{"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-contrast","entry":"rand_contrast","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":6,"n_papers":6,"n_buckets":2,"n_distinct_outputs":3,"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-contrast","buckets":[{"bucket":[[4,"float","float32"]],"n_implementations_compared":5,"n_papers":6,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"90093f6a41d6bb16","size":3,"n_papers":4,"shape":[2,3,4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":3,"torch_reference_conventions_with_this_digest":[],"values":[0.7203453779220581,0.6505820751190186,1.4406204223632812,1.0943752527236938,1.1329858303070068,-0.1992313265800476,-0.27052319049835205,0.8288122415542603,0.3420155346393585,-0.1319407969713211,-1.186152696609497,-0.012718858197331429,-0.7064722180366516,-0.43462255597114563,-2.6557908058166504,0.8098667860031128,-0.4513891935348511,0.12500986456871033,0.5905697345733643,-1.4583792686462402,-0.722356915473938,1.1470766067504883,-0.3961152732372284,1.4281032085418701,0.22277700901031494,1.1802072525024414,-2.06038498878479,-0.1684918999671936,0.3727916181087494,0.003846774809062481,0.8918973803520203,-0.496235191822052,-0.419846773147583,1.016760230064392,-0.48191308975219727,-0.4837033152580261,-0.6594470739364624,1.9754139184951782,0.21172823011875153,-1.1995686292648315,-0.21130555868148804,-1.4739452600479126,-0.7398549318313599,1.2127729654312134,0.022565118968486786,-0.1632840931415558,0.3312802314758301,-1.2418440580368042,1.3001630306243896,0.5946768522262573,2.6567540168762207,-0.03242744132876396,2.0894320011138916,-0.8006036877632141,-3.0630621910095215,-0.2804652154445648,-1.767642855644226,-2.5533626079559326,-1.744444489479065,-0.042118851095438004,-3.5547032356262207,-0.9452224373817444,-0.8137499690055847,0.261346697807312,1.0618287324905396,-1.3919333219528198,0.9709208607673645,2.647341012954712,0.6059991121292114,0.01943521946668625,3.9284801483154297,0.08474911004304886,0.7599557042121887,0.3518292009830475,0.645557165145874,-0.8578857183456421,1.3772190809249878,0.33007681369781494,0.8311624526977539,0.29214218258857727,-2.8200206756591797,-0.11958330869674683,0.20115169882774353,-1.0723204612731934,0.9003665447235107,1.5517584085464478,-1.938077688217163,1.358351230621338,0.28101179003715515,0.5483679175376892,2.4930551052093506,-1.4907325506210327,0.6223363876342773,0.17889852821826935,-1.743209719657898,-0.370880663394928],"values_recorded":96,"members":[{"code_sha256_prefix":"cf3f99cfbe8f451a","path":"DiffAugment_pytorch.py","papers":["2006.10738","2111.01007"],"paper_pages":[{"arxiv_id":"2006.10738","page":"/paper/differentiable-augmentation-for-data"},{"arxiv_id":"2111.01007","page":"/paper/projected-gans-converge-faster"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"08cac66a8707ba68","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_08cac66a8707ba68__rand_contrast.Param object at 0xffff47"},"class_bearing":false},{"code_sha256_prefix":"b551aeb91085de7c","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_b551aeb91085de7c__rand_contrast.Param object at 0xffff4d"},"class_bearing":false}]},{"output_sha":"5e8aa6f60ddba054","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":[1.004886269569397,0.9080921411514282,2.0042409896850586,1.523838758468628,1.5774095058441162,-0.270992636680603,-0.3699074983596802,1.1553798913955688,0.4799673855304718,-0.1776295006275177,-1.6403096914291382,-0.012213466688990593,-0.9747706651687622,-0.5975893139839172,-3.6793782711029053,1.129093885421753,-0.6208524107933044,0.17888006567955017,0.824827253818512,-2.0180139541625977,-0.9968100786209106,1.5969599485397339,-0.544161856174469,1.986873984336853,0.31452837586402893,1.6429274082183838,-2.8532748222351074,-0.22834281623363495,0.5226680636405945,0.010770739056169987,1.242908239364624,-0.6830745339393616,-0.577088475227356,1.416150689125061,-0.6632031798362732,-0.6656870245933533,-0.9095250368118286,2.7462472915649414,0.29919856786727905,-1.6589237451553345,-0.2877452075481415,-2.039611339569092,-1.021087884902954,1.6881113052368164,0.036741748452186584,-0.22111718356609344,0.4650725722312927,-1.7175793647766113,1.446924090385437,0.6597859859466553,2.9605250358581543,-0.039898451417684555,2.3275418281555176,-0.8969823122024536,-3.4212944507598877,-0.31664374470710754,-1.975945234298706,-2.852602958679199,-1.9500617980957031,-0.050711531192064285,-3.9698374271392822,-1.05833899974823,-0.9116501212120056,0.2878766655921936,1.1810053586959839,-1.5567516088485718,1.0795758962631226,2.9500226974487305,0.6724186539649963,0.01796671375632286,4.379438877105713,0.0908399373292923,0.8441939353942871,0.3888314962387085,0.7165550589561462,-0.9608941078186035,1.5328985452651978,0.364561527967453,0.9236420392990112,0.32223638892173767,-3.1501235961914062,-0.1371416300535202,0.22071479260921478,-1.2001471519470215,1.000855803489685,1.727638840675354,-2.1661059856414795,1.511846899986267,0.30981776118278503,0.6081172823905945,2.7778797149658203,-1.6669857501983643,0.690646767616272,0.19588607549667358,-1.9486842155456543,-0.4175237715244293],"values_recorded":96,"members":[{"code_sha256_prefix":"22b1451f3070f9e5","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_22b1451f3070f9e5__rand_contrast.Param object at 0xffff75"},"class_bearing":false},{"code_sha256_prefix":"da0792c30cd6923d","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_da0792c30cd6923d__rand_contrast.Param object at 0xffff4a"},"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":"538ba40b39a5cdcb","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":[-1.1075530052185059,-1.1505216360092163,0.8942040205001831,1.650810956954956,-0.8811295032501221,-0.7852150201797485,0.28831759095191956,-1.028727412223816,1.6075314283370972,-1.294541597366333,-0.14203910529613495,-0.2920403480529785,-1.1547038555145264,1.2119601964950562,-1.5880024433135986,0.043085455894470215,-0.7842353582382202,-2.308398962020874,0.13186469674110413,0.343504399061203,0.1408337950706482,-0.4945174753665924,0.14857453107833862,-0.8407692909240723,-1.4071253538131714,-1.4707635641098022,0.9582769870758057,0.1777961254119873,0.37855055928230286,-1.8082995414733887,-0.641228437423706,1.229196310043335,1.0792440176010132,-0.49950650334358215,-0.3644436001777649,0.4189516007900238,-1.8381420373916626,-0.2091244012117386,-0.3956836760044098,-0.3888165354728699,-0.4870966672897339,-0.7629587650299072,-0.27841630578041077,-1.2413657903671265,0.00382116436958313,-0.4206676483154297,0.15265071392059326,-0.2553069591522217,-1.16960608959198,1.6029669046401978,-0.9571528434753418,0.016476362943649292,-0.3031845986843109,-1.0996484756469727,-0.3450697064399719,0.5292251110076904,0.6770538091659546,1.4899522066116333,0.5129700899124146,-0.32129669189453125,-1.7328282594680786,-0.7050528526306152,-1.0271375179290771,-0.7639806270599365,0.02733778953552246,-0.06668925285339355,0.23702788352966309,-0.35515040159225464,0.10249096155166626,-0.951258659362793,0.114053875207901,-0.3206554651260376,0.5454081296920776,-0.919609785079956,0.36012163758277893,1.3299376964569092,-0.9836571216583252,-2.4807417392730713,1.1948684453964233,-1.2159709930419922,0.19636180996894836,-0.8457313776016235,-0.45894014835357666,-0.5007593631744385,-0.9573007822036743,-0.21865694224834442,1.7278974056243896,0.2505699694156647,-0.4999382495880127,-0.01748540997505188,-0.17720481753349304,-0.14929679036140442,-0.10081815719604492,-0.3448587954044342,1.091387152671814,-1.0437161922454834,0.010006405413150787,0.3501155376434326,0.06342460215091705,2.7901546955108643,1.528648018836975,-0.4704301357269287,-0.21297195553779602,2.6104724407196045,0.08326181769371033,1.1256272792816162,0.5856292843818665,-1.1755375862121582,-0.6106230020523071,1.302852988243103,0.3987741768360138,2.070774555206299,1.2319484949111938,-0.6338435411453247,-0.08355429023504257,-1.5361038446426392,1.4090594053268433,0.5395886898040771,-0.8369846343994141,0.8248092532157898,0.5445820689201355,0.8973604440689087,0.6451703906059265,0.00022482872009277344,-1.5574229955673218,-0.23581168055534363,4.264537811279297,0.3132801651954651,-0.5355495810508728,-0.8672095537185669,-2.5861592292785645,-1.4843744039535522,-0.05688533931970596,0.6758223176002502,-0.27866610884666443,0.2825801372528076,-0.7767394185066223,-0.5608165264129639,1.6406246423721313,1.8334366083145142,0.21173182129859924,-1.5902655124664307,0.42788928747177124,0.7003386616706848,-2.6815125942230225,0.005019336938858032,-1.5577894449234009,-2.5271170139312744,1.31884765625,1.0030293464660645,-0.7477555871009827,-0.7174507975578308,3.41426420211792,-0.1985575258731842,-1.7695069313049316,1.6259777545928955,2.0838260650634766,-1.8882060050964355,1.1340786218643188,0.4768381118774414,-0.6122296452522278,0.8207093477249146,2.9622995853424072,-2.170269250869751,-1.3972878456115723,-2.4366588592529297,1.0562069416046143,-0.01641824096441269,0.0021523386240005493,-0.8028805255889893,-1.3810579776763916,1.0851490497589111,0.16804072260856628,-0.5058878064155579,-1.059307336807251,0.5107833743095398,2.005436658859253,1.9865933656692505,-0.16330811381340027,0.9361763000488281,-1.4989732503890991,0.41322430968284607,-0.7671818733215332,0.02063080668449402,0.35192692279815674,-1.2077157497406006,-0.4049986004829407,0.41077736020088196,-0.0002573728561401367,1.3118668794631958,-1.6135364770889282,0.7861421704292297],"values_recorded":192,"members":[{"code_sha256_prefix":"93a3d74d32b20296","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}]}]}]}