{"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/transpose","entry":"transpose","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":13,"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/transpose","buckets":[{"bucket":[[4,"float","float32"]],"n_implementations_compared":4,"n_papers":7,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"9922279e74e85dd5","size":3,"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":3,"torch_reference_conventions_with_this_digest":[],"values":[0.7231047749519348,1.1372957229614258,0.3433533310890198,-0.709074079990387,0.6530793309211731,-0.19992724061012268,-0.13238386809825897,-0.4362029433250427,1.4460861682891846,-0.2714869976043701,-1.1905570030212402,-2.665717124938965,1.0985400676727295,0.8319791555404663,-0.012713957577943802,0.812962532043457,-0.45303258299827576,-0.7250184416770935,0.22366678714752197,0.3742450773715973,0.12553228437900543,1.1514394283294678,1.184694528579712,0.00391392083838582,0.5928415060043335,-0.3975509703159332,-2.0680742263793945,0.895301342010498,-1.463806390762329,1.4335219860076904,-0.16907231509685516,-0.4980470836162567,-0.4213716387748718,-0.6618722677230835,-0.21204684674739838,0.022702597081661224,1.020633339881897,1.982889175415039,-1.479430913925171,-0.16384494304656982,-0.4836711883544922,0.2125764787197113,-0.7425822019577026,0.3325777053833008,-0.4854681193828583,-1.2040232419967651,1.2173826694488525,-1.246457576751709,1.0319796800613403,1.654322624206543,-1.3870023488998413,-2.796109437942505,0.47569993138313293,-0.6244865655899048,-2.00654673576355,-0.7385192513465881,2.1016592979431152,-2.408447742462158,-1.3687102794647217,-0.6348524689674377,-0.01877530850470066,-0.21435445547103882,-0.026417039334774017,0.21286723017692566,0.8440517783164978,0.4846275746822357,0.6060231924057007,1.0927388668060303,-1.0907533168792725,0.022118685767054558,0.28421318531036377,0.267061322927475,0.7723703980445862,3.1044223308563232,0.5158193111419678,0.6621701121330261,2.0942370891571045,0.0736190527677536,-0.6696537733078003,0.2371496558189392,-2.2168080806732178,0.7167379260063171,0.22837327420711517,0.49750959873199463,-0.08749820291996002,1.2303640842437744,0.4391850531101227,0.14785639941692352,0.16540314257144928,-1.5213911533355713,1.9725817441940308,-1.3677366971969604,-0.8387367129325867,1.0778614282608032,-1.1686570644378662,-0.28564757108688354],"values_recorded":96,"members":[{"code_sha256_prefix":"55f1419d4d8c483c","path":"rmi/rmi.py","papers":["1910.12037","2411.09894","2306.10008"],"paper_pages":[{"arxiv_id":"1910.12037","page":"/paper/region-mutual-information-loss-for-semantic"},{"arxiv_id":"2411.09894","page":"/paper/free-lunch-in-pathology-foundation-model-task"},{"arxiv_id":"2306.10008","page":"/paper/clip2protect-protecting-facial-privacy-using-1"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"3778d2aa87cc4d43","path":"algorithm/method_step/info_nce_loss.py","papers":["2406.04815"],"paper_pages":[{"arxiv_id":"2406.04815","page":"/paper/skill-aware-mutual-information-optimisation"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"f5c2aaad64fdace4","path":"encoder.py","papers":["2208.05962"],"paper_pages":[{"arxiv_id":"2208.05962","page":"/paper/pointtree-transformation-robust-point-cloud"}],"arg_sig_recorded":[["ans",4,"float","float32"]],"scalar_args":{"dim":"-2"},"class_bearing":false}]},{"output_sha":"a4f1f39c95af785e","size":1,"n_papers":2,"shape":[4,4,3,2],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.7231047749519348,1.0319796800613403,-0.45303258299827576,0.8440517783164978,-0.4213716387748718,-2.2168080806732178,1.1372957229614258,1.654322624206543,-0.7250184416770935,0.4846275746822357,-0.6618722677230835,0.7167379260063171,0.3433533310890198,-1.3870023488998413,0.22366678714752197,0.6060231924057007,-0.21204684674739838,0.22837327420711517,-0.709074079990387,-2.796109437942505,0.3742450773715973,1.0927388668060303,0.022702597081661224,0.49750959873199463,0.6530793309211731,0.47569993138313293,0.12553228437900543,-1.0907533168792725,1.020633339881897,-0.08749820291996002,-0.19992724061012268,-0.6244865655899048,1.1514394283294678,0.022118685767054558,1.982889175415039,1.2303640842437744,-0.13238386809825897,-2.00654673576355,1.184694528579712,0.28421318531036377,-1.479430913925171,0.4391850531101227,-0.4362029433250427,-0.7385192513465881,0.00391392083838582,0.267061322927475,-0.16384494304656982,0.14785639941692352,1.4460861682891846,2.1016592979431152,0.5928415060043335,0.7723703980445862,-0.4836711883544922,0.16540314257144928,-0.2714869976043701,-2.408447742462158,-0.3975509703159332,3.1044223308563232,0.2125764787197113,-1.5213911533355713,-1.1905570030212402,-1.3687102794647217,-2.0680742263793945,0.5158193111419678,-0.7425822019577026,1.9725817441940308,-2.665717124938965,-0.6348524689674377,0.895301342010498,0.6621701121330261,0.3325777053833008,-1.3677366971969604,1.0985400676727295,-0.01877530850470066,-1.463806390762329,2.0942370891571045,-0.4854681193828583,-0.8387367129325867,0.8319791555404663,-0.21435445547103882,1.4335219860076904,0.0736190527677536,-1.2040232419967651,1.0778614282608032,-0.012713957577943802,-0.026417039334774017,-0.16907231509685516,-0.6696537733078003,1.2173826694488525,-1.1686570644378662,0.812962532043457,0.21286723017692566,-0.4980470836162567,0.2371496558189392,-1.246457576751709,-0.28564757108688354],"values_recorded":96,"members":[{"code_sha256_prefix":"129462f7f783e0f3","path":"src/model/tmr.py","papers":["2305.00976","2510.03200"],"paper_pages":[{"arxiv_id":"2305.00976","page":"/paper/tmr-text-to-motion-retrieval-using"},{"arxiv_id":"2510.03200","page":"/paper/arxiv-2510-03200"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"]],"n_implementations_compared":2,"n_papers":6,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"601c34c933feef6a","size":2,"n_papers":6,"shape":[8,4],"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":[1.8026286363601685,0.5188759565353394,0.06639543920755386,-0.7956128120422363,-1.5337762832641602,0.9591456651687622,-1.6228755712509155,0.43327441811561584,0.47605323791503906,-0.3971995711326599,0.4321114122867584,0.9449777603149414,-0.6908870339393616,-1.5683481693267822,-0.4061858654022217,1.0175182819366455,-0.9028494954109192,-0.28853508830070496,-0.02259422466158867,-1.225785732269287,-1.0304712057113647,2.322108745574951,-1.180782437324524,1.274217963218689,-0.6627609133720398,-0.5147839784622192,-0.5368682742118835,-1.3222218751907349,0.5728892087936401,0.5505285859107971,0.983674168586731,-0.5941091179847717],"values_recorded":32,"members":[{"code_sha256_prefix":"8f1a49e9d8b29d83","path":"scripts/merge_llama_with_chinese_lora.py","papers":["2312.03414","2304.08177","2401.10334","2503.01303"],"paper_pages":[{"arxiv_id":"2312.03414","page":"/paper/compressed-context-memory-for-online-language"},{"arxiv_id":"2304.08177","page":"/paper/efficient-and-effective-text-encoding-for"},{"arxiv_id":"2401.10334","page":"/paper/drugassist-a-large-language-model-for"},{"arxiv_id":"2503.01303","page":"/paper/proper-a-progressive-learning-framework-for"}],"arg_sig_recorded":[["weight",2,"float","float32"]],"scalar_args":{"fan_in_fan_out":"True"},"class_bearing":false},{"code_sha256_prefix":"5aaa7db51b41253b","path":"sharelora/peft/tuners/lora/layer.py","papers":["2305.14314","2410.13618"],"paper_pages":[{"arxiv_id":"2305.14314","page":"/paper/qlora-efficient-finetuning-of-quantized-llms"},{"arxiv_id":"2410.13618","page":"/paper/loldu-low-rank-adaptation-via-lower-diag"}],"arg_sig_recorded":[["weight",2,"float","float32"]],"scalar_args":{"fan_in_fan_out":"True"},"class_bearing":false}]}]}]}