{"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/loss-func","entry":"loss_func","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":3,"n_distinct_outputs":4,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":1,"by_error":{"ValueError":1}},"no_array_argument_ran_on_own_fixture_arguments_only":{"n":1,"n_papers":1,"recorded_shared_digest_equals_own_fixture_digest":1},"output_not_digested_non_numeric":{"n":0,"by_type":{}}},"withdrawn_excluded":0,"code_page":"/code/loss-func","buckets":[{"bucket":[[1,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"eedcc9f64347fe03","size":2,"n_papers":2,"shape":[],"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":[0.3692583739757538],"values_recorded":1,"members":[{"code_sha256_prefix":"3ef32b5700dabe8c","path":"src/models/patch.py","papers":["2301.09785"],"paper_pages":[{"arxiv_id":"2301.09785","page":"/paper/transformer-patcher-one-mistake-worth-one"}],"arg_sig_recorded":[["loss",1,"float","float32"]],"scalar_args":{"loss_type":"'margin'"},"class_bearing":false},{"code_sha256_prefix":"7ba48886f3a5f906","path":"easyeditor/models/unike/unike_main.py","papers":["2409.19872"],"paper_pages":[{"arxiv_id":"2409.19872","page":"/paper/towards-unified-multimodal-editing-with"}],"arg_sig_recorded":[["loss",1,"float","float32"]],"scalar_args":{"loss_type":"'margin'"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"5e691976ed3da60f","size":1,"n_papers":1,"shape":[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":[0.5547454357147217,-0.6519855856895447,2.1006054878234863,-1.4474146366119385,-1.1076042652130127,-0.9704298377037048,-1.508839726448059,1.7455382347106934],"values_recorded":8,"members":[{"code_sha256_prefix":"a0cb57b5b394f6f4","path":"utils.py","papers":["1612.02806"],"paper_pages":[{"arxiv_id":"1612.02806","page":"/paper/quantum-autoencoders-for-efficient"}],"arg_sig_recorded":[["output",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"5f71001451ac818d","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":[-0.09194524586200714],"values_recorded":1,"members":[{"code_sha256_prefix":"49e2a4eb90f7b049","path":"terapipe.py","papers":["2102.07988"],"paper_pages":[{"arxiv_id":"2102.07988","page":"/paper/terapipe-token-level-pipeline-parallelism-for"}],"arg_sig_recorded":[["y",2,"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":"bd9b4f62ae1d8205","path":"ellipses/script_train_fourier_unet_it_jit-nojit.py","papers":["2001.01258"],"paper_pages":[{"arxiv_id":"2001.01258","page":"/paper/the-troublesome-kernel-why-deep-learning-for"}],"arg_sig_recorded":[["pred",2,"float","float32"],["tar",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}