{"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/huber-loss","entry":"huber_loss","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":7,"n_buckets":5,"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/huber-loss","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"599afeec565a28b8","size":2,"n_papers":2,"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":[1.3026286363601685,1.0337762832641602,0.11331333965063095,0.238662451505661,0.4075686037540436,0.5304712057113647,0.21962600946426392,0.1641010195016861,0.13461613655090332,0.45998018980026245,0.07888375222682953,1.0683481693267822,0.04162624850869179,1.8221087455749512,0.1325012743473053,0.1515408605337143,0.002204177202656865,1.1228755712509155,0.09336013346910477,0.08249347656965256,0.00025524949887767434,0.6807824373245239,0.14411377906799316,0.48380744457244873,0.31649985909461975,0.0938633605837822,0.4464914798736572,0.5175182819366455,0.7257857322692871,0.774217963218689,0.8222218751907349,0.17648282647132874],"values_recorded":32,"members":[{"code_sha256_prefix":"bd237d8a9c8b33f6","path":"models/loss_helper_unlabeled.py","papers":["2401.05011"],"paper_pages":[{"arxiv_id":"2401.05011","page":"/paper/dual-perspective-knowledge-enrichment-for"}],"arg_sig_recorded":[["error",2,"float","float32"]],"scalar_args":{"delta":"1.0"},"class_bearing":false},{"code_sha256_prefix":"d52eb4ad208682cb","path":"algo/model_free/tracer.py","papers":["2411.00465"],"paper_pages":[{"arxiv_id":"2411.00465","page":"/paper/uncertainty-based-offline-variational"}],"arg_sig_recorded":[["diff",2,"float","float32"]],"scalar_args":{"sigma":"1.0"},"class_bearing":false}]}]},{"bucket":[[1,"float","float64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"8e5de9e837aaf1d1","size":1,"n_papers":1,"shape":[],"dtype":"float64","type":"float64","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[2.275315987387226],"values_recorded":1,"members":[{"code_sha256_prefix":"88fde780024a2ac5","path":"conquer/joint.py","papers":["2109.05640"],"paper_pages":[{"arxiv_id":"2109.05640","page":"/paper/high-dimensional-quantile-regression"}],"arg_sig_recorded":[["u",1,"float","float64"]],"scalar_args":{"c":"1.0"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[0,"float","float32"]],"n_implementations_compared":1,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"3fb89ca22de02572","size":1,"n_papers":2,"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":[-3.5802667140960693,0.0,-1.691455364227295,-1.9973411560058594,-2.2991385459899902,-2.480849504470825,-1.9572943449020386,-1.8293328285217285,-1.7524274587631226,-2.3792943954467773,-1.579181432723999,0.0,-1.4244623184204102,-4.319915771484375,-1.7466011047363281,-1.7974953651428223,-1.1081743240356445,0.0,-1.628889799118042,-1.5919764041900635,-1.045809030532837,-2.694866418838501,-1.7780452966690063,-2.4142186641693115,-2.1464521884918213,-1.630545735359192,-2.359121799468994,-2.462406873703003,-2.7589433193206787,-2.827902317047119,-2.8962514400482178,-1.859546422958374],"values_recorded":32,"members":[{"code_sha256_prefix":"317a7486c52962a6","path":"src/learners/poam_learner.py","papers":["2402.06700","2404.10740"],"paper_pages":[{"arxiv_id":"2402.06700","page":"/paper/entropy-regularized-token-level-policy"},{"arxiv_id":"2404.10740","page":"/paper/n-agent-ad-hoc-teamwork"}],"arg_sig_recorded":[["e",2,"float","float32"],["d",0,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"af5570f5a1810b7a","size":1,"n_papers":1,"shape":[],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0],"values_recorded":1,"members":[{"code_sha256_prefix":"ad44a67c8db05805","path":"algo/offline_offline/droco.py","papers":["2512.02486"],"paper_pages":[{"arxiv_id":"2512.02486","page":"/paper/arxiv-2512-02486"}],"arg_sig_recorded":[["y_true",2,"float","float32"],["y_pred",2,"float","float32"]],"scalar_args":{"delta":"30.0"},"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":"0f6abb0cb0bcd655","size":1,"n_papers":1,"shape":[2,3],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.832574725151062,0.7579707503318787,0.7604018449783325,1.4479118585586548,0.8776646256446838,0.9974384903907776],"values_recorded":6,"members":[{"code_sha256_prefix":"ab891ef221209094","path":"generation/dps.py","papers":["2505.17004"],"paper_pages":[{"arxiv_id":"2505.17004","page":"/paper/guided-diffusion-sampling-on-function-spaces"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{"n_obs":"8","delta":"1.0"},"class_bearing":false}]}]}]}