{"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/log-sum-exp","entry":"log_sum_exp","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":10,"n_papers":12,"n_buckets":3,"n_distinct_outputs":5,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":1,"by_error":{"RuntimeError":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/log-sum-exp","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":8,"n_papers":10,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"5e734a878a040f70","size":5,"n_papers":6,"shape":[4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":5,"torch_reference_conventions_with_this_digest":[],"values":[2.437394857406616,2.9149835109710693,2.081465721130371,2.486630916595459],"values_recorded":4,"members":[{"code_sha256_prefix":"5efe6eb2209f6591","path":"modules/vae.py","papers":["2310.10567","2110.12381"],"paper_pages":[{"arxiv_id":"2310.10567","page":"/paper/regavae-a-retrieval-augmented-gaussian"},{"arxiv_id":"2110.12381","page":"/paper/regularizing-variational-autoencoder-with"}],"arg_sig_recorded":[["value",2,"float","float32"]],"scalar_args":{"dim":"1","keepdim":"False"},"class_bearing":false},{"code_sha256_prefix":"5e0544169ee07211","path":"i2l/networks/discriminator_model.py","papers":["2002.11879"],"paper_pages":[{"arxiv_id":"2002.11879","page":"/paper/state-only-imitation-with-transition-dynamics-1"}],"arg_sig_recorded":[["value",2,"float","float32"]],"scalar_args":{"dim":"1","keepdim":"False"},"class_bearing":false},{"code_sha256_prefix":"99c65fd4e843a6a0","path":"layers/modules/multibox_loss_gmm.py","papers":["2103.16130"],"paper_pages":[{"arxiv_id":"2103.16130","page":"/paper/active-learning-for-deep-object-detection-via"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"a42f23f7210ea856","path":"code/models.py","papers":["2309.02190"],"paper_pages":[{"arxiv_id":"2309.02190","page":"/paper/exchanging-based-multimodal-fusion-with"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"ed2c8f941b766ebb","path":"k+1_gan.py","papers":["2010.04092"],"paper_pages":[{"arxiv_id":"2010.04092","page":"/paper/improved-techniques-for-model-inversion-1"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"axis":"1"},"class_bearing":false}]},{"output_sha":"88436f094ddcd3b1","size":2,"n_papers":4,"shape":[8],"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":[2.226315498352051,1.5183781385421753,1.8555432558059692,1.4211854934692383,0.8862270712852478,2.669790029525757,0.6750720739364624,1.9071500301361084],"values_recorded":8,"members":[{"code_sha256_prefix":"d4329236872658c9","path":"src/model.py","papers":["1603.01360","1603.01354","1511.08308"],"paper_pages":[{"arxiv_id":"1603.01360","page":"/paper/neural-architectures-for-named-entity"},{"arxiv_id":"1603.01354","page":"/paper/end-to-end-sequence-labeling-via-bi"},{"arxiv_id":"1511.08308","page":"/paper/named-entity-recognition-with-bidirectional"}],"arg_sig_recorded":[["smat",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"bd9ad74746bdeace","path":"src/model.py","papers":["2205.12585"],"paper_pages":[{"arxiv_id":"2205.12585","page":"/paper/a-simple-and-unified-tagging-model-with"}],"arg_sig_recorded":[["tensor",2,"float","float32"]],"scalar_args":{"dim":"0","keepdim":"False"},"class_bearing":false}]},{"output_sha":"325a49dd5d3d6b7f","size":1,"n_papers":1,"shape":[4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[2.437394857406616,2.395503520965576,2.9004201889038086,3.0150415897369385,2.9568750858306885,2.9149835109710693,3.419900417327881,3.5345215797424316,1.6184403896331787,1.5765489339828491,2.081465721130371,2.196087121963501,1.9089841842651367,1.8670927286148071,2.372009754180908,2.486630916595459],"values_recorded":16,"members":[{"code_sha256_prefix":"ca4d0de367bcc625","path":"src/LSTM-CNNs-CRF/model.py","papers":["1603.01360"],"paper_pages":[{"arxiv_id":"1603.01360","page":"/paper/neural-architectures-for-named-entity"}],"arg_sig_recorded":[["input",2,"float","float32"]],"scalar_args":{"keepdim":"False"},"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":"4a41174115cead50","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":[8026290.0,13221093.0,-163257.359375,2742181.5],"values_recorded":4,"members":[{"code_sha256_prefix":"79526833a41be6f5","path":"pytorch_generation/CIFAR_NRF_supervised.py","papers":["1806.00271"],"paper_pages":[{"arxiv_id":"1806.00271","page":"/paper/learning-neural-random-fields-with-inclusive"}],"arg_sig_recorded":[["logits",2,"float","float32"],["mask",2,"float","float32"]],"scalar_args":{"inf":"10000000.0"},"class_bearing":false}]}]},{"bucket":[[3,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"c6140b78c69eb559","size":1,"n_papers":1,"shape":[2,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[2.269655704498291,2.23923397064209,0.7410995960235596,1.4207115173339844,1.479884386062622,2.030714988708496,1.0802357196807861,2.4037234783172607,0.5188460946083069,2.394864797592163,2.080625534057617,0.6306852698326111,2.6110522747039795,2.002910614013672,1.1920839548110962,2.1951208114624023],"values_recorded":16,"members":[{"code_sha256_prefix":"a1572564f4e423a2","path":"mi_estimators.py","papers":["2006.12013"],"paper_pages":[{"arxiv_id":"2006.12013","page":"/paper/club-a-contrastive-log-ratio-upper-bound-of"}],"arg_sig_recorded":[["value",3,"float","float32"]],"scalar_args":{"dim":"1","keepdim":"False"},"class_bearing":false}]}]}]}