{"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","entry":"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":8,"n_papers":7,"n_buckets":6,"n_distinct_outputs":7,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":5,"by_error":{"RuntimeError":3,"ValueError":2}},"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","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":3,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"af5570f5a1810b7a","size":2,"n_papers":1,"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":[0.0],"values_recorded":1,"members":[{"code_sha256_prefix":"5c9c60032bf7c292","path":"infinite_training_time.py","papers":["2309.01213"],"paper_pages":[{"arxiv_id":"2309.01213","page":"/paper/implicit-regularization-of-deep-residual"}],"arg_sig_recorded":[["pred",2,"float","float32"],["Y",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"9e75157a4fa4aa8b","path":"finite_training_time_convergence.py","papers":["2309.01213"],"paper_pages":[{"arxiv_id":"2309.01213","page":"/paper/implicit-regularization-of-deep-residual"}],"arg_sig_recorded":[["pred",2,"float","float32"],["Y",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"3e72399f4d4c8d1e","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":[179.95858134915812],"values_recorded":1,"members":[{"code_sha256_prefix":"f7ebefe54a10d4b9","path":"shica/shicaj.py","papers":["2110.13502"],"paper_pages":[{"arxiv_id":"2110.13502","page":"/paper/shared-independent-component-analysis-for"}],"arg_sig_recorded":[["D",2,"float","float32"],["CY",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[1,"float","float32"],[1,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"e37c9e3b518da7a2","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":[7.78375768661499],"values_recorded":1,"members":[{"code_sha256_prefix":"68cef691420d81ee","path":"test_func/run_toy.py","papers":["2506.05454"],"paper_pages":[{"arxiv_id":"2506.05454","page":"/paper/zeroth-order-optimization-finds-flat-minima"}],"arg_sig_recorded":[["x",1,"float","float32"],["y",1,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[1,"float","float64"],[1,"float","float64"],[1,"float","float64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"8021914464b7136d","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":[1.4658514900294763],"values_recorded":1,"members":[{"code_sha256_prefix":"ee4033ae07851e27","path":"dmft.py","papers":["2402.03220"],"paper_pages":[{"arxiv_id":"2402.03220","page":"/paper/the-benefits-of-reusing-batches-for-gradient"}],"arg_sig_recorded":[["a",1,"float","float64"],["h",1,"float","float64"],["h_star",1,"float","float64"]],"scalar_args":{"symmetry":"'TEST'"},"class_bearing":false}]}]},{"bucket":[[1,"float","float64"],[1,"float","float64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"f5a5fd42d16a2030","size":1,"n_papers":1,"shape":[8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0],"values_recorded":8,"members":[{"code_sha256_prefix":"68f28b95be7dc320","path":"examples/gromov/plot_gromov.py","papers":["2303.06595"],"paper_pages":[{"arxiv_id":"2303.06595","page":"/paper/a-convergent-single-loop-algorithm-for"}],"arg_sig_recorded":[["x",1,"float","float64"],["y",1,"float","float64"]],"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":"4775be33aff8be93","size":1,"n_papers":1,"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":[2.599575996398926,0.47049394249916077,0.18130134046077728,0.09546498209238052,0.16302745044231415,0.21237419545650482,0.0878504067659378,0.2625616490840912,0.2153858244419098,0.735968291759491,0.03155350312590599,0.49194321036338806,0.016650499776005745,4.313751220703125,0.05300050973892212,0.24246537685394287,0.0035266836639493704,0.5267450213432312,0.14937621355056763,0.03299739211797714,0.00010209980246145278,0.27884945273399353,0.057645510882139206,0.774091899394989,0.12659995257854462,0.150181382894516,0.7143864035606384,0.8282747268676758,0.30051013827323914,1.2989052534103394,0.3496541380882263,0.07059313356876373],"values_recorded":32,"members":[{"code_sha256_prefix":"162c85e425a085c5","path":"IQL.py","papers":["2110.06169"],"paper_pages":[{"arxiv_id":"2110.06169","page":"/paper/offline-reinforcement-learning-with-implicit"}],"arg_sig_recorded":[["diff",2,"float","float32"]],"scalar_args":{"expectile":"0.8"},"class_bearing":false}]}]},{"bucket":[[3,"float","float32"],[3,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"374708fff7719dd5","size":1,"n_papers":1,"shape":[2],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,0.0],"values_recorded":2,"members":[{"code_sha256_prefix":"7ccf5c554ef3c0de","path":"toy_experiment.py","papers":["1911.10036"],"paper_pages":[{"arxiv_id":"1911.10036","page":"/paper/low-variance-black-box-gradient-estimates-for"}],"arg_sig_recorded":[["P",3,"float","float32"],["target_P",3,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}