{"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/attention","entry":"Attention","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":12,"n_buckets":4,"n_distinct_outputs":10,"n_class_bearing":13,"not_compared":{"not_run_on_shared_input":{"n":35,"by_error":{"RuntimeError":34,"AssertionError":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/attention","buckets":[{"bucket":[[3,"float","float32"]],"n_implementations_compared":7,"n_papers":7,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"61b654db79d659bf","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":[-0.21509240567684174,0.27265363931655884,-0.16609640419483185,-0.22487223148345947,-0.053506821393966675,0.1956906020641327,0.032025039196014404,0.4698483347892761,-0.1984909176826477,0.3008524775505066,-0.15762653946876526,-0.23161156475543976,-0.04308484494686127,0.21453039348125458,0.04554623365402222,0.4885972738265991,-0.26085543632507324,0.22174927592277527,-0.16859054565429688,-0.2580450773239136,-0.08375567197799683,0.20507898926734924,0.026253432035446167,0.46665704250335693,-0.261001855134964,0.23638439178466797,-0.16440393030643463,-0.2676047384738922,-0.06099492311477661,0.21850574016571045,0.011608660221099854,0.4493352174758911,-0.381656289100647,-0.042911261320114136,-0.402044415473938,0.13668061792850494,-0.2795192301273346,-0.11287428438663483,-0.026704370975494385,0.22129960358142853,-0.31704530119895935,0.11162783950567245,-0.3423129916191101,0.042173877358436584,-0.24695707857608795,-0.12276975810527802,0.013207927346229553,0.29403403401374817,-0.29375746846199036,0.14356443285942078,-0.33560848236083984,0.043071672320365906,-0.2771379351615906,-0.15567292273044586,0.026319697499275208,0.28825831413269043,-0.23504066467285156,0.1858839988708496,-0.34958431124687195,0.06723816692829132,-0.2923144996166229,-0.22278644144535065,0.01925201714038849,0.27048367261886597],"values_recorded":64,"members":[{"code_sha256_prefix":"8598c6b96e3a0fbb","path":"models/backbone.py","papers":["2304.07193"],"paper_pages":[{"arxiv_id":"2304.07193","page":"/paper/dinov2-learning-robust-visual-features"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"b181227b8cc95f3d","path":"models/bidir_modeling_crossattn.py","papers":["2311.18825"],"paper_pages":[{"arxiv_id":"2311.18825","page":"/paper/cast-cross-attention-in-space-and-time-for-1"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"70a37b82927092cf","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":[-0.21509239077568054,0.27265363931655884,-0.16609640419483185,-0.22487223148345947,-0.053506821393966675,0.1956905871629715,0.0320250540971756,0.4698483347892761,-0.1984909176826477,0.3008524775505066,-0.15762653946876526,-0.23161157965660095,-0.04308485984802246,0.21453039348125458,0.04554623365402222,0.4885972738265991,-0.26085543632507324,0.22174927592277527,-0.16859054565429688,-0.2580450773239136,-0.08375567197799683,0.20507900416851044,0.026253432035446167,0.46665704250335693,-0.261001855134964,0.23638439178466797,-0.16440393030643463,-0.2676047384738922,-0.06099492311477661,0.21850572526454926,0.011608630418777466,0.4493352174758911,-0.381656289100647,-0.042911261320114136,-0.402044415473938,0.13668058812618256,-0.2795192003250122,-0.11287425458431244,-0.026704341173171997,0.22129961848258972,-0.31704527139663696,0.11162786930799484,-0.3423129916191101,0.0421738475561142,-0.24695709347724915,-0.12276975810527802,0.013207927346229553,0.29403403401374817,-0.29375746846199036,0.1435644030570984,-0.33560848236083984,0.043071672320365906,-0.2771379351615906,-0.15567292273044586,0.026319697499275208,0.2882583439350128,-0.23504066467285156,0.1858839988708496,-0.34958431124687195,0.06723816692829132,-0.2923145294189453,-0.22278644144535065,0.01925201714038849,0.27048367261886597],"values_recorded":64,"members":[{"code_sha256_prefix":"c3ac8c3472cc1f67","path":"sonics/models/spectttra.py","papers":["2408.14080"],"paper_pages":[{"arxiv_id":"2408.14080","page":"/paper/sonics-synthetic-or-not-identifying"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"cf18d01a00853bcb","path":"models/rfmsr.py","papers":["2607.12753"],"paper_pages":[{"arxiv_id":"2607.12753","page":"/paper/arxiv-2607-12753"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{"rope":"None"},"class_bearing":true}]},{"output_sha":"f9b2f741e78df141","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":[-0.31387531757354736,0.3756217360496521,-0.12825046479701996,-0.3143441081047058,-0.0956915095448494,0.4063319265842438,0.12560401856899261,0.48621901869773865,-0.2017882913351059,0.3517201244831085,-0.17363783717155457,-0.2568117678165436,-0.028045162558555603,0.23975634574890137,0.03311478719115257,0.5697053074836731,-0.27878156304359436,0.25406181812286377,-0.18717367947101593,-0.28944575786590576,-0.07825607061386108,0.22808793187141418,0.009296503849327564,0.5426185727119446,-0.27896231412887573,0.2721298933029175,-0.18200498819351196,-0.301247775554657,-0.0,0.24466416239738464,-0.008783489465713501,0.5212336182594299,-0.3519023358821869,0.1308767944574356,-0.3226833641529083,0.07127604633569717,-0.4318503737449646,-0.0,0.10012415796518326,0.2807275056838989,-0.3019639253616333,0.0,-0.39399659633636475,0.0,-0.228594571352005,-0.14405164122581482,-0.028249291703104973,0.29956549406051636,-0.3194013833999634,0.1575372964143753,-0.3933686912059784,0.08230333775281906,-0.3169996440410614,-0.21728481352329254,0.009378360584378242,0.32237327098846436,-0.3692323863506317,0.11477174609899521,-0.3206174671649933,-0.1698647290468216,-0.186483234167099,-0.02922043390572071,0.16602584719657898,0.3752836287021637],"values_recorded":64,"members":[{"code_sha256_prefix":"6dc45d11eb542c0c","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":[["x",3,"float","float32"]],"scalar_args":{"pos":"None","ret_attn":"False"},"class_bearing":true},{"code_sha256_prefix":"d969a5ba04920f2e","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}]},{"output_sha":"a331af7abd4a20dd","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":[-0.0,0.3029485046863556,-0.18455156683921814,-0.0,-0.05945202708244324,0.21743398904800415,0.03558339551091194,0.5220537185668945,-0.2205454707145691,0.3342805504798889,-0.1751406043767929,-0.2573462128639221,-0.04787207022309303,0.23836711049079895,0.05060692876577377,0.5428858995437622,-0.28983938694000244,0.24638809263706207,-0.18732284009456635,-0.2867167592048645,-0.09306186437606812,0.2278655767440796,0.029170481488108635,0.5185078382492065,-0.29000207781791687,0.2626493275165558,-0.18267104029655457,-0.297338604927063,-0.06777214258909225,0.24278415739536285,0.012898478657007217,0.49926137924194336,-0.4240625500679016,-0.04767918214201927,-0.4467160403728485,0.0,-0.3105769157409668,-0.1254158467054367,-0.02967149205505848,0.24588847160339355,-0.35227254033088684,0.12403097003698349,-0.3803477883338928,0.04685983434319496,-0.27439677715301514,-0.13641084730625153,0.014675475656986237,0.3267045021057129,-0.0,0.15951600670814514,-0.3728983402252197,0.047857414931058884,-0.3079310655593872,-0.0,0.029244109988212585,0.3202870786190033,-0.2611563205718994,0.20653778314590454,-0.3884270191192627,0.07470908015966415,-0.3247939348220825,-0.24754050374031067,0.0213911309838295,0.0],"values_recorded":64,"members":[{"code_sha256_prefix":"f9763b6132534e57","path":"models/early_exit.py","papers":["2410.09633"],"paper_pages":[{"arxiv_id":"2410.09633","page":"/paper/duodiff-accelerating-diffusion-models-with-a"}],"arg_sig_recorded":[["x",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]},{"bucket":[[3,"float","float32"],[3,"float","float32"],[3,"float","float32"]],"n_implementations_compared":4,"n_papers":3,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"2626132f91926ebf","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":[-0.0,1.4899859428405762,-1.2846678495407104,-0.0,0.2356245219707489,-1.2000970840454102,-0.3115166127681732,-0.1546124368906021,-1.8962385654449463,0.4437248110771179,-1.0282154083251953,-0.694729208946228,0.6685923337936401,-0.4178890585899353,-0.0012174085713922977,0.32861748337745667,1.7128777503967285,-0.24001389741897583,-0.3388213515281677,0.4744797945022583,-0.7674230933189392,1.2503845691680908,-0.611699640750885,1.3382700681686401,1.1353681087493896,0.7008253931999207,-0.7223013043403625,-0.13473448157310486,-0.9906726479530334,1.2577701807022095,-0.8774322271347046,1.781146764755249,-1.0910913944244385,1.7953671216964722,-1.1044807434082031,-0.0,1.1539946794509888,0.6715097427368164,-0.01358032412827015,1.6785892248153687,-1.1887363195419312,0.09642539173364639,-0.8426810503005981,-0.8164846897125244,1.127777099609375,0.215151846408844,0.11297145485877991,0.9919331073760986,-0.0,0.7202776074409485,1.0838851928710938,-0.8123161196708679,1.4840954542160034,0.0,-0.9762108325958252,-0.643273651599884,-1.3544634580612183,1.219143033027649,1.696317195892334,-0.6748347878456116,1.983585238456726,1.296323299407959,-1.3374779224395752,-0.0],"values_recorded":64,"members":[{"code_sha256_prefix":"6f534d51aff2ec87","path":"src/nlp/layers/encoder.py","papers":["1706.03762"],"paper_pages":[{"arxiv_id":"1706.03762","page":"/paper/attention-is-all-you-need"}],"arg_sig_recorded":[["q",3,"float","float32"],["k",3,"float","float32"],["v",3,"float","float32"]],"scalar_args":{"mask":"None"},"class_bearing":true}]},{"output_sha":"5a2eda2611f0e323","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":[-1.0037922859191895,1.3409870862960815,-1.1562007665634155,-0.33927446603775024,0.21206198632717133,-1.0800870656967163,-0.28036487102508545,-0.13915103673934937,-1.7066144943237305,0.39935237169265747,-0.92539381980896,-0.6252561807632446,0.6017330884933472,-0.3761001527309418,-0.0010956935584545135,0.2957557141780853,1.5415898561477661,-0.2160124033689499,-0.30493927001953125,0.4270317852497101,-0.6906808018684387,1.125346064567566,-0.5505297183990479,1.204443097114563,1.0218312740325928,0.6307428479194641,-0.6500711441040039,-0.12126103788614273,-0.8916052579879761,1.131993055343628,-0.7896889448165894,1.6030319929122925,-0.9819822907447815,1.6158301830291748,-0.9940325617790222,-0.7865397334098816,1.0385953187942505,0.6043587327003479,-0.012222315184772015,1.510730266571045,-1.0698626041412354,0.08678285032510757,-0.7584128975868225,-0.7348361611366272,1.0149993896484375,0.19363665580749512,0.10167430341243744,0.8927397727966309,-0.9612483382225037,0.6482497453689575,0.9754964709281921,-0.7310845255851746,1.3356858491897583,0.766312301158905,-0.8785896301269531,-0.5789461731910706,-1.2190170288085938,1.0972286462783813,1.526685357093811,-0.6073513031005859,1.7852264642715454,1.1666909456253052,-1.2037301063537598,-0.7931501865386963],"values_recorded":64,"members":[{"code_sha256_prefix":"a08f05b65312af52","path":"lightglue/lightglue.py","papers":["2306.13643"],"paper_pages":[{"arxiv_id":"2306.13643","page":"/paper/lightglue-local-feature-matching-at-light"}],"arg_sig_recorded":[["q",3,"float","float32"],["k",3,"float","float32"],["v",3,"float","float32"]],"scalar_args":{"mask":"None"},"class_bearing":true}]},{"output_sha":"e5a7b22e38a66304","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":[-0.45955872535705566,-0.618600070476532,0.3968018591403961,-0.10914910584688187,0.1620553433895111,-0.09815052151679993,-0.01054982841014862,-0.11756294220685959,-0.44747546315193176,-0.5558622479438782,0.38291770219802856,-0.0953177735209465,0.19701814651489258,-0.04624223709106445,-0.027053870260715485,-0.12913700938224792,-0.4540401101112366,-0.6210067272186279,0.379155695438385,-0.11641372740268707,0.1381930410861969,-0.09511913359165192,-0.0049454569816589355,-0.11424965411424637,-0.4393197298049927,-0.633393406867981,0.32110559940338135,-0.10056879371404648,0.1531306505203247,-0.14360573887825012,-0.0563836470246315,-0.08060108870267868,-0.2886436879634857,-0.7072979211807251,-0.26738590002059937,-0.012554213404655457,0.1854352355003357,0.02395346760749817,-0.42354339361190796,0.04530465602874756,-0.27062755823135376,-0.6718648076057434,-0.257840633392334,0.013644993305206299,0.2529507875442505,0.06685367226600647,-0.44518759846687317,0.03208905830979347,-0.30078956484794617,-0.643012285232544,-0.157051682472229,-0.0352935791015625,0.16115683317184448,0.08493471145629883,-0.31931430101394653,-0.011643551290035248,-0.3424142599105835,-0.5554158091545105,0.031739622354507446,-0.09679622948169708,0.05742461234331131,0.09980052709579468,-0.12179840356111526,-0.08429282158613205],"values_recorded":64,"members":[{"code_sha256_prefix":"8d12ff40c5428f95","path":"TRANSFORMERS.py","papers":["1706.03762"],"paper_pages":[{"arxiv_id":"1706.03762","page":"/paper/attention-is-all-you-need"}],"arg_sig_recorded":[["query",3,"float","float32"],["key",3,"float","float32"],["value",3,"float","float32"]],"scalar_args":{"mask":"None"},"class_bearing":true}]},{"output_sha":"f1e879c2058dc97c","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":[0.2403973788022995,-0.0802590548992157,-0.20528855919837952,0.05419182777404785,-0.2920725345611572,0.6059292554855347,-0.41717204451560974,-0.009299322962760925,0.3049015998840332,-0.0616350919008255,-0.2653224766254425,0.07345864176750183,-0.24996031820774078,0.6187258362770081,-0.41545602679252625,0.11365693807601929,0.36760762333869934,-0.04780752956867218,-0.32353225350379944,-0.016383886337280273,-0.23996464908123016,0.647084653377533,-0.4004666805267334,0.12314118444919586,0.2664025127887726,-0.07335162162780762,-0.2244851142168045,0.15064933896064758,-0.22135065495967865,0.5932337641716003,-0.3984135389328003,0.1537940800189972,-0.779963493347168,-0.22800418734550476,-0.1880931556224823,0.6722904443740845,0.019690178334712982,0.042101651430130005,-0.130692258477211,-0.2761324346065521,-0.45753857493400574,-0.19429266452789307,-0.15875458717346191,0.5185954570770264,-0.042120642960071564,0.17014820873737335,-0.20949849486351013,-0.13826137781143188,-0.3505540192127228,-0.21095286309719086,-0.12087175250053406,0.5262749195098877,-0.016870401799678802,0.15104474127292633,-0.22411316633224487,-0.03558292239904404,-0.33704903721809387,-0.2509898245334625,-0.10728009045124054,0.5537426471710205,0.0069208405911922455,0.10842011868953705,-0.20152990520000458,-0.01888224482536316],"values_recorded":64,"members":[{"code_sha256_prefix":"e843618eb9a8862f","path":"network/models/d2ls.py","papers":["2503.06683"],"paper_pages":[{"arxiv_id":"2503.06683","page":"/paper/dynamic-dictionary-learning-for-remote"}],"arg_sig_recorded":[["q",3,"float","float32"],["k",3,"float","float32"],["v",3,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]},{"bucket":[[3,"float","float32"],[3,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"61b654db79d659bf","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":[-0.21509240567684174,0.27265363931655884,-0.16609640419483185,-0.22487223148345947,-0.053506821393966675,0.1956906020641327,0.032025039196014404,0.4698483347892761,-0.1984909176826477,0.3008524775505066,-0.15762653946876526,-0.23161156475543976,-0.04308484494686127,0.21453039348125458,0.04554623365402222,0.4885972738265991,-0.26085543632507324,0.22174927592277527,-0.16859054565429688,-0.2580450773239136,-0.08375567197799683,0.20507898926734924,0.026253432035446167,0.46665704250335693,-0.261001855134964,0.23638439178466797,-0.16440393030643463,-0.2676047384738922,-0.06099492311477661,0.21850574016571045,0.011608660221099854,0.4493352174758911,-0.381656289100647,-0.042911261320114136,-0.402044415473938,0.13668061792850494,-0.2795192301273346,-0.11287428438663483,-0.026704370975494385,0.22129960358142853,-0.31704530119895935,0.11162783950567245,-0.3423129916191101,0.042173877358436584,-0.24695707857608795,-0.12276975810527802,0.013207927346229553,0.29403403401374817,-0.29375746846199036,0.14356443285942078,-0.33560848236083984,0.043071672320365906,-0.2771379351615906,-0.15567292273044586,0.026319697499275208,0.28825831413269043,-0.23504066467285156,0.1858839988708496,-0.34958431124687195,0.06723816692829132,-0.2923144996166229,-0.22278644144535065,0.01925201714038849,0.27048367261886597],"values_recorded":64,"members":[{"code_sha256_prefix":"d252bbacc051912d","path":"models/hd_former.py","papers":["2302.01825"],"paper_pages":[{"arxiv_id":"2302.01825","page":"/paper/hdformer-high-order-directed-transformer-for"}],"arg_sig_recorded":[["fv",3,"float","float32"],["fe",3,"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":"859fd91fbb1ad680","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":[0.1935724914073944,-0.22407931089401245,0.12915846705436707,0.10446887463331223,0.15550518035888672,-0.19887800514698029,0.179483100771904,0.12538214027881622,0.1180102676153183,-0.1748937964439392,0.22857899963855743,0.14896292984485626,0.10018360614776611,-0.17563578486442566,0.2401057481765747,0.15031050145626068,0.1034134030342102,0.01609523594379425,0.06238636374473572,0.16607795655727386,0.13560736179351807,-0.00785084068775177,-0.02289024367928505,0.16830343008041382,0.16251225769519806,0.06558145582675934,0.002710839733481407,0.13549675047397614,0.11394031345844269,0.025938957929611206,0.035729121416807175,0.14739549160003662,0.1420058161020279,0.11277104914188385,-0.01690012961626053,0.15091609954833984,0.12392626702785492,0.14696353673934937,-0.022833172231912613,0.13406246900558472,0.23061230778694153,-0.029552310705184937,0.021528862416744232,0.20114001631736755,0.1537814736366272,0.08692267537117004,0.02218802087008953,0.14542846381664276,0.10218800604343414,0.13078635931015015,0.14192840456962585,0.14798924326896667,0.27345359325408936,0.010127566754817963,0.2126057893037796,0.11874482035636902,0.5014634728431702,-0.11472351849079132,0.0029387958347797394,0.20649263262748718,0.5492746233940125,-0.1548326462507248,-0.015368178486824036,0.1785026490688324,0.6163660287857056,-0.38403207063674927,-0.183649480342865,-0.01466892659664154,0.6056263446807861,-0.32542020082473755,-0.20519748330116272,-0.04643280804157257,0.5875751972198486,-0.28917306661605835,-0.17361339926719666,-0.018239349126815796,0.5947743654251099,-0.2936455011367798,-0.18436944484710693,-0.034889429807662964,0.14021186530590057,-0.003504522144794464,0.05601123720407486,0.1619461327791214,0.2783380448818207,0.03064102679491043,-0.04518140107393265,0.06884639710187912,0.1294838935136795,0.08877423405647278,0.005575778894126415,0.166768416762352,0.21588756144046783,0.03883594274520874,-0.0033077578991651535,0.11697382479906082],"values_recorded":96,"members":[{"code_sha256_prefix":"cc958048d557e1e9","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",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]}]}