{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LINTUUTQIOZXILZRO7TIZLBY5X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7a5a4618e56161ae1e907003c05b4405afa8320187e5fe6775ee98f8b3e64911","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-15T17:43:40Z","title_canon_sha256":"494c189225aeb24c14450140ac40e51270005ed6a04fafc76170fde049807a85"},"schema_version":"1.0","source":{"id":"2309.08586","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08586","created_at":"2026-07-05T07:01:25Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08586v2","created_at":"2026-07-05T07:01:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08586","created_at":"2026-07-05T07:01:25Z"},{"alias_kind":"pith_short_12","alias_value":"LINTUUTQIOZX","created_at":"2026-07-05T07:01:25Z"},{"alias_kind":"pith_short_16","alias_value":"LINTUUTQIOZXILZR","created_at":"2026-07-05T07:01:25Z"},{"alias_kind":"pith_short_8","alias_value":"LINTUUTQ","created_at":"2026-07-05T07:01:25Z"}],"graph_snapshots":[{"event_id":"sha256:012ff79c6eacf4eaa85619183ae85019682de70a4f74276235c4e36b46b3e404","target":"graph","created_at":"2026-07-05T07:01:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.08586/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous research observed accuracy degradation when replacing the attention softmax with a point-wise activation such as ReLU. In the context of vision transformers, we find that this degradation is mitigated when dividing by sequence length. Our experiments training small to large vision transformers on ImageNet-21k indicate that ReLU-attention can approach or match the performance of softmax-attention in terms of scaling behavior as a function of compute.","authors_text":"Jaehoon Lee, Justin Gilmer, Mitchell Wortsman, Simon Kornblith","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-15T17:43:40Z","title":"Replacing softmax with ReLU in Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08586","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b935b4c761f875b19a4b926fc78dea4733b8f266c33332f49a7b9d189fefe4d4","target":"record","created_at":"2026-07-05T07:01:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7a5a4618e56161ae1e907003c05b4405afa8320187e5fe6775ee98f8b3e64911","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-15T17:43:40Z","title_canon_sha256":"494c189225aeb24c14450140ac40e51270005ed6a04fafc76170fde049807a85"},"schema_version":"1.0","source":{"id":"2309.08586","kind":"arxiv","version":2}},"canonical_sha256":"5a1b3a527043b3742f3177e68cac38edf7a0daed1c0638a022e99de4fc059431","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a1b3a527043b3742f3177e68cac38edf7a0daed1c0638a022e99de4fc059431","first_computed_at":"2026-07-05T07:01:25.684007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:25.684007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"To8Pbc5AX+WmQUqwH5WX6OAj2On+nQimC+0Hy6KZQxUntp6Fa5FSwwa9yyq9wrDH202jI30myO2z9Neujz9HBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:25.684475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08586","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b935b4c761f875b19a4b926fc78dea4733b8f266c33332f49a7b9d189fefe4d4","sha256:012ff79c6eacf4eaa85619183ae85019682de70a4f74276235c4e36b46b3e404"],"state_sha256":"c83c94cca6b1c380c4a44adea94e7b6c3e4b9f196369feff25b108426ff854b5"}