{"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/l2-normalize","entry":"l2_normalize","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":15,"n_papers":13,"n_buckets":3,"n_distinct_outputs":5,"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/l2-normalize","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":13,"n_papers":11,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"2803cfee2d9ac85e","size":8,"n_papers":7,"shape":[4,8],"dtype":"float32","type":"ndarray","finite":true,"max_difference_among_recorded_values":5.960464477539063e-08,"members_with_recorded_values":8,"torch_reference_conventions_with_this_digest":["last_dim"],"values":[0.6025403738021851,-0.5126747488975525,0.15912389755249023,-0.23093350231647491,-0.30178332328796387,-0.3444417119026184,-0.2215321660041809,0.191491961479187,0.16532592475414276,0.30560606718063354,-0.12655700743198395,-0.49971213936805725,-0.091933973133564,0.7398777604103088,-0.16402211785316467,0.1754111796617508,0.027956431731581688,-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":"1ff76032d3ce9d1f","path":"library-records-dataset/data-analysis/analysis3/gnd_embed_and_polysemy.py","papers":["2603.10876"],"paper_pages":[{"arxiv_id":"2603.10876","page":"/paper/arxiv-2603-10876"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"axis":"-1","eps":"1e-12"},"class_bearing":false},{"code_sha256_prefix":"2cf4de80fe770aa5","path":"main_text.py","papers":["2306.10234"],"paper_pages":[{"arxiv_id":"2306.10234","page":"/paper/federated-few-shot-learning"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"6325cd34bc332e95","path":"objective.py","papers":["2002.05709"],"paper_pages":[{"arxiv_id":"2002.05709","page":"/paper/a-simple-framework-for-contrastive-learning"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"dim":"1","eps":"1e-12"},"class_bearing":false},{"code_sha256_prefix":"a08ad4db2fd1d778","path":"objective.py","papers":["2010.11694"],"paper_pages":[{"arxiv_id":"2010.11694","page":"/paper/unsupervised-representation-learning-by-2"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"bc6f55493c37776f","path":"main_image.py","papers":["2306.10234"],"paper_pages":[{"arxiv_id":"2306.10234","page":"/paper/federated-few-shot-learning"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"d5090a7e490968ab","path":"core/models/semantic_kitti/geoclass.py","papers":["2508.11265"],"paper_pages":[{"arxiv_id":"2508.11265","page":"/paper/arxiv-2508-11265"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"f06b0faae251c6c8","path":"train_TENT.py","papers":["2206.11972"],"paper_pages":[{"arxiv_id":"2206.11972","page":"/paper/task-adaptive-few-shot-node-classification"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"f1934dc514a9afa5","path":"src/cosmapdr/cosmapdr.py","papers":["2608.11269"],"paper_pages":[{"arxiv_id":"2608.11269","page":"/paper/arxiv-2608-11269"}],"arg_sig_recorded":[["X",2,"float","float32"]],"scalar_args":{"eps":"1e-12"},"class_bearing":false}]},{"output_sha":"4171f3b5f627ddab","size":4,"n_papers":3,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":4,"torch_reference_conventions_with_this_digest":[],"values":[0.31660425662994385,-0.2693844437599182,0.08361149579286575,-0.12134378403425217,-0.1585717648267746,-0.18098656833171844,-0.11640385538339615,0.10061926394701004,0.09113265573978424,0.16845932602882385,-0.06976205110549927,-0.2754564583301544,-0.05067679286003113,0.4078430235385895,-0.09041396528482437,0.09669195860624313,0.011661347001791,-0.28503337502479553,0.07589378952980042,-0.07134035974740982,-0.0039683314971625805,-0.20738644897937775,-0.09429273754358292,0.17276738584041595,-0.13973726332187653,0.07609805464744568,0.16597095131874084,0.17871159315109253,-0.2152905911207199,0.22379697859287262,-0.2322281301021576,-0.10434621572494507],"values_recorded":32,"members":[{"code_sha256_prefix":"00696863cb395244","path":"low_rank_linear.py","papers":["2602.12429"],"paper_pages":[{"arxiv_id":"2602.12429","page":"/paper/arxiv-2602-12429"}],"arg_sig_recorded":[["v",2,"float","float32"]],"scalar_args":{"eps":"1e-12"},"class_bearing":false},{"code_sha256_prefix":"5f294d9fde22ad26","path":"skew_ortho_conv.py","papers":["2105.11417"],"paper_pages":[{"arxiv_id":"2105.11417","page":"/paper/skew-orthogonal-convolutions"}],"arg_sig_recorded":[["tensor",2,"float","float32"]],"scalar_args":{"eps":"1e-12"},"class_bearing":false},{"code_sha256_prefix":"bf5a05c7adc49b0b","path":"sn_gan/sn_modules.py","papers":["1802.05957"],"paper_pages":[{"arxiv_id":"1802.05957","page":"/paper/spectral-normalization-for-generative"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"eps":"1e-12"},"class_bearing":false},{"code_sha256_prefix":"d00da20762480770","path":"skew_ortho_conv.py","papers":["2105.11417"],"paper_pages":[{"arxiv_id":"2105.11417","page":"/paper/skew-orthogonal-convolutions"}],"arg_sig_recorded":[["tensor",2,"float","float32"]],"scalar_args":{"eps":"1e-12"},"class_bearing":false}]},{"output_sha":"58eaef3f9b5e9d5f","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.6025401949882507,-0.5126745700836182,0.15912385284900665,-0.23093341290950775,-0.3017832338809967,-0.34444159269332886,-0.22153207659721375,0.19149188697338104,0.16532588005065918,0.3056059777736664,-0.12655696272850037,-0.4997119903564453,-0.0919339507818222,0.7398775219917297,-0.1640220731496811,0.1754111349582672,0.027956420555710793,-0.6833269000053406,0.18194454908370972,-0.17102834582328796,-0.009513509459793568,-0.49717947840690613,-0.2260534018278122,0.41418519616127014,-0.2817060649394989,0.15341134369373322,0.33459237217903137,0.36027711629867554,-0.4340192675590515,0.45116788148880005,-0.4681648313999176,-0.21035878360271454],"values_recorded":32,"members":[{"code_sha256_prefix":"4760e36330feac9d","path":"src/MoA.py","papers":["2308.00951"],"paper_pages":[{"arxiv_id":"2308.00951","page":"/paper/from-sparse-to-soft-mixtures-of-experts"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"axis":"1","eps":"1e-06"},"class_bearing":false}]}]},{"bucket":[[2,"float","float64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"2803cfee2d9ac85e","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.6025403738021851,-0.5126747488975525,0.15912389755249023,-0.23093350231647491,-0.30178332328796387,-0.3444417119026184,-0.2215321660041809,0.191491961479187,0.16532592475414276,0.30560606718063354,-0.12655700743198395,-0.49971213936805725,-0.091933973133564,0.7398777604103088,-0.16402211785316467,0.1754111796617508,0.027956431731581688,-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":"4bb9a4bd0cf9085d","path":"recipe/leeps/task_sampler.py","papers":["2607.28077"],"paper_pages":[{"arxiv_id":"2607.28077","page":"/paper/arxiv-2607-28077"}],"arg_sig_recorded":[["values",2,"float","float64"]],"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":"0e0d73a888ed9088","size":1,"n_papers":1,"shape":[2,4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.16031098365783691,0.3020620346069336,-0.22594787180423737,-0.04634639993309975,0.027102874591946602,-0.25753071904182434,-0.061054110527038574,-0.06840978562831879,-0.3839760720729828,0.002131028100848198,-0.1523812711238861,-0.13860583305358887,0.1501663327217102,-0.030411820858716965,0.027227425947785378,0.0730389729142189,0.33740943670272827,-0.13377666473388672,-0.01571035385131836,0.1390121877193451,-0.10238884389400482,0.2018090784549713,-0.072430819272995,0.17176084220409393,0.17129288613796234,0.1658075451850891,-0.13545002043247223,-0.05497083440423012,-0.18556872010231018,0.22275272011756897,-0.1635964810848236,0.3296644985675812,-0.1655448079109192,0.32311394810676575,-0.20432865619659424,-0.1390393078327179,0.17279323935508728,0.10904347896575928,0.007614902686327696,0.30119946599006653,-0.20620892941951752,-0.15522360801696777,-0.17546376585960388,-0.11864084005355835,0.16999013721942902,-0.02487562969326973,0.067388616502285,0.15639682114124298,-0.05869297310709953,-0.016865631565451622,0.12950439751148224,-0.17257662117481232,0.09131905436515808,0.032598115503787994,-0.12255049496889114,-0.16662538051605225,-0.21993006765842438,0.19981451332569122,0.28598499298095703,-0.10056955367326736,0.32451993227005005,0.21460770070552826,-0.22007623314857483,-0.14872486889362335],"values_recorded":64,"members":[{"code_sha256_prefix":"ddaf1f8283422da4","path":"models/mahalanobis.py","papers":["1807.03888"],"paper_pages":[{"arxiv_id":"1807.03888","page":"/paper/a-simple-unified-framework-for-detecting-out"}],"arg_sig_recorded":[["d",3,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}