{"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/geglu","entry":"GEGLU","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":12,"n_papers":12,"n_buckets":1,"n_distinct_outputs":1,"n_class_bearing":12,"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/geglu","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":12,"n_papers":12,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"2fde4292a2c28363","size":12,"n_papers":12,"shape":[4,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":12,"torch_reference_conventions_with_this_digest":[],"values":[-0.29832589626312256,0.23928076028823853,-0.08005796372890472,-0.2836473882198334,-0.05785972625017166,2.2047152519226074,0.0620269812643528,-0.6121837496757507,-0.0007365558412857354,0.22773750126361847,-0.06859372556209564,-0.33457183837890625,0.10741380602121353,0.496163547039032,-0.1162596344947815,-0.16697940230369568],"values_recorded":16,"members":[{"code_sha256_prefix":"06c174629a88b34c","path":"make_a_video_pytorch/make_a_video.py","papers":["2006.11239"],"paper_pages":[{"arxiv_id":"2006.11239","page":"/paper/denoising-diffusion-probabilistic-models"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"22d4e66449e24cb5","path":"model/cross_modal_attention.py","papers":["2308.15512"],"paper_pages":[{"arxiv_id":"2308.15512","page":"/paper/shatter-and-gather-learning-referring-image"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"579b2c6b2cba46b3","path":"phenaki_pytorch/phenaki_pytorch.py","papers":["2209.04439"],"paper_pages":[{"arxiv_id":"2209.04439","page":"/paper/improved-masked-image-generation-with-token"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"594fabefbfea082e","path":"models/model.py","papers":["2303.15555"],"paper_pages":[{"arxiv_id":"2303.15555","page":"/paper/object-discovery-from-motion-guided-tokens"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"5f34e2fdaf110b16","path":"marge_pytorch/marge_pytorch.py","papers":["2006.15020"],"paper_pages":[{"arxiv_id":"2006.15020","page":"/paper/pre-training-via-paraphrasing"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"7852fe36c3e3b1f9","path":"utils/perceiver.py","papers":["2103.03206"],"paper_pages":[{"arxiv_id":"2103.03206","page":"/paper/perceiver-general-perception-with-iterative"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"845f84e3a319753d","path":"src/model/transformer_xl.py","papers":["1901.02860"],"paper_pages":[{"arxiv_id":"1901.02860","page":"/paper/transformer-xl-attentive-language-models"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"96a67196734e1c67","path":"cod/models/vae/vae.py","papers":["2503.08737"],"paper_pages":[{"arxiv_id":"2503.08737","page":"/paper/representing-3d-shapes-with-64-latent-vectors"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"98fc29d2020b2786","path":"models/m3.py","papers":["2604.15377"],"paper_pages":[{"arxiv_id":"2604.15377","page":"/paper/arxiv-2604-15377"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"a23cbed08cdc0263","path":"model/FedMVP.py","papers":["2504.20860"],"paper_pages":[{"arxiv_id":"2504.20860","page":null}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"c5c74119405bfc64","path":"block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","papers":["2203.07852"],"paper_pages":[{"arxiv_id":"2203.07852","page":"/paper/block-recurrent-transformers"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"c83d2ae566da79c3","path":"model/CoIFNet.py","papers":["2506.13064"],"paper_pages":[{"arxiv_id":"2506.13064","page":null}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]}]}