{"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/gelu-new","entry":"gelu_new","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":3,"n_papers":7,"n_buckets":1,"n_distinct_outputs":1,"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/gelu-new","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":3,"n_papers":7,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"fbdb323a3bf06188","size":3,"n_papers":7,"shape":[4,8],"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":[1.7381689548492432,-0.09613436460494995,0.32512131333351135,-0.16919474303722382,-0.1656133085489273,-0.15617094933986664,-0.16821636259555817,0.41052737832069397,0.36219537258148193,0.7971585392951965,-0.1372835338115692,-0.09178822487592697,-0.11151190102100372,2.2989766597747803,-0.15617986023426056,0.3903122842311859,0.03495509922504425,-0.08506333827972412,0.2882816195487976,-0.13904662430286407,-0.011093470267951488,-0.14053864777088165,-0.1587630957365036,0.8235445022583008,-0.16965042054653168,0.2892405092716217,0.7819916605949402,0.8602001667022705,-0.13522674143314362,1.1449211835861206,-0.12326118350028992,-0.1641363799571991],"values_recorded":32,"members":[{"code_sha256_prefix":"77601724cad03f95","path":"models/transformers/modeling_bert.py","papers":["2006.03535","2002.10345","2404.19563"],"paper_pages":[{"arxiv_id":"2006.03535","page":"/paper/cocon-a-self-supervised-approach-for"},{"arxiv_id":"2002.10345","page":"/paper/improving-bert-fine-tuning-via-self-ensemble"},{"arxiv_id":"2404.19563","page":"/paper/repeval-effective-text-evaluation-with-llm"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"dc9ffc0f29e7fa3d","path":"gpt/examples/NLG/src/model_nola.py","papers":["2310.02556","2402.02347","2312.12198"],"paper_pages":[{"arxiv_id":"2310.02556","page":"/paper/nola-networks-as-linear-combination-of-low"},{"arxiv_id":"2402.02347","page":"/paper/riemannian-preconditioned-lora-for-fine"},{"arxiv_id":"2312.12198","page":"/paper/mask-grounding-for-referring-image"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"de48fec0ec9764b0","path":"model/squidnet.py","papers":["2210.08714"],"paper_pages":[{"arxiv_id":"2210.08714","page":"/paper/selective-query-guided-debiasing-network-for"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}