{"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/compute-loss","entry":"compute_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":11,"n_papers":11,"n_buckets":7,"n_distinct_outputs":9,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":8,"by_error":{"IndexError":3,"RuntimeError":3,"ValueError":2}},"no_array_argument_ran_on_own_fixture_arguments_only":{"n":6,"n_papers":7,"recorded_shared_digest_equals_own_fixture_digest":6},"output_not_digested_non_numeric":{"n":0,"by_type":{}}},"withdrawn_excluded":0,"code_page":"/code/compute-loss","buckets":[{"bucket":[[2,"float","float32"],[1,"int","int64"],[2,"float","float32"],[0,"float","float32"],[2,"float","float32"]],"n_implementations_compared":3,"n_papers":3,"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":"3bdfc4201b35c55b","path":"src/robust_vlm/train/adversarial_training_clip.py","papers":["2506.03355"],"paper_pages":[{"arxiv_id":"2506.03355","page":"/paper/robustness-in-both-domains-clip-needs-a"}],"arg_sig_recorded":[["embedding",2,"float","float32"],["targets",1,"int","int64"],["embedding_orig",2,"float","float32"],["logit_scale",0,"float","float32"],["embedding_text_labels_norm",2,"float","float32"]],"scalar_args":{"loss_str":"'l2'","reduction":"'mean'"},"class_bearing":false},{"code_sha256_prefix":"735c7110db767760","path":"train/align_training_clip.py","papers":["2506.02557"],"paper_pages":[{"arxiv_id":"2506.02557","page":null}],"arg_sig_recorded":[["embedding",2,"float","float32"],["targets",1,"int","int64"],["embedding_orig",2,"float","float32"],["logit_scale",0,"float","float32"],["embedding_text_labels_norm",2,"float","float32"]],"scalar_args":{"loss_str":"'l2'","reduction":"'mean'"},"class_bearing":false},{"code_sha256_prefix":"b03f0274dabbb8c0","path":"train/adversarial_training_clip.py","papers":["2402.12336"],"paper_pages":[{"arxiv_id":"2402.12336","page":"/paper/robust-clip-unsupervised-adversarial-fine"}],"arg_sig_recorded":[["embedding",2,"float","float32"],["targets",1,"int","int64"],["embedding_orig",2,"float","float32"],["logit_scale",0,"float","float32"],["embedding_text_labels_norm",2,"float","float32"]],"scalar_args":{"loss_str":"'l2'","reduction":"'mean'"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"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":"310b4b2e126ed8b6","path":"models/graphedx.py","papers":["2409.17687"],"paper_pages":[{"arxiv_id":"2409.17687","page":"/paper/graph-edit-distance-with-general-costs-using"}],"arg_sig_recorded":[["lower_bound",2,"float","float32"],["upper_bound",2,"float","float32"],["out",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"af7e12f89d3e8367","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":[-3.6222481727600098],"values_recorded":1,"members":[{"code_sha256_prefix":"ddaa3dd8a024013d","path":"model.py","papers":["2108.07386"],"paper_pages":[{"arxiv_id":"2108.07386","page":"/paper/bobcat-bilevel-optimization-based"}],"arg_sig_recorded":[["output",2,"float","float32"],["labels",2,"float","float32"],["mask",2,"float","float32"]],"scalar_args":{"reduction":"True"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"81e565f324d2be20","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":[0.03162277862429619],"values_recorded":1,"members":[{"code_sha256_prefix":"06a1ef9308233244","path":"src/srtta.py","papers":["2310.19011"],"paper_pages":[{"arxiv_id":"2310.19011","page":"/paper/efficient-test-time-adaptation-for-super-1"}],"arg_sig_recorded":[["pred",2,"float","float32"],["target",2,"float","float32"]],"scalar_args":{"eps":"0.001"},"class_bearing":false}]},{"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":"303d355d2a45ca05","path":"bayesian_laws_icl/analyse.py","papers":["2410.16531"],"paper_pages":[{"arxiv_id":"2410.16531","page":"/paper/bayesian-scaling-laws-for-in-context-learning"}],"arg_sig_recorded":[["true_nll",2,"float","float32"],["est_nll",2,"float","float32"]],"scalar_args":{"mode":"'mse_prob'"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[1,"int","int64"],[1,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"74999fd28ab18ccc","size":1,"n_papers":1,"shape":[],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[NaN],"values_recorded":1,"members":[{"code_sha256_prefix":"193acceb49ed1761","path":"src/NERDA_Con/training.py","papers":["2206.14607"],"paper_pages":[{"arxiv_id":"2206.14607","page":"/paper/nerda-con-extending-ner-models-for-continual"}],"arg_sig_recorded":[["preds",2,"float","float32"],["target_tags",1,"int","int64"],["masks",1,"float","float32"]],"scalar_args":{"device":"'cpu'","n_tags":"4"},"class_bearing":false}]}]},{"bucket":[[2,"float","float32"],[1,"int","int64"],[2,"float","float32"],[0,"float","float32"]],"n_implementations_compared":1,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"af5570f5a1810b7a","size":1,"n_papers":2,"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":"75f68885e2ff2684","path":"train/adversarial_training_clip.py","papers":["2402.12336","2308.10741"],"paper_pages":[{"arxiv_id":"2402.12336","page":"/paper/robust-clip-unsupervised-adversarial-fine"},{"arxiv_id":"2308.10741","page":"/paper/on-the-adversarial-robustness-of-multi-modal"}],"arg_sig_recorded":[["embedding",2,"float","float32"],["targets",1,"int","int64"],["embedding_orig",2,"float","float32"],["logit_scale",0,"float","float32"]],"scalar_args":{"loss_str":"'l2'","embedding_text_labels_norm":"None","reduction":"'mean'"},"class_bearing":false}]}]},{"bucket":[[3,"float","float32"],[2,"bool","bool"],[3,"bool","bool"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"ad9b9550123ed44e","size":1,"n_papers":1,"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":[0.2282368540763855,-0.8460121750831604,-0.8877213001251221,0.7032288312911987],"values_recorded":4,"members":[{"code_sha256_prefix":"59178d244fffc6d5","path":"materials/train_edm.py","papers":["2407.11942"],"paper_pages":[{"arxiv_id":"2407.11942","page":"/paper/context-guided-diffusion-for-out-of"}],"arg_sig_recorded":[["xh",3,"float","float32"],["node_mask",2,"bool","bool"],["edge_mask",3,"bool","bool"]],"scalar_args":{"model":"DummyModel(\n  (linear): Linear(in_features=4, out_features=1","num_node_features":"2"},"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":"7300b9435f4800f9","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":[0.021091222763061523],"values_recorded":1,"members":[{"code_sha256_prefix":"39ed029c556af56b","path":"Codes/PhyCRNet_burgers.py","papers":["2106.14103"],"paper_pages":[{"arxiv_id":"2106.14103","page":"/paper/phycrnet-physics-informed-convolutional"}],"arg_sig_recorded":[["output",4,"float","float32"]],"scalar_args":{"loss_func":"PhysicsLossModule()"},"class_bearing":false}]}]}]}