{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YW7HCI7L4XCBMTMRUAWPZBBFSU","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":"5ed16e778b3c95fdd031ffe35804575658ff1f96bbd3a07ce8aadc9ab7d9c043","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T06:37:37Z","title_canon_sha256":"be61b15fbbb15ce1d66885d3421ab5013a33cf587dd2be8e8da6a4b0630032d5"},"schema_version":"1.0","source":{"id":"2410.02247","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02247","created_at":"2026-07-05T11:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02247v3","created_at":"2026-07-05T11:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02247","created_at":"2026-07-05T11:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"YW7HCI7L4XCB","created_at":"2026-07-05T11:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"YW7HCI7L4XCBMTMR","created_at":"2026-07-05T11:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"YW7HCI7L","created_at":"2026-07-05T11:02:39Z"}],"graph_snapshots":[{"event_id":"sha256:b06295378e4303c2d2bb738350b68bbd3bbfd82841d27bd66c0385fbb3873231","target":"graph","created_at":"2026-07-05T11:02:39Z","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/2410.02247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), built on Transformer architectures, exhibit remarkable generalization across a wide range of tasks. However, fine-tuning these models for specific tasks remains resource-intensive due to their extensive parameterization. In this paper, we explore two remarkable phenomena related to the attention mechanism during the fine-tuning of LLMs (where $\\mathbf{W}_q$, $\\mathbf{W}_k$, and $\\mathbf{W}_v$ denote the weights of the query, key, and value layers, respectively). The first phenomenon, termed \"Unequal Importance of Attention Matrices\", highlights the impact of fine-","authors_text":"Bin Wang, Gengze Xu, Hongjin Qian, Jian Luan, Wei Liu, Xiaolin Hu, Xinhao Yao, Yong Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T06:37:37Z","title":"Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02247","kind":"arxiv","version":3},"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":"sha256:66eb4a85ff51fe7e65981ed9f783e4cec55ad8320e6596471531d6599fdedb56","target":"record","created_at":"2026-07-05T11:02:39Z","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":"5ed16e778b3c95fdd031ffe35804575658ff1f96bbd3a07ce8aadc9ab7d9c043","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T06:37:37Z","title_canon_sha256":"be61b15fbbb15ce1d66885d3421ab5013a33cf587dd2be8e8da6a4b0630032d5"},"schema_version":"1.0","source":{"id":"2410.02247","kind":"arxiv","version":3}},"canonical_sha256":"c5be7123ebe5c4164d91a02cfc8425950d94b57ab4e0694c13d9e4ab40d13c0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5be7123ebe5c4164d91a02cfc8425950d94b57ab4e0694c13d9e4ab40d13c0e","first_computed_at":"2026-07-05T11:02:39.792103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:39.792103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OguDtTlLHjyBNmHYbN7nTXpj2ztZn8n8tCp6NemNwpfz8e1pES4ekCCtqq89XTWqwFgZpfy2mi/Hk7rSUx2qBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:39.792574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02247","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66eb4a85ff51fe7e65981ed9f783e4cec55ad8320e6596471531d6599fdedb56","sha256:b06295378e4303c2d2bb738350b68bbd3bbfd82841d27bd66c0385fbb3873231"],"state_sha256":"11697f60d23a4f86c267685e0aaef42372a4e0de2a2a7f60ee05f9d1d98357c9"}