{"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-saturation","entry":"rand_saturation","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":9,"n_buckets":1,"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-saturation","buckets":[{"bucket":[[4,"float","float32"]],"n_implementations_compared":6,"n_papers":9,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"b0c029e8c1cae021","size":3,"n_papers":3,"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":[0.2908012270927429,0.6232744455337524,0.9276449680328369,0.3261220455169678,0.4552038609981537,0.4584503173828125,-0.20479582250118256,0.5647558569908142,0.21759246289730072,-0.13796667754650116,-1.270575761795044,0.1873110681772232,-0.3709426820278168,-0.30347710847854614,-1.4437928199768066,0.18509039282798767,-0.22803369164466858,0.390555202960968,0.5512492060661316,-0.8042176961898804,-0.3663274347782135,1.0545849800109863,-0.2604070007801056,0.8301172256469727,0.16479459404945374,0.4430422782897949,-1.6576790809631348,0.11833599209785461,0.1069469228386879,-0.1093263104557991,0.1270957887172699,-0.39324137568473816,-0.21406695246696472,0.7854152917861938,0.07636219263076782,-0.3726388216018677,-0.3384714722633362,1.4213662147521973,0.0087413489818573,-0.3333953022956848,-0.027413778007030487,-0.7321957349777222,-1.0729585886001587,0.7299493551254272,-0.048130642622709274,-0.18333055078983307,-0.12114107608795166,-0.7233911752700806,0.4105091989040375,0.09058938920497894,1.5111420154571533,0.2150505632162094,1.2732576131820679,-0.17214159667491913,-1.2511318922042847,0.0713953971862793,-0.7344855070114136,-1.1500343084335327,-0.42371097207069397,-0.34928956627845764,-1.4972846508026123,-0.39639174938201904,-0.5328378081321716,0.1271105259656906,0.32453179359436035,-0.6260660886764526,0.9029897451400757,1.181757926940918,0.7381197810173035,0.12368157505989075,1.271017074584961,0.2031438648700714,0.17732760310173035,-0.10200709104537964,0.43846502900123596,-0.643571674823761,0.28187111020088196,0.06366334855556488,0.06055256724357605,0.13821977376937866,-1.0758177042007446,-0.16707488894462585,0.6253010034561157,-0.16008341312408447,0.8443107008934021,0.6764562129974365,-0.8453017473220825,0.6625867486000061,0.00455203652381897,-0.031107157468795776,1.1049367189407349,-0.8718666434288025,0.009552568197250366,0.009126871824264526,-0.8681337833404541,-0.10096099972724915],"values_recorded":96,"members":[{"code_sha256_prefix":"5cb7afb924303755","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_5cb7afb924303755__rand_saturation.Param object at 0xfffe"},"class_bearing":false},{"code_sha256_prefix":"7f5ed98fe0143f9c","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_7f5ed98fe0143f9c__rand_saturation.Param object at 0xffff"},"class_bearing":false},{"code_sha256_prefix":"c464d3d7b7e65175","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_c464d3d7b7e65175__rand_saturation.ParamConfig object at "},"class_bearing":false}]},{"output_sha":"be418ff3d8ca149e","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":[0.7173134088516235,0.6526800394058228,1.4391409158706665,1.088192343711853,1.1281580924987793,-0.19110733270645142,-0.2705935835838318,0.8283993005752563,0.34166857600212097,-0.1324586570262909,-1.1916289329528809,-0.010034352540969849,-0.7045443058013916,-0.43442487716674805,-2.6493475437164307,0.8045512437820435,-0.45001840591430664,0.12908264994621277,0.5922843217849731,-1.4549702405929565,-0.7202132344245911,1.150141954421997,-0.395713746547699,1.4254385232925415,0.222878098487854,1.174759030342102,-2.0625762939453125,-0.16522201895713806,0.37066423892974854,0.002396911382675171,0.8850101232528687,-0.49664306640625,-0.41859447956085205,1.0174822807312012,-0.476168692111969,-0.48395660519599915,-0.6575398445129395,1.9753667116165161,0.20984581112861633,-1.1923599243164062,-0.2095733880996704,-1.4694205522537231,-0.7470080852508545,1.210852861404419,0.021753676235675812,-0.16410598158836365,0.32649949193000793,-1.2394503355026245,1.6465144157409668,0.8565126061439514,2.6855862140655518,-0.24999165534973145,2.031134843826294,-1.071783185005188,-3.5528476238250732,-0.4969153106212616,-2.0322370529174805,-2.8535003662109375,-2.3031630516052246,0.29285216331481934,-4.080438613891602,-1.0768284797668457,-0.7357286214828491,0.29766687750816345,1.3577736616134644,-1.5502545833587646,0.6432088017463684,2.996532678604126,0.2339644432067871,-0.07831074297428131,4.9173665046691895,-0.054460227489471436,1.0299344062805176,0.6661231517791748,0.5923103094100952,-0.6954448223114014,1.894556999206543,0.4681892991065979,1.2570735216140747,0.3349754512310028,-3.345064878463745,-0.00880962610244751,-0.28936219215393066,-1.5098161697387695,0.5905888676643372,1.7780901193618774,-2.1899352073669434,1.4885015487670898,0.4496966600418091,0.904228687286377,2.8305435180664062,-1.4621351957321167,0.9800208806991577,0.28503769636154175,-1.8617639541625977,-0.46827298402786255],"values_recorded":96,"members":[{"code_sha256_prefix":"5b0d8787e670fc63","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":"abafb0afcfb5d028","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":"3ea8887af711080e","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":[0.1415034979581833,0.6129812598228455,0.7485992908477783,0.05936446785926819,0.21964076161384583,0.6858235597610474,-0.18176375329494476,0.4724692702293396,0.1741604506969452,-0.13989470899105072,-1.298210620880127,0.2563905119895935,-0.25416767597198486,-0.25763970613479614,-1.021796464920044,-0.0317477285861969,-0.15032945573329926,0.48208189010620117,0.536885142326355,-0.5764261484146118,-0.24245205521583557,1.021135926246643,-0.21304379403591156,0.6217290759086609,0.14446283876895905,0.1869097203016281,-1.5159474611282349,0.21759358048439026,0.014634460210800171,-0.14843426644802094,-0.13820698857307434,-0.35704630613327026,-0.1424734741449356,0.7041817903518677,0.269771933555603,-0.33367276191711426,-0.22678372263908386,1.2274420261383057,-0.06165391206741333,-0.03272053599357605,0.03634996712207794,-0.474135160446167,-1.1870553493499756,0.5616123080253601,-0.07259318232536316,-0.19005998969078064,-0.2778346538543701,-0.5427480936050415,0.3264344334602356,0.03849025070667267,1.4312547445297241,0.24668335914611816,1.221705675125122,-0.11094675958156586,-1.0945661067962646,0.1100526750087738,-0.6462106704711914,-1.034162163734436,-0.29586806893348694,-0.39296892285346985,-1.3215749263763428,-0.3501075208187103,-0.5190368890762329,0.1155090481042862,0.25424924492836,-0.5632015466690063,0.9206603765487671,1.0583144426345825,0.7724131345748901,0.1374213695526123,1.0229874849319458,0.22066643834114075,0.11933213472366333,-0.15425634384155273,0.428000271320343,-0.6400431394577026,0.17217400670051575,0.03614693880081177,-0.02083638310432434,0.12483619153499603,-0.9214603900909424,-0.17784030735492706,0.6875176429748535,-0.06827276945114136,0.8615692257881165,0.6015215516090393,-0.7538379430770874,0.6064069271087646,-0.025727301836013794,-0.0947299599647522,0.9875586032867432,-0.8317157626152039,-0.056460022926330566,-0.00964096188545227,-0.8005457520484924,-0.0759759247303009],"values_recorded":96,"members":[{"code_sha256_prefix":"0d4958248aaee956","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_0d4958248aaee956__rand_saturation.Param object at 0xffff"},"class_bearing":false}]}]}]}