{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FDDLIKUK3YF54SR6DEIIG72ACS","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":"2994f983dfca421c35155689b31455ef96ebe79876724e38847a3d2d20f2f9e9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-04T21:30:21Z","title_canon_sha256":"001182d7b223ebecaedf3cd925e897bd953a4781c04272aa4d5b5e74ab446590"},"schema_version":"1.0","source":{"id":"2309.01826","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.01826","created_at":"2026-07-05T07:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2309.01826v2","created_at":"2026-07-05T07:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01826","created_at":"2026-07-05T07:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"FDDLIKUK3YF5","created_at":"2026-07-05T07:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"FDDLIKUK3YF54SR6","created_at":"2026-07-05T07:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"FDDLIKUK","created_at":"2026-07-05T07:03:30Z"}],"graph_snapshots":[{"event_id":"sha256:c1370693350d3713848ae30c20856d9f5c8b6672d85348751ee4f6940b2d3273","target":"graph","created_at":"2026-07-05T07:03:30Z","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/2309.01826/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Transformer architecture has two main non-embedding components: Attention and the Feed Forward Network (FFN). Attention captures interdependencies between words regardless of their position, while the FFN non-linearly transforms each input token independently. In this work we explore the role of the FFN, and find that despite taking up a significant fraction of the model's parameters, it is highly redundant. Concretely, we are able to substantially reduce the number of parameters with only a modest drop in accuracy by removing the FFN on the decoder layers and sharing a single FFN across t","authors_text":"Ant\\'onio V. Lopes, Hendra Setiawan, Telmo Pessoa Pires, Yannick Assogba","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-04T21:30:21Z","title":"One Wide Feedforward is All You Need"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01826","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":"sha256:3eaf5102ed7a49341c58c1428dd03e49b9985fdb20166dfadbcb34070285e238","target":"record","created_at":"2026-07-05T07:03:30Z","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":"2994f983dfca421c35155689b31455ef96ebe79876724e38847a3d2d20f2f9e9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-04T21:30:21Z","title_canon_sha256":"001182d7b223ebecaedf3cd925e897bd953a4781c04272aa4d5b5e74ab446590"},"schema_version":"1.0","source":{"id":"2309.01826","kind":"arxiv","version":2}},"canonical_sha256":"28c6b42a8ade0bde4a3e1910837f401482116bee14c1489374380faf9ef38592","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28c6b42a8ade0bde4a3e1910837f401482116bee14c1489374380faf9ef38592","first_computed_at":"2026-07-05T07:03:30.640862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:30.640862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zeX3GKUj5QhX/kPq0hW/Tewrvg3eJHnZqNzZYs2u3v+FImUnlCauzUYBEclBhHD0ReEbAmk5bSKtgIJK3OsRCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:30.641426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.01826","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3eaf5102ed7a49341c58c1428dd03e49b9985fdb20166dfadbcb34070285e238","sha256:c1370693350d3713848ae30c20856d9f5c8b6672d85348751ee4f6940b2d3273"],"state_sha256":"2ad2806c03a7750ede58ca18ac6e50803a756d31a1f0cd28cfc843a09a74c456"}