,"n_papers":6,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"10d8865d27038279","size":3,"n_papers":2,"shape":[2,4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":1.1920928955078125e-07,"members_with_recorded_values":3,"torch_reference_conventions_with_this_digest":[],"values":[-0.8931272625923157,2.6828532218933105,-1.2588046789169312,0.7417941093444824,0.15099599957466125,-0.4347594976425171,-0.34014570713043213,0.618874192237854,-1.2977430820465088,0.5521746873855591,-0.7491157054901123,0.22280102968215942,0.8466090559959412,0.8305191397666931,0.15268990397453308,1.4069154262542725,2.789078712463379,-1.1614457368850708,0.11114352196455002,1.7545336484909058,-0.5504317879676819,2.124122142791748,-0.4015277922153473,1.9569149017333984,1.0954298973083496,-0.06624269485473633,-0.45910125970840454,0.6490820646286011,-1.0038481950759888,2.240553855895996,-0.9084314703941345,2.836627960205078,-0.9571838974952698,2.8682522773742676,-1.1814329624176025,0.19607150554656982,0.9990944862365723,1.6304919719696045,0.044029541313648224,2.741542339324951,-0.3508337736129761,-0.3572041988372803,-0.9147021174430847,0.30902010202407837,0.9928866624832153,0.8561185598373413,0.3906424939632416,1.9042894840240479,0.569933295249939,-0.5136643052101135,0.9474666714668274,-0.017775356769561768,0.5480075478553772,1.188283085823059,-0.7065898180007935,0.036566197872161865,-1.1305207014083862,0.16533958911895752,1.9490920305252075,0.3738410472869873,1.9063770771026611,2.2404167652130127,-1.2694858312606812,0.14006489515304565],"values_recorded":64,"members":[{"code_sha256_prefix":"4f5b948868e1eae9","path":"model/standard.py","papers":["1706.03762"],"paper_pages":[{"arxiv_id":"1706.03762","page":"/paper/attention-is-all-you-need"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"5dc71b216687fd19","path":"models.py","papers":["2210.00313"],"paper_pages":[{"arxiv_id":"2210.00313","page":"/paper/crisp-curriculum-based-sequential-neural"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"92aea12edbd4f5de","path":"model/scratch_model.py","papers":["1706.03762"],"paper_pages":[{"arxiv_id":"1706.03762","page":"/paper/attention-is-all-you-need"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"28cd979073fbb3da","size":2,"n_papers":2,"shape":[2,4,8],"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":[-0.0,2.9809482097625732,-1.3986719846725464,0.0,0.16777333617210388,-0.4830661416053772,-0.37793970108032227,0.6876380443572998,-1.4419368505477905,0.6135274767875671,-0.8323508501052856,0.24755671620368958,0.940676748752594,0.9227991104125977,0.1696554571390152,1.5632394552230835,3.0989766120910645,-1.2904952764511108,0.12349280714988708,1.9494819641113281,-0.6115909218788147,2.360135793685913,-0.4461420178413391,2.1743500232696533,1.2171443700790405,-0.07360299676656723,-0.5101125240325928,0.7212023138999939,-1.115386962890625,2.489504337310791,-1.0093683004379272,3.151808977127075,-1.0635377168655396,3.1869471073150635,-1.3127033710479736,0.0,1.110105037689209,1.8116577863693237,0.04892171546816826,3.0461583137512207,-0.3898153305053711,-0.39689356088638306,-1.0163357257843018,0.3433556854724884,1.1032074689865112,0.9512428641319275,0.43404722213745117,2.115877389907837,0.0,-0.5707381367683411,1.0527408123016357,-0.01975039765238762,0.60889732837677,0.0,-0.7850998640060425,0.04062911123037338,-1.2561341524124146,0.18371066451072693,2.1656579971313477,0.41537895798683167,2.118196964263916,2.489351987838745,-1.4105398654937744,0.0],"values_recorded":64,"members":[{"code_sha256_prefix":"429a06288f895ed4","path":"lib/eeg_transformer.py","papers":["1706.03762"],"paper_pages":[{"arxiv_id":"1706.03762","page":"/paper/attention-is-all-you-need"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"ba3da5536ab7c680","path":"models/TimeDART.py","papers":["2410.05711"],"paper_pages":[{"arxiv_id":"2410.05711","page":"/paper/diffusion-auto-regressive-transformer-for"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"f52b65ca7dcaa7e6","size":2,"n_papers":2,"shape":[2,4,8],"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":[-0.0,2.9809482097625732,-1.3986719846725464,0.0,0.16777333617210388,-0.4830661416053772,-0.37793970108032227,0.6876380443572998,-2.3769044876098633,1.1243027448654175,-0.9432768821716309,0.25310763716697693,0.9295658469200134,0.9228546619415283,0.16854433715343475,1.5632399320602417,2.0886459350585938,0.28300127387046814,-0.09725088626146317,1.9716300964355469,-0.6338116526603699,2.3603579998016357,-0.4483642280101776,2.1743521690368652,1.0603443384170532,2.1374998092651367,-0.8384683132171631,0.7708284258842468,-1.1487152576446533,2.490004301071167,-1.0127017498016357,3.1518139839172363,-0.12856994569301605,2.6761717796325684,-1.2017773389816284,0.0,1.121216058731079,1.811602234840393,0.05003282427787781,3.0461578369140625,-0.3898153305053711,-0.39689356088638306,-1.0163357257843018,0.3433556854724884,1.1032074689865112,0.9512428641319275,0.43404722213745117,2.115877389907837,0.0,0.4919831454753876,0.9429231286048889,-0.0031530859414488077,0.5977874398231506,0.0,-0.7862109541893005,0.04063083231449127,-0.4779663681983948,1.8840383291244507,1.948228120803833,0.45945414900779724,2.0959794521331787,2.4897964000701904,-1.4127620458602905,0.0],"values_recorded":64,"members":[{"code_sha256_prefix":"117a93cfb4606d84","path":"uniMASK/transformer.py","papers":["2211.10869"],"paper_pages":[{"arxiv_id":"2211.10869","page":"/paper/unimask-unified-inference-in-sequential"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"b9af059fe8645d6e","path":"model.py","papers":["1706.03762"],"paper_pages":[{"arxiv_id":"1706.03762","page":"/paper/attention-is-all-you-need"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"766cc7234ad6f22f","size":1,"n_papers":1,"shape":[2,1,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,1.0,0.0,1.0,0.8414709568023682,0.5403022766113281,0.009999833069741726,0.9999499917030334],"values_recorded":8,"members":[{"code_sha256_prefix":"6d88134a57f82380","path":"grounded_compgen_research/models/imitation/conv_transformer.py","papers":["2207.02518"],"paper_pages":[{"arxiv_id":"2207.02518","page":"/paper/compositional-generalization-in-grounded"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"f5efe631655adb6b","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":[-0.0,1.9809479713439941,-1.3986719846725464,-0.0,0.16777333617210388,-1.483066201210022,-0.37793970108032227,-0.3123619854450226,-2.2834079265594482,0.07322517037391663,-0.9321842193603516,-0.7474474906921387,0.9306769967079163,-0.07715094834566116,0.16865545511245728,0.5632399320602417,2.189678907394409,-0.8743484616279602,-0.07517650723457336,0.9694153070449829,-0.6315895915031433,1.3603358268737793,-0.44814202189445496,1.1743519306182861,1.0760244131088257,0.916389524936676,-0.8056327104568481,-0.2341342270374298,-1.1453824043273926,1.4899542331695557,-1.0123684406280518,2.151813507080078,-1.0635377168655396,2.1869471073150635,-1.3127033710479736,-0.0,1.110105037689209,0.811657726764679,0.04892171546816826,2.0461580753326416,-1.2312862873077393,-0.9371958374977112,-1.1161692142486572,-0.6516485214233398,1.093207597732544,-0.048707179725170135,0.43304723501205444,1.1158778667449951,-0.0,-0.15459129214286804,0.8540714979171753,-0.9998170137405396,0.5888985991477966,0.0,-0.7870998382568359,-0.9593689441680908,-1.3972541093826294,1.1737031936645508,1.8701376914978027,-0.539957582950592,2.0882015228271484,1.4898018836975098,-1.4135398864746094,-0.0],"values_recorded":64,"members":[{"code_sha256_prefix":"6ae60d8c5e429a3a","path":"model.py","papers":["2504.05956"],"paper_pages":[{"arxiv_id":"2504.05956","page":"/paper/temporal-alignment-free-video-matching-for-1"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]},{"bucket":[[1,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"a53e4536a65fa9e1","size":1,"n_papers":1,"shape":[8,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.48178955912590027,0.48178955912590027,0.48178955912590027,0.48178955912590027,0.8762869238853455,0.8762869238853455,0.8762869238853455,0.8762869238853455,0.5226739645004272,0.5226739645004272,0.5226739645004272,0.5226739645004272,-0.8525326251983643,-0.8525326251983643,-0.8525326251983643,-0.8525326251983643,-0.19375960528850555,-0.19375960528850555,-0.19375960528850555,-0.19375960528850555,0.9810490608215332,0.9810490608215332,0.9810490608215332,0.9810490608215332,-0.7727338075637817,-0.7727338075637817,-0.7727338075637817,-0.7727338075637817,-0.6347302198410034,-0.6347302198410034,-0.6347302198410034,-0.6347302198410034,0.5736269950866699,0.5736269950866699,0.5736269950866699,0.5736269950866699,-0.8191165924072266,-0.8191165924072266,-0.8191165924072266,-0.8191165924072266,0.0816468819975853,0.0816468819975853,0.0816468819975853,0.0816468819975853,0.9966613054275513,0.9966613054275513,0.9966613054275513,0.9966613054275513,0.9776174426078796,0.9776174426078796,0.9776174426078796,0.9776174426078796,-0.21039052307605743,-0.21039052307605743,-0.21039052307605743,-0.21039052307605743,0.9953981637954712,0.9953981637954712,0.9953981637954712,0.9953981637954712,0.09582564234733582,0.09582564234733582,0.09582564234733582,0.09582564234733582],"values_recorded":64,"members":[{"code_sha256_prefix":"078a37135b02e3e5","path":"model.py","papers":["2206.08545"],"paper_pages":[{"arxiv_id":"2206.08545","page":"/paper/nu-wave-2-a-general-neural-audio-upsampling"}],"arg_sig_recorded":[["noise_level",1,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]},{"bucket":[[1,"int","int64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"bea48acc7c12fc6d","size":1,"n_papers":1,"shape":[8,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.9092974066734314,-0.416146844625473,0.019998665899038315,0.9998000264167786,0.8414709568023682,0.5403022766113281,0.009999833069741726,0.9999499917030334,0.14112000167369843,-0.9899924993515015,0.029995499178767204,0.9995500445365906,0.0,1.0,0.0,1.0,0.8414709568023682,0.5403022766113281,0.009999833069741726,0.9999499917030334,0.9092974066734314,-0.416146844625473,0.019998665899038315,0.9998000264167786,0.9092974066734314,-0.416146844625473,0.019998665899038315,0.9998000264167786,0.9092974066734314,-0.416146844625473,0.019998665899038315,0.9998000264167786],"values_recorded":32,"members":[{"code_sha256_prefix":"2fd498d95c2bf66d","path":"k-edge-identification/src/ehnn/models.py","papers":["2208.10428"],"paper_pages":[{"arxiv_id":"2208.10428","page":"/paper/equivariant-hypergraph-neural-networks"}],"arg_sig_recorded":[["x",1,"int","int64"]],"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":"ac63a8474c7689b1","size":1,"n_papers":1,"shape":[4,128],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.5810841917991638,-0.9458231329917908,-0.6141840219497681,0.9693824052810669,0.47607526183128357,-0.8373255133628845,-0.915539562702179,0.73651123046875,0.994375467300415,0.21063362061977386,-0.41181614995002747,-0.7505488991737366,-0.9919478297233582,0.25125494599342346,-0.4863898456096649,-0.8499583601951599,0.9971714615821838,0.14989475905895233,-0.2964024841785431,-0.5661661624908447,-0.9333714842796326,-0.6699960231781006,0.9947627782821655,0.20335060358047485,-0.8255109190940857,0.9318138360977173,-0.6763787865638733,0.9963789582252502,0.16943126916885376,-0.3339632749557495,-0.6295782923698425,-0.9782853722572327,-0.30049076676368713,0.5732070207595825,0.9393838047981262,0.6441682577133179,-0.985427737236023,-0.33523187041282654,0.6316677927970886,0.9793872237205505,0.09558210521936417,-0.1902889758348465,-0.3736240863800049,-0.6931325793266296,-0.9992339611053467,-0.0782088190317154,0.1559385359287262,0.308061808347702,-0.8720951080322266,0.853495717048645,-0.8895129561424255,0.8128545880317688,-0.9469214081764221,0.6088044047355652,-0.9659538269042969,-0.49981239438056946,0.9738965630531311,-0.44213396310806274,0.7931432723999023,0.9661042094230652,-0.4988044202327728,0.8646420836448669,0.8687722086906433,-0.8604527115821838,0.8138434290885925,0.3246822655200958,-0.789162814617157,0.24555596709251404,-0.8794045448303223,0.5467047095298767,-0.4022279679775238,-0.6764253377914429,0.10591252148151398,-0.9775650501251221,0.9112669825553894,0.6608149409294128,-0.12664726376533508,-0.9679209589958191,0.8737419247627258,0.5268498063087463,0.0751599669456482,-0.9887019395828247,0.9550631046295166,0.8242911696434021,0.35891178250312805,-0.7423646450042725,0.10221060365438461,-0.9791060090065002,-0.5643861293792725,-0.3629366457462311,-0.736553966999054,0.08502350747585297,-0.9855419993400574,0.9425860643386841,0.7769370675086975,0.20726241171360016,-0.953784704208374,0.8194105625152588,0.3428674340248108,-0.764883816242218,0.1700945943593979,-0.9421356320381165,0.7752391695976257,0.20199163258075714,-0.9954215288162231,0.9817281365394592,0.9275802373886108,0.7208101153373718,0.03913439065217972,-0.9969369769096375,0.9877667427062988,0.9513663649559021,-0.48933637142181396,-0.521099865436554,-0.4569098949432373,-0.5824666619300842,-0.3214651048183441,-0.79332035779953,0.2587144076824188,-0.8661336898803711,-0.22699226438999176,-0.8969489932060242,0.609035074710846,-0.25815248489379883,-0.866714596748352,0.5023882985115051,-0.49521195888519287,-0.509530246257782,0.9982422590255737,-0.11832331866025925,0.23498423397541046,0.4568089544773102,0.812722384929657,0.9470672607421875,-0.608083963394165,0.9654825329780579,0.12799546122550964,-0.25388532876968384,-0.4911332130432129,-0.8556370139122009,-0.8857149481773376,0.8223499655723572,-0.9358047246932983,0.6597776412963867,-0.9483010768890381,-0.6019285321235657,0.9613400101661682,0.5294369459152222,-0.8982948660850525,-0.7894091606140137,0.9691851139068604,-0.47748568654060364,0.977035641670227,0.4163656532764435,-0.7571170330047607,-0.9892176985740662,0.28974658250808716,-0.5546348690986633,-0.9230164885520935,-0.7102802991867065,-0.7873259782791138,-0.9708310961723328,0.4655414819717407,-0.8240326642990112,-0.9336986541748047,0.6686398386955261,-0.9943830370903015,-0.21049408614635468,0.8478591442108154,0.8991063833236694,-0.7871319651603699,0.970981776714325,-0.46442747116088867,0.8226042985916138,0.9354890584945679,-0.6611207127571106,-0.9989216327667236,0.09275706112384796,-0.18471433222293854,-0.36307162046432495,-0.6765921115875244,-0.9964280128479004,-0.1682891696691513,0.3317779302597046,0.9874271750450134,-0.31217411160469055,0.5931463837623596,0.9550779461860657,0.5660838484764099,-0.9332997798919678,-0.6702924966812134,0.9948441386222839,-0.05926583707332611,-0.992975115776062,0.9719991683959961,0.8895648121833801,0.5826511383056641,-0.3210352659225464,-0.7938727140426636,0.2604677975177765,-0.9917747378349304,0.9672343134880066,0.871084451675415,0.5175763368606567,-0.4642294645309448,-0.5689820051193237,-0.35251888632774353,-0.7514608502388,0.31737205386161804,-0.7985499501228333,0.2753640115261078,-0.8483493328094482,0.4393931031227112,-0.6138674020767212,-0.24633358418941498,-0.8786395192146301,0.21307598054409027,-0.9091972708702087,0.6532793045043945,-0.1464523822069168,-0.957103431224823,0.8320938348770142,0.3847603499889374,-0.7039189338684082,0.6165369153022766,-0.23976440727710724,-0.8850260376930237,0.5665422677993774,-0.35805976390838623,-0.7435864210128784,0.10584155470132828,-0.9775951504707336,0.5302215814590454,-0.43773016333580017,-0.6167845726013184,-0.23915354907512665,-0.8856111764907837,0.5686142444610596,-0.35335564613342285,-0.7502795457839966,-0.04642859846353531,-0.995688796043396,0.9827922582626343,0.9317612648010254,0.7363579869270325,0.08444622159004211,-0.985737681388855,0.943357527256012,-0.1580744981765747,-0.9500249028205872,0.8050946593284607,0.2963548004627228,-0.8243476748466492,0.3590981960296631,-0.742097020149231,0.10141589492559433,0.20707814395427704,0.4051792025566101,0.740859866142273,0.9952113032341003,-0.1945573091506958,0.38167908787727356,0.7055680751800537,0.9999905228614807,0.9264129996299744,0.6976054310798645,-0.9996436834335327,-0.053367577493190765,0.10658305138349533,0.2119518667459488,0.4142726957798004,0.754102885723114,0.9773422479629517,0.41373831033706665,-0.7533313035964966,-0.9908434152603149,0.26755955815315247,-0.5156093835830688,-0.8835727572441101,-0.8275435566902161,-0.9568818211555481,-0.5559051632881165,0.9241875410079956,0.7059664726257324,-0.9999948143959045,-0.006445419043302536,0.012890569865703583,0.02577899768948555,-0.07092226296663284,-0.14148733019828796,-0.28012797236442566,-0.5378247499465942,-0.9068335294723511,-0.7644407153129578,0.98566073179245,-0.33263924717903137,0.5379006862640381,-0.9069094061851501,-0.7642084956169128,0.9857820272445679,-0.3312804400920868,0.6251476407051086,0.9758635759353638,0.42621999979019165,-0.9932997822761536,0.2295839637517929,-0.4469030201435089,-0.7995831370353699,-0.9603879451751709,0.5352557897567749,-0.9042505025863647,-0.772234320640564,0.05126651003956795,-0.10239819437265396,-0.2037198692560196,-0.39889541268348694,-0.7315713167190552,-0.997519314289093,0.14043720066547394,-0.27809080481529236,0.9783244132995605,0.9142372608184814,0.6716595888137817,-0.09774672985076904,-0.9808911681175232,0.9242948889732361,0.7086421251296997,0.004347402136772871,0.3765088617801666,-0.7164821624755859,0.026693301275372505,-0.9985749125480652,0.994303822517395,0.9772800803184509,0.910152792930603,0.6567562818527222,0.21166500449180603,-0.9103958606719971,0.6576412320137024,-0.135016068816185,-0.9635413289070129,0.8568238019943237,0.4682939648628235,-0.5614015460014343,0.2904774248600006,-0.8312457203865051,0.38193896412849426,-0.7082452774047852,0.0032227260526269674,-0.9999792575836182,0.9999169111251831,0.9996676445007324,0.9974818229675293,0.9899400472640991,0.9599626660346985,0.8430566191673279,0.42148900032043457,-0.6446940302848816,-0.1687392145395279,-0.9430541396141052,-0.8430082201957703,0.4213257133960724,-0.6449692845344543,-0.16802926361560822,-0.9435323476791382,0.7805065512657166,0.21838092803955078,-0.9046195149421692,-0.11556629836559296,-0.9732888340950012,0.8945823907852173,0.6005553603172302,-0.2786664664745331,-0.8446900248527527,0.4270024299621582,-0.6353378891944885,-0.9986850023269653,0.9947434663772583,0.9790292382240295,0.916996419429779,0.6817649006843567,-0.07039321959018707,-0.9900895953178406,0.9605547785758972,-0.5988794565200806,0.9592123031616211,0.5423131585121155,-0.9112774729728699,-0.7505151629447937,0.9919607639312744,-0.2510572373867035,0.4860329031944275,0.9781091213226318,0.40707480907440186,-0.7436400055885315,-0.9943660497665405,0.21080756187438965,-0.412140429019928,-0.7510190606117249,-0.9917665123939514,0.17199790477752686,-0.3388693332672119,-0.6376392245292664,-0.9823917746543884,-0.36708536744117737,0.6829162240028381,0.9977360963821411,0.13419708609580994,-0.05500766262412071,0.109848752617836,0.21836796402931213,0.4261959493160248,0.7711000442504883,0.9819403886795044,-0.3715476989746094,0.6899001002311707,0.651323139667511,-0.9884486198425293,-0.2996114194393158,0.5716953277587891,0.9381131529808044,0.649791419506073,-0.9878292679786682,-0.3072981834411621,-0.7588080167770386,0.9884451031684875,-0.2996554672718048,0.5717710852622986,0.9381771087646484,0.6495106220245361,-0.9877140522003174,-0.3087038993835449,0.8480474948883057,-0.8987950086593628,0.7880080342292786,-0.9702978730201721,0.4694557785987854,-0.8290175795555115,-0.9272106289863586,0.6945555806159973,-0.956612229347229,0.5574449896812439,-0.9255971312522888,-0.7006957530975342,0.9998370409011841,0.03609587624669075,-0.07214470207691193,-0.1439134180545807,-0.8008391857147217,0.282686710357666,-0.8401764035224915,0.4117928743362427,-0.6608532667160034,-0.1265459656715393,-0.9679722189903259,0.8739405274391174,0.20809273421764374,-0.9133948087692261,0.6685802340507507,-0.10600098967552185,-0.9775275588035583,0.9111203551292419,0.6602805256843567,-0.12805919349193573,-0.9850972890853882,0.9408334493637085,0.7703351378440857,0.1868324726819992,-0.9301872849464417,0.7304967045783997,0.06725078821182251,-0.9909546375274658,-0.9984859228134155,0.9939483404159546,0.9758664965629578,0.9046308398246765,0.636713981628418,-0.1891905665397644,-0.9284138679504395,0.7239046096801758,-0.7588005065917969,0.15155638754367828,-0.9540613293647766,0.8204659819602966,0.3463289439678192,-0.7601125240325928,0.15554215013980865,-0.9516133069992065,-0.651314377784729,-0.15157921612262726,-0.9540475010871887,0.8204132318496704,0.34615567326545715,-0.7603524923324585,0.15627190470695496,-0.9511581659317017,-0.529920220375061,-0.43836912512779236,-0.6156650185585022,-0.24191322922706604,-0.8829559683799744,0.5592225193977356,-0.3745403587818146,-0.7194390296936035,-0.2913641631603241,-0.8302138447761536,0.37851011753082275,-0.7134602069854736,0.01805087924003601,-0.9993483424186707,0.9973942041397095,0.9895902872085571],"values_recorded":512,"members":[{"code_sha256_prefix":"a043ead72fcc2e75","path":"golf/model.py","papers":["2505.19813"],"paper_pages":[{"arxiv_id":"2505.19813","page":"/paper/golf-nrt-integrating-global-context-and-local"}],"arg_sig_recorded":[["coords",2,"float","float32"]],"scalar_args":{"rays":"None"},"class_bearing":true}]}]},{"bucket":[[2,"int","int64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"a721946fbb2cedd0","size":1,"n_papers":1,"shape":[4,8,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.9092974066734314,-0.416146844625473,0.019998665899038315,0.9998000264167786,0.14112000167369843,-0.9899924993515015,0.029995501041412354,0.9995500445365906,0.9092974066734314,-0.416146844625473,0.019998665899038315,0.9998000264167786,0.8414709568023682,0.5403022766113281,0.009999833069741726,0.9999499917030334,0.8414709568023682,0.5403022766113281,0.009999833069741726,0.9999499917030334,0.14112000167369843,-0.9899924993515015,0.029995501041412354,0.9995500445365906,0.0,0.0,0.0,0.0,0.8414709568023682,0.5403022766113281,0.009999833069741726,0.9999499917030334,0.8414709568023682,0.5403022766113281,0.009999833069741726,0.9999499917030334,0.0,0.0,0.0,0.0,0.8414709568023682,0.5403022766113281,0.009999833069741726,0.9999499917030334,0.14112000167369843,-0.9899924993515015,0.029995501041412354,0.9995500445365906,0.14112000167369843,-0.9899924993515015,0.029995501041412354,0.9995500445365906,0.14112000167369843,-0.9899924993515015,0.029995501041412354,0.9995500445365906,0.14112000167369843,-0.9899924993515015,0.029995501041412354,0.9995500445365906,0.9092974066734314,-0.416146844625473,0.019998665899038315,0.9998000264167786,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.9092974066734314,-0.416146844625473,0.019998665899038315,0.9998000264167786,0.0,0.0,0.0,0.0,0.9092974066734314,-0.416146844625473,0.019998665899038315,0.9998000264167786,0.0,0.0,0.0,0.0,0.8414709568023682,0.5403022766113281,0.009999833069741726,0.9999499917030334,0.8414709568023682,0.5403022766113281,0.009999833069741726,0.9999499917030334,0.14112000167369843,-0.9899924993515015,0.029995501041412354,0.9995500445365906,0.14112000167369843,-0.9899924993515015,0.029995501041412354,0.9995500445365906,0.8414709568023682,0.5403022766113281,0.009999833069741726,0.9999499917030334,0.14112000167369843,-0.9899924993515015,0.029995501041412354,0.9995500445365906,0.14112000167369843,-0.9899924993515015,0.029995501041412354,0.9995500445365906,0.9092974066734314,-0.416146844625473,0.019998665899038315,0.9998000264167786,0.8414709568023682,0.5403022766113281,0.009999833069741726,0.9999499917030334,0.9092974066734314,-0.416146844625473,0.019998665899038315,0.9998000264167786],"values_recorded":128,"members":[{"code_sha256_prefix":"c1e9ee7b425adeaf","path":"transformer/models.py","papers":["1706.03762"],"paper_pages":[{"arxiv_id":"1706.03762","page":"/paper/attention-is-all-you-need"}],"arg_sig_recorded":[["inputs",2,"int","int64"]],"scalar_args":{},"class_bearing":true}]}]}]}