{"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/normalize-tensor","entry":"normalize_tensor","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":3,"n_papers":5,"n_buckets":2,"n_distinct_outputs":2,"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/normalize-tensor","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":2,"n_papers":4,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"2803cfee2d9ac85e","size":2,"n_papers":4,"shape":[4,8],"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":[0.6025403738021851,-0.5126747488975525,0.15912389755249023,-0.23093350231647491,-0.30178332328796387,-0.3444417119026184,-0.2215321660041809,0.191491961479187,0.16532593965530396,0.30560609698295593,-0.12655700743198395,-0.49971216917037964,-0.09193398058414459,0.7398778200149536,-0.16402213275432587,0.175411194562912,0.027956431731581688,-0.6833271980285645,0.18194462358951569,-0.17102842032909393,-0.009513513185083866,-0.49717968702316284,-0.22605349123477936,0.41418537497520447,-0.28170618414878845,0.153411403298378,0.3345924913883209,0.3602772355079651,-0.43401941657066345,0.451168030500412,-0.46816498041152954,-0.2103588581085205],"values_recorded":32,"members":[{"code_sha256_prefix":"4d9196e5759e6950","path":"src/models/tokenizer/tokenizer.py","papers":["2502.01591","2307.15208"],"paper_pages":[{"arxiv_id":"2502.01591","page":"/paper/improving-transformer-world-models-for-data"},{"arxiv_id":"2307.15208","page":"/paper/generative-ai-for-medical-imaging-extending"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"eps":"1e-10"},"class_bearing":false},{"code_sha256_prefix":"7257fdf155f5ef45","path":"models/models_v2l.py","papers":["2403.07874","2412.08781"],"paper_pages":[{"arxiv_id":"2403.07874","page":"/paper/beyond-text-frozen-large-language-models-in"},{"arxiv_id":"2412.08781","page":"/paper/generative-modeling-with-explicit-memory"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"eps":"1e-10"},"class_bearing":false}]}]},{"bucket":[[4,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"947f3f029bf2db99","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":[0.7598283886909485,0.5361105799674988,0.8839045166969299,0.5801753401756287,0.7569923400878906,-0.0868622362613678,-0.5158882141113281,0.4061167240142822,0.7441689968109131,-0.06967820227146149,-0.4763834476470947,-0.010343843139708042,-0.8840245604515076,-0.9361063241958618,-0.9414018988609314,0.5180506706237793,-0.4760403037071228,0.10304901748895645,0.3623679578304291,-0.7730845808982849,-0.4825775623321533,0.5002650022506714,-0.7554389834403992,0.6997498273849487,0.4847656190395355,0.6235456466674805,-0.8275087475776672,-0.1375541388988495,0.46658289432525635,0.008399407379329205,0.31617698073387146,-0.3173745572566986,-0.44277140498161316,0.837834358215332,-0.295638769865036,-0.2563917636871338,-0.44054698944091797,0.8615043759346008,0.40394455194473267,-0.5877238512039185,-0.45958107709884644,-0.7786756157875061,-0.29713308811187744,0.9904402494430542,0.028304027393460274,-0.3516167998313904,0.1174503043293953,-0.7942901849746704,0.3989374041557312,0.3986809551715851,0.9360711574554443,-0.008322286419570446,0.886127769947052,-0.45254212617874146,-0.5716170072555542,-0.19461429119110107,-0.9060936570167542,-0.9676551222801208,-0.5573580861091614,-0.01960914209485054,-0.9188674092292786,-0.9241648316383362,-0.38548821210861206,0.497403621673584,0.32628920674324036,-0.9141530990600586,0.3440108597278595,0.9282851815223694,0.2595877945423126,0.01602858677506447,0.7367984652519226,0.06683938950300217,0.3958996534347534,0.13706152141094208,0.2100488692522049,-0.4970782697200775,0.35909974575042725,0.33419397473335266,0.40207573771476746,0.554144024848938,-0.856962263584137,-0.07333166152238846,0.07366994023323059,-0.37177589535713196,0.38391628861427307,0.8915989995002747,-0.3610844612121582,0.9785999059677124,0.1491905003786087,0.21179653704166412,0.8032630085945129,-0.8674841523170471,0.16349337995052338,0.18502385914325714,-0.8305022120475769,-0.6674683690071106],"values_recorded":96,"members":[{"code_sha256_prefix":"61e29634518807c2","path":"HandFormer/models/hf_pose.py","papers":["2403.09805"],"paper_pages":[{"arxiv_id":"2403.09805","page":"/paper/on-the-utility-of-3d-hand-poses-for-action"}],"arg_sig_recorded":[["tensor",4,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}