{"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/focal-loss","entry":"focal_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":13,"n_buckets":3,"n_distinct_outputs":4,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":5,"by_error":{"RuntimeError":4,"ValueError":1}},"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/focal-loss","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":3,"n_papers":4,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"74999fd28ab18ccc","size":2,"n_papers":2,"shape":[],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":2,"torch_reference_conventions_with_this_digest":[],"values":[NaN],"values_recorded":1,"members":[{"code_sha256_prefix":"3c8319d0c4370678","path":"src/model.py","papers":["1505.04597"],"paper_pages":[{"arxiv_id":"1505.04597","page":"/paper/u-net-convolutional-networks-for-biomedical"}],"arg_sig_recorded":[["yhat",2,"float","float32"],["ytrue",2,"float","float32"]],"scalar_args":{"alpha":"0.75","gamma":"2"},"class_bearing":false},{"code_sha256_prefix":"eb19c575ed458088","path":"scripts/self_train.py","papers":["2103.04527"],"paper_pages":[{"arxiv_id":"2103.04527","page":"/paper/one-shot-medical-landmark-detection"}],"arg_sig_recorded":[["pred",2,"float","float32"],["gt",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"ae0dac54e1e9bd51","size":1,"n_papers":2,"shape":[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":[0.07591351866722107,0.1202298104763031,0.15510809421539307,0.05798642337322235],"values_recorded":4,"members":[{"code_sha256_prefix":"6ccd040c4ef8720b","path":"transductive/imb_loss.py","papers":["2110.04099","2308.14181"],"paper_pages":[{"arxiv_id":"2110.04099","page":"/paper/topology-imbalance-learning-for-semi"},{"arxiv_id":"2308.14181","page":"/paper/topological-augmentation-for-class-imbalanced"}],"arg_sig_recorded":[["labels",2,"float","float32"],["logits",2,"float","float32"]],"scalar_args":{"alpha":"0.25","gamma":"2.0"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"]],"n_implementations_compared":2,"n_papers":8,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"1e616596e6c2d66a","size":2,"n_papers":8,"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":[-2.9984583854675293],"values_recorded":1,"members":[{"code_sha256_prefix":"1b3f82e6c53766e7","path":"loss.py","papers":["2410.21042","2305.11733","2304.01279","2305.10772"],"paper_pages":[{"arxiv_id":"2410.21042","page":"/paper/improving-visual-prompt-tuning-by-gaussian"},{"arxiv_id":"2305.11733","page":"/paper/long-tailed-visual-recognition-via-gaussian-1"},{"arxiv_id":"2304.01279","page":"/paper/long-tailed-visual-recognition-via-self"},{"arxiv_id":"2305.10772","page":"/paper/feature-balanced-loss-for-long-tailed-visual-1"}],"arg_sig_recorded":[["input_values",2,"float","float32"]],"scalar_args":{"gamma":"2.0"},"class_bearing":false},{"code_sha256_prefix":"4dcf06ba28983266","path":"utils/losses.py","papers":["2311.03236","2407.12568","2605.23254","2604.06468"],"paper_pages":[{"arxiv_id":"2311.03236","page":"/paper/out-of-distribution-detection-learning-with"},{"arxiv_id":"2407.12568","page":"/paper/ltrl-boosting-long-tail-recognition-via"},{"arxiv_id":"2605.23254","page":"/paper/arxiv-2605-23254"},{"arxiv_id":"2604.06468","page":"/paper/arxiv-2604-06468"}],"arg_sig_recorded":[["input_values",2,"float","float32"]],"scalar_args":{"gamma":"2.0"},"class_bearing":false}]}]},{"bucket":[[1,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"aa19b108ef849679","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":[-3.745140790939331],"values_recorded":1,"members":[{"code_sha256_prefix":"b6c954a2933604c5","path":"source/defenses/membership_inference/loss_function.py","papers":["2402.05453"],"paper_pages":[{"arxiv_id":"2402.05453","page":"/paper/mitigating-privacy-risk-in-membership"}],"arg_sig_recorded":[["input_values",1,"float","float32"]],"scalar_args":{"gamma":"2.0","reduction":"'mean'"},"class_bearing":false}]}]}]}