{"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-weights","entry":"compute_weights","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":4,"n_distinct_outputs":5,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":0,"by_error":{}},"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/compute-weights","buckets":[{"bucket":[[1,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"0c77544de6fbb01e","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":[0.08755764365196228,0.14883044362068176,0.2155187577009201,0.09398584812879562,0.12597885727882385,0.14128197729587555,0.060948047786951065,0.12589840590953827],"values_recorded":8,"members":[{"code_sha256_prefix":"35d54d75bfd87097","path":"run_experiment.py","papers":["2006.14422"],"paper_pages":[{"arxiv_id":"2006.14422","page":"/paper/incremental-training-of-graph-neural-networks"}],"arg_sig_recorded":[["ts",1,"float","float32"]],"scalar_args":{"exponential_decay":"0.5","initial_quantity":"1.0","normalize":"True"},"class_bearing":false}]},{"output_sha":"9af470c3185f6f58","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":[0.0,0.00047186625306494534,0.002695531351491809,0.0,0.0,0.00015925441402941942,0.0,0.0],"values_recorded":8,"members":[{"code_sha256_prefix":"3fb59f94f820e2cf","path":"pipeline_mvd_warp_mix_classifier.py","papers":["2412.06699"],"paper_pages":[{"arxiv_id":"2412.06699","page":"/paper/you-see-it-you-got-it-learning-3d-creation-on"}],"arg_sig_recorded":[["timesteps",1,"float","float32"]],"scalar_args":{"max_time":"333.0","min_time":"0.0"},"class_bearing":false}]}]},{"bucket":[[1,"float","float64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"3f321b9c9269ea1d","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":[0.0196078431372549,0.24019607843137256,0.3137254901960784,0.04411764705882353,0.12254901960784313,0.17647058823529413,0.004901960784313725,0.0784313725490196],"values_recorded":8,"members":[{"code_sha256_prefix":"545a1ee00e59c770","path":"src/utils.py","papers":["2605.26849"],"paper_pages":[{"arxiv_id":"2605.26849","page":"/paper/arxiv-2605-26849"}],"arg_sig_recorded":[["s",1,"float","float64"]],"scalar_args":{"strategy":"'borda'","tau":"1.0","p":"2.0","q":"50","alpha":"2.0","temp":"0.1"},"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":"acfc7c36fce590b1","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":[1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0],"values_recorded":32,"members":[{"code_sha256_prefix":"7ff1e86fbdd99c43","path":"Algorithms/BGPO.py","papers":["2106.12112"],"paper_pages":[{"arxiv_id":"2106.12112","page":"/paper/bregman-gradient-policy-optimization"}],"arg_sig_recorded":[["o_lh",2,"float","float32"],["c_lh",2,"float","float32"]],"scalar_args":{"th":"1.99"},"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":"b753f8fa646f0cf1","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":[0.5114477872848511,0.5783314108848572,1.042493462562561,0.9114888906478882,0.8043884038925171,0.7487110495567322,0.9272500872612,0.980326771736145,1.0143342018127441,0.779083251953125,1.0972858667373657,0.5689459443092346,1.1795437335968018,0.4139656126499176,1.01697838306427,0.9942060112953186,1.3757128715515137,0.5546404123306274,1.0725429058074951,1.0908417701721191,1.4194300174713135,0.6903473138809204,1.0028226375579834,0.7684310674667358,0.8561089038848877,1.0717322826385498,0.7853379249572754,0.7540916800498962,0.6742368340492249,0.6575468182563782,0.6416374444961548,0.9674093723297119],"values_recorded":32,"members":[{"code_sha256_prefix":"f2e90ad69c40bd2a","path":"Adversarial ML/WEAT_loss.py","papers":["2407.06315"],"paper_pages":[{"arxiv_id":"2407.06315","page":"/paper/shedding-more-light-on-robust-classifiers"}],"arg_sig_recorded":[["energy",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}