{"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/quat2mat","entry":"quat2mat","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":5,"n_papers":5,"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/quat2mat","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":4,"n_papers":4,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"eb09c2471865b1ef","size":3,"n_papers":3,"shape":[4,3,3],"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":[0.5472395420074463,0.11513590812683105,0.42854470014572144,-0.44145113229751587,0.07220964133739471,0.5443204045295715,0.045030415058135986,-0.6913085579872131,0.12822939455509186,-0.14500118792057037,0.08787757903337479,-0.3472764790058136,-0.2425839602947235,-0.29975801706314087,0.02543492615222931,-0.26358386874198914,0.22753338515758514,0.16763316094875336,0.4053630530834198,-0.23909273743629456,0.2439097762107849,-0.25821810960769653,-0.4623013436794281,-0.024028625339269638,0.22356370091438293,-0.10044218599796295,-0.47000762820243835,-0.1388583928346634,0.30564525723457336,-0.07797227799892426,-0.10032404214143753,0.03797575831413269,0.3275260031223297,0.2990548014640808,0.1546582281589508,0.0736708790063858],"values_recorded":36,"members":[{"code_sha256_prefix":"918a33896f8c5b03","path":"main/model.py","papers":["2402.17062"],"paper_pages":[{"arxiv_id":"2402.17062","page":"/paper/hoisdf-constraining-3d-hand-object-pose"}],"arg_sig_recorded":[["quat",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"baa1c1737c3796df","path":"event_pose_estimation/model.py","papers":["2108.06819"],"paper_pages":[{"arxiv_id":"2108.06819","page":"/paper/eventhpe-event-based-3d-human-pose-and-shape"}],"arg_sig_recorded":[["quat",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"bec37e39340a8433","path":"PIANOLayer.py","papers":["2106.10893"],"paper_pages":[{"arxiv_id":"2106.10893","page":"/paper/piano-a-parametric-hand-bone-model-from"}],"arg_sig_recorded":[["quat",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"3b61bd3bff45dada","size":1,"n_papers":1,"shape":[4,3,3],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.16787077486515045,-0.6514105200767517,-0.13580001890659332,-0.4600391089916229,-0.012424370273947716,-0.5090849995613098,0.48077160120010376,0.2155640721321106,-0.43971434235572815,0.017649848014116287,0.16495126485824585,0.13880817592144012,0.018520958721637726,0.13759751617908478,-0.16586756706237793,-0.2147873491048813,0.02541957050561905,-0.0028962669894099236,-0.2734813988208771,-0.16259852051734924,-0.4801444411277771,0.09769227355718613,0.5184289216995239,-0.23120708763599396,0.4974265694618225,-0.1912124902009964,-0.21857181191444397,0.06152641028165817,-0.28735047578811646,-0.0709771141409874,0.13374055922031403,-0.03768252581357956,0.2684902548789978,-0.2640482783317566,-0.08604229986667633,0.11945190280675888],"values_recorded":36,"members":[{"code_sha256_prefix":"076cd329bededdb1","path":"rigid_warp.py","papers":["2102.02629"],"paper_pages":[{"arxiv_id":"2102.02629","page":"/paper/learning-monocular-depth-in-dynamic-scenes"}],"arg_sig_recorded":[["quat",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[3,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"2487a726d552d7af","size":1,"n_papers":1,"shape":[2,4,3,3],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.25952428579330444,-0.6162733435630798,0.1809602826833725,-0.4952690005302429,-0.0677402913570404,0.4795958399772644,-0.40895968675613403,-0.3090481162071228,-0.46597588062286377,0.4785722494125366,-0.4880587160587311,0.5306185483932495,0.48213908076286316,0.6901757717132568,0.19997023046016693,-0.5360029935836792,0.18505369126796722,0.653639554977417,0.4727512300014496,-0.37764716148376465,-0.2014356255531311,0.4130780100822449,0.323981374502182,0.36206358671188354,-0.11207243800163269,-0.39888107776641846,0.48478975892066956,0.11913009732961655,-0.08762224018573761,-0.2171066254377365,-0.214140847325325,0.05768924206495285,-0.14078554511070251,0.09463955461978912,0.24083027243614197,-0.04526655003428459,0.21733830869197845,-0.547228217124939,-0.06822013854980469,-0.26430216431617737,-0.16772106289863586,0.5033514499664307,-0.48400115966796875,-0.15414145588874817,-0.30550289154052734,0.12796342372894287,0.03260451555252075,0.642344057559967,0.608259379863739,0.20670825242996216,-0.13166551291942596,-0.20902025699615479,0.6214919090270996,0.010093532502651215,-0.4179336726665497,-0.24033311009407043,-0.09154842048883438,0.15507033467292786,-0.09613634645938873,-0.4555443525314331,0.20516899228096008,-0.41690224409103394,0.1578223556280136,-0.008968977257609367,0.17420555651187897,-0.412773072719574,0.3942226767539978,0.19923599064350128,0.07551908493041992,0.212879478931427,-0.3616172969341278,-0.15724150836467743],"values_recorded":72,"members":[{"code_sha256_prefix":"9a0bc7c0ec0d80ce","path":"supr/pytorch/supr.py","papers":["2210.13861"],"paper_pages":[{"arxiv_id":"2210.13861","page":"/paper/supr-a-sparse-unified-part-based-human"}],"arg_sig_recorded":[["quat",3,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}