{"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-fn","entry":"loss_fn","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":8,"n_papers":9,"n_buckets":3,"n_distinct_outputs":6,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":5,"by_error":{"RuntimeError":2,"ValueError":2,"IndexError":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/loss-fn","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":6,"n_papers":7,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"af5570f5a1810b7a","size":3,"n_papers":3,"shape":[],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":3,"torch_reference_conventions_with_this_digest":[],"values":[0.0],"values_recorded":1,"members":[{"code_sha256_prefix":"2ec9e2662f3e2b31","path":"example.py","papers":["2305.07583"],"paper_pages":[{"arxiv_id":"2305.07583","page":"/paper/momo-momentum-models-for-adaptive-learning"}],"arg_sig_recorded":[["output",2,"float","float32"],["labels",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"bb53e8b539584939","path":"src/recon.py","papers":["2402.13809"],"paper_pages":[{"arxiv_id":"2402.13809","page":"/paper/neuraldiffuser-controllable-fmri"}],"arg_sig_recorded":[["t",2,"float","float32"],["p",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"c9c18a8a3248d43b","path":"run_model.py","papers":["2208.04360"],"paper_pages":[{"arxiv_id":"2208.04360","page":"/paper/sdwpf-a-dataset-for-spatial-dynamic-wind"}],"arg_sig_recorded":[["y_pred",2,"float","float32"],["y_true",2,"float","float32"]],"scalar_args":{"mask_value":"0.0"},"class_bearing":false}]},{"output_sha":"715623d0a8210901","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":[2.384185791015625e-07,-2.384185791015625e-07,0.0,0.0],"values_recorded":4,"members":[{"code_sha256_prefix":"00cae89471470576","path":"models.py","papers":["2102.06514","2403.06606"],"paper_pages":[{"arxiv_id":"2102.06514","page":"/paper/bootstrapped-representation-learning-on"},{"arxiv_id":"2403.06606","page":"/paper/distributionally-generative-augmentation-for"}],"arg_sig_recorded":[["x",2,"float","float32"],["y",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"036f1acf1061664d","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":[-2.071410894393921],"values_recorded":1,"members":[{"code_sha256_prefix":"f50416d9707b5c6f","path":"lstmn.py","papers":["1601.06733"],"paper_pages":[{"arxiv_id":"1601.06733","page":"/paper/long-short-term-memory-networks-for-machine"}],"arg_sig_recorded":[["pred",2,"float","float32"],["gt",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"5ce9706d86b70742","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":[-0.2493068277835846],"values_recorded":1,"members":[{"code_sha256_prefix":"3459c1b6589faba2","path":"LLMs_WellXplain/Llama_experiment.py","papers":["2406.12058"],"paper_pages":[{"arxiv_id":"2406.12058","page":"/paper/welldunn-on-the-robustness-and-explainability"}],"arg_sig_recorded":[["outputs",2,"float","float32"],["targets",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"float","float32"],[2,"float","float32"],[2,"float","float32"],[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"ba961b80d5308de1","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":[53.288330078125],"values_recorded":1,"members":[{"code_sha256_prefix":"4360bbfc62d0fcb0","path":"disVAE.py","papers":["1803.02991"],"paper_pages":[{"arxiv_id":"1803.02991","page":"/paper/disentangled-sequential-autoencoder"}],"arg_sig_recorded":[["original_seq",2,"float","float32"],["recon_seq",2,"float","float32"],["f_mean",2,"float","float32"],["f_logvar",2,"float","float32"],["z_mean",2,"float","float32"],["z_logvar",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"3da2111422b6aec7","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":[-0.07830430567264557],"values_recorded":1,"members":[{"code_sha256_prefix":"1784b58cb375899c","path":"generate_images_concept_erasure.py","papers":["2412.07658"],"paper_pages":[{"arxiv_id":"2412.07658","page":"/paper/trasce-trajectory-steering-for-concept"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}