{"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/rand-brightness","entry":"rand_brightness","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":7,"n_papers":9,"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/rand-brightness","buckets":[{"bucket":[[4,"float","float32"]],"n_implementations_compared":6,"n_papers":9,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"536312369585b433","size":2,"n_papers":5,"shape":[2,3,4,4],"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":[0.7193613648414612,0.6493359208106995,1.442342758178711,1.0947966575622559,1.1335523128509521,-0.2036706507205963,-0.27523040771484375,0.8282357454299927,0.33960992097854614,-0.1361272782087326,-1.1943004131317139,-0.016457367688417435,-0.7128174901008606,-0.43994635343551636,-2.6694605350494385,0.8092191219329834,-0.4567759931087494,0.1217888742685318,0.5890980958938599,-1.4675498008728027,-0.7287618517875671,1.1476960182189941,-0.40129438042640686,1.4297785758972168,0.21992337703704834,1.1809511184692383,-2.071817636489868,-0.1728157252073288,0.37050166726112366,0.00017051072791218758,0.8915579319000244,-0.5017905235290527,-0.42511504888534546,1.0168899297714233,-0.4874145984649658,-0.4892115294933319,-0.6656156778335571,1.9791457653045654,0.20883306860923767,-1.2077666521072388,-0.215790256857872,-1.4831743240356445,-0.7463256120681763,1.213639259338379,0.01895918697118759,-0.16758835315704346,0.32883429527282715,-1.2502009868621826,1.300201416015625,0.7439217567443848,2.3698811531066895,0.24944648146629333,1.9225444793701172,-0.35626477003097534,-2.140225887298584,0.053867340087890625,-1.1187806129455566,-1.7383248805999756,-1.1004884243011475,0.24180474877357483,-2.5278875827789307,-0.4702974557876587,-0.3666306734085083,0.4810890257358551,1.1122735738754272,-0.822531521320343,1.0405921936035156,2.3624589443206787,0.7528493404388428,0.29034048318862915,3.3726441860198975,0.34184086322784424,0.8742449879646301,0.5524349808692932,0.7840411067008972,-0.40143197774887085,1.3609607219696045,0.535283088684082,0.9303919076919556,0.5053714513778687,-1.9485862255096436,0.18072359263896942,0.43362492322921753,-0.5705149173736572,0.9849597215652466,1.4985859394073486,-1.253169298171997,1.346083164215088,0.4965950846672058,0.7074068784713745,2.2408034801483154,-0.9004352688789368,0.7657313942909241,0.41607820987701416,-1.0995149612426758,-0.0174257755279541],"values_recorded":96,"members":[{"code_sha256_prefix":"011230b2b9b8fb6f","path":"src/utils/diffaug.py","papers":["2111.01007","2111.01118","2104.03310","2609.15120"],"paper_pages":[{"arxiv_id":"2111.01007","page":"/paper/projected-gans-converge-faster"},{"arxiv_id":"2111.01118","page":"/paper/rebooting-acgan-auxiliary-classifier-gans"},{"arxiv_id":"2104.03310","page":"/paper/regularizing-generative-adversarial-networks"},{"arxiv_id":"2609.15120","page":"/paper/arxiv-2609-15120"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"fd66a45971195f9a","path":"DiffAugment_pytorch.py","papers":["2006.10738","2111.01118"],"paper_pages":[{"arxiv_id":"2006.10738","page":"/paper/differentiable-augmentation-for-data"},{"arxiv_id":"2111.01118","page":"/paper/rebooting-acgan-auxiliary-classifier-gans"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"baa10f0e43eaf5a7","size":2,"n_papers":2,"shape":[2,3,4,4],"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":[0.7223560810089111,0.6523306369781494,1.4453375339508057,1.0977914333343506,1.1365470886230469,-0.20067591965198517,-0.2722356915473938,0.8312304615974426,0.3426046371459961,-0.13313254714012146,-1.1913056373596191,-0.013462639413774014,-0.7098227739334106,-0.4369516372680664,-2.6664657592773438,0.8122138381004333,-0.45378127694129944,0.12478360533714294,0.5920928120613098,-1.464555025100708,-0.7257671356201172,1.1506907939910889,-0.3982996642589569,1.4327733516693115,0.22291810810565948,1.183945894241333,-2.0688228607177734,-0.16982099413871765,0.3734963834285736,0.003165238769724965,0.8945526480674744,-0.4987957775592804,-0.4221203327178955,1.019884705543518,-0.48441988229751587,-0.48621681332588196,-0.6626209616661072,1.9821405410766602,0.21182779967784882,-1.204771876335144,-0.21279552578926086,-1.4801795482635498,-0.7433308959007263,1.2166340351104736,0.021953914314508438,-0.1645936220884323,0.3318290114402771,-1.247206211090088,1.0856239795684814,0.5293443202972412,2.155303716659546,0.03486905246973038,1.7079670429229736,-0.5708422064781189,-2.3548033237457275,-0.16071009635925293,-1.3333580493927002,-1.9529023170471191,-1.315065860748291,0.02722731977701187,-2.742465019226074,-0.6848748922348022,-0.5812081098556519,0.26651158928871155,0.8976961374282837,-1.0371088981628418,0.8260147571563721,2.147881507873535,0.5382719039916992,0.0757630467414856,3.158066749572754,0.1272634118795395,0.6596675515174866,0.33785754442214966,0.5694636702537537,-0.6160094141960144,1.146383285522461,0.32070568203926086,0.715814471244812,0.2907940149307251,-2.163163661956787,-0.03385384380817413,0.21904750168323517,-0.7850923538208008,0.770382285118103,1.284008502960205,-1.4677467346191406,1.1315057277679443,0.28201764822006226,0.49282941222190857,2.026226043701172,-1.1150126457214355,0.5511539578437805,0.2015007585287094,-1.3140923976898193,-0.23200321197509766],"values_recorded":96,"members":[{"code_sha256_prefix":"1cad5517390bb5b5","path":"main_DataDAM.py","papers":["2310.00093"],"paper_pages":[{"arxiv_id":"2310.00093","page":"/paper/datadam-efficient-dataset-distillation-with-1"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"param":"<fx_1cad5517390bb5b5__rand_brightness.Param object at 0xffff"},"class_bearing":false},{"code_sha256_prefix":"2381e0ea15f245ea","path":"distill.py","papers":["2203.01531"],"paper_pages":[{"arxiv_id":"2203.01531","page":"/paper/cafe-learning-to-condense-dataset-by-aligning"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"param":"<fx_2381e0ea15f245ea__rand_brightness.Param object at 0xffff"},"class_bearing":false}]},{"output_sha":"88afd26e1e13abc3","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":[0.837785542011261,0.7677600979804993,1.5607669353485107,1.2132208347320557,1.251976490020752,-0.08524645864963531,-0.15680621564388275,0.9466599225997925,0.45803409814834595,-0.017703086137771606,-1.075876235961914,0.10196682810783386,-0.5943933129310608,-0.32152217626571655,-2.5510363578796387,0.9276432991027832,-0.3383517861366272,0.2402130663394928,0.7075222730636597,-1.349125623703003,-0.6103376746177673,1.266120195388794,-0.28287017345428467,1.5482027530670166,0.33834755420684814,1.299375295639038,-1.9533934593200684,-0.0543915331363678,0.48892587423324585,0.1185947060585022,1.0099821090698242,-0.38336628675460815,-0.30669087171554565,1.1353141069412231,-0.368990421295166,-0.3707873225212097,-0.5471915006637573,2.0975699424743652,0.32725727558135986,-1.089342474937439,-0.09736606478691101,-1.3647501468658447,-0.6279014348983765,1.3320634365081787,0.137383371591568,-0.04916416108608246,0.44725847244262695,-1.1317768096923828,1.1564809083938599,0.6002011299133301,2.2261605262756348,0.10572588443756104,1.7788238525390625,-0.49998536705970764,-2.2839465141296387,-0.08985326439142227,-1.2625011205673218,-1.8820455074310303,-1.2442090511322021,0.09808415174484253,-2.6716082096099854,-0.6140180826187134,-0.510351300239563,0.3373684287071228,0.9685529470443726,-0.9662521481513977,0.8968715667724609,2.218738317489624,0.6091287732124329,0.14661987125873566,3.2289235591888428,0.19812023639678955,0.7305243611335754,0.4087143838405609,0.6403204798698425,-0.5451526045799255,1.2172400951385498,0.3915625214576721,0.7866712808609009,0.36165085434913635,-2.0923068523406982,0.037002988159656525,0.28990432620048523,-0.7142355442047119,0.8412390947341919,1.354865312576294,-1.3968899250030518,1.2023626565933228,0.3528744578361511,0.5636862516403198,2.0970828533172607,-1.0441558361053467,0.6220107674598694,0.2723575830459595,-1.243235468864441,-0.1611463725566864],"values_recorded":96,"members":[{"code_sha256_prefix":"bbcf3d37a05e74fa","path":"main_run.py","papers":["2605.13475"],"paper_pages":[{"arxiv_id":"2605.13475","page":"/paper/arxiv-2605-13475"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"param":"<fx_bbcf3d37a05e74fa__rand_brightness.ParamConfig object at "},"class_bearing":false}]},{"output_sha":"d7a8dd70b7b92858","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":[0.837785542011261,0.7677600979804993,1.5607669353485107,1.2132208347320557,1.251976490020752,-0.08524645864963531,-0.15680621564388275,0.9466599225997925,0.45803409814834595,-0.017703086137771606,-1.075876235961914,0.10196682810783386,-0.5943933129310608,-0.32152217626571655,-2.5510363578796387,0.9276432991027832,-0.3383517861366272,0.2402130663394928,0.7075222730636597,-1.349125623703003,-0.6103376746177673,1.266120195388794,-0.28287017345428467,1.5482027530670166,0.33834755420684814,1.299375295639038,-1.9533934593200684,-0.0543915331363678,0.48892587423324585,0.1185947060585022,1.0099821090698242,-0.38336628675460815,-0.30669087171554565,1.1353141069412231,-0.368990421295166,-0.3707873225212097,-0.5471915006637573,2.0975699424743652,0.32725727558135986,-1.089342474937439,-0.09736606478691101,-1.3647501468658447,-0.6279014348983765,1.3320634365081787,0.137383371591568,-0.04916416108608246,0.44725847244262695,-1.1317768096923828,1.1466604471206665,0.5903807282447815,2.2163400650024414,0.09590547531843185,1.7690033912658691,-0.5098057985305786,-2.293766975402832,-0.09967367351055145,-1.2723215818405151,-1.8918659687042236,-1.2540295124053955,0.08826374262571335,-2.6814286708831787,-0.623838484287262,-0.5201717019081116,0.3275480270385742,0.958732545375824,-0.9760725498199463,0.8870511651039124,2.2089178562164307,0.5993083715438843,0.13679946959018707,3.2191030979156494,0.18829983472824097,0.7207039594650269,0.39889395236968994,0.630500078201294,-0.5549730062484741,1.2074196338653564,0.38174211978912354,0.7768508791923523,0.3518304228782654,-2.1021273136138916,0.027182579040527344,0.28008392453193665,-0.7240559458732605,0.8314186930656433,1.3450448513031006,-1.4067103862762451,1.1925421953201294,0.34305405616760254,0.5538658499717712,2.0872626304626465,-1.05397629737854,0.6121903657913208,0.2625371813774109,-1.2530559301376343,-0.17096678912639618],"values_recorded":96,"members":[{"code_sha256_prefix":"ff7b23be3efb6c10","path":"distill.py","papers":["2406.18561"],"paper_pages":[{"arxiv_id":"2406.18561","page":"/paper/selmatch-effectively-scaling-up-dataset"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"param":"<fx_ff7b23be3efb6c10__rand_brightness.Param object at 0xffff"},"class_bearing":false}]}]},{"bucket":[[5,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"754faf4b7d3479b5","size":1,"n_papers":1,"shape":[2,2,3,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-1.1126277446746826,-1.1557577848434448,0.8966507911682129,1.6561006307601929,-0.8853535056114197,-0.7890786528587341,0.2884877622127533,-1.0335060358047485,1.6126585006713867,-1.300318956375122,-0.14348599314689636,-0.2940508723258972,-1.1599557399749756,1.2156009674072266,-1.5948824882507324,0.04233415424823761,-0.788095235824585,-2.317986011505127,0.13144700229167938,0.3438819646835327,0.14044979214668274,-0.4972887933254242,0.14821960031986237,-0.8448415994644165,-1.4133257865905762,-1.477203130722046,0.9609645009040833,0.1775510013103485,0.37905973196029663,-1.816007375717163,-0.6445510387420654,1.2329018115997314,1.0823860168457031,-0.5022965669631958,-0.3667261600494385,0.4196126163005829,-1.8459620475769043,-0.21082335710525513,-0.3980836272239685,-0.39119067788124084,-0.4898400902748108,-0.7667388319969177,-0.2803756296634674,-1.2469433546066284,0.0029223538003861904,-0.42316147685050964,0.15231113135814667,-0.2571794390678406,-1.174914002418518,1.608076810836792,-0.9616624712944031,0.015625104308128357,-0.3052369952201843,-1.1046935319900513,-0.34727945923805237,0.530300498008728,0.6786847114562988,1.4946374893188477,0.5139844417572021,-0.32341712713241577,-1.7402524948120117,-0.708615243434906,-1.0319100618362427,-0.7677645087242126,0.026527337729930878,-0.06785301864147186,0.2370053082704544,-0.35739803314208984,0.10196290165185928,-0.9557461738586426,0.11356925219297409,-0.3227735161781311,0.5465442538261414,-0.923978328704834,0.3605616092681885,1.3340216875076294,-0.9882663488388062,-2.490976333618164,1.1984449625015259,-1.221453070640564,0.19618645310401917,-0.8498223423957825,-0.46157777309417725,-0.5035541653633118,-0.9618109464645386,-0.22039172053337097,1.7334767580032349,0.250598281621933,-0.5027299523353577,-0.018464304506778717,-0.1787838339805603,-0.15077094733715057,-0.10211016237735748,-0.34706777334213257,1.0945748090744019,-1.048551082611084,0.16631606221199036,0.4344940185546875,0.20843660831451416,2.358478546142578,1.3637734651565552,-0.2125108540058136,-0.009503647685050964,2.2167980670928955,0.22407835721969604,1.0459893941879272,0.6201978921890259,-0.7684919834136963,-0.3230537176132202,1.1857328414916992,0.4728616178035736,1.791243314743042,1.129824161529541,-0.34136325120925903,0.09254293143749237,-1.0528004169464111,1.269477128982544,0.583894670009613,-0.5015411376953125,0.8087925910949707,0.587831974029541,0.865999698638916,0.6671464443206787,0.1586032211780548,-1.0696107149124146,-0.02751287817955017,3.5210378170013428,0.40544912219047546,-0.2638578712940216,-0.5253735780715942,-1.880774974822998,-1.0120115280151367,0.11357154697179794,0.6913156509399414,-0.06130383908748627,0.38124197721481323,-0.4540373980998993,-0.2837810516357422,1.4520676136016846,1.6041009426116943,0.3253776729106903,-1.095507264137268,0.4958190321922302,0.7106468677520752,-1.9559617042541504,0.16238372027873993,-1.0698996782302856,-1.834220051765442,1.1983447074890137,0.9493201971054077,-0.43118348717689514,-0.40728798508644104,2.8505923748016357,0.0018622130155563354,-1.2368401288986206,1.4405184984207153,1.8015345335006714,-1.330435037612915,1.0526533126831055,0.5344154834747314,-0.32432055473327637,0.8055598735809326,2.494215726852417,-1.5528433322906494,-0.9433432817459106,-1.7628933191299438,0.9912511110305786,0.14548006653785706,0.1601230800151825,-0.4746498167514801,-0.9305459260940552,1.014072060585022,0.290926992893219,-0.24046939611434937,-0.6768437623977661,0.5611814856529236,1.7397239208221436,1.7248659133911133,0.029656581580638885,0.8966062068939209,-1.0235227346420288,0.4842556118965149,-0.446501225233078,0.17469346523284912,0.4359222948551178,-0.7938647270202637,-0.16091769933700562,0.4823261797428131,0.1582230180501938,1.192840337753296,-1.113856554031372,0.7783033847808838],"values_recorded":192,"members":[{"code_sha256_prefix":"0054342024c45e46","path":"diff_augment.py","papers":["2006.10738"],"paper_pages":[{"arxiv_id":"2006.10738","page":"/paper/differentiable-augmentation-for-data"}],"arg_sig_recorded":[["x",5,"float","float32"]],"scalar_args":{"scale":"0.5"},"class_bearing":false}]}]}]}