{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QRZVECMPSOKANJJI2LRG7AL3BC","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":"14de0cd5b16221fecbf79843c8a5464aeacd17ea7bcc8408ee094eb1e8274801","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T09:31:27Z","title_canon_sha256":"f24f663a01ced2bf48f6caa8e14a9b7c582c9ecf8317b1d9e34d4858447e9794"},"schema_version":"1.0","source":{"id":"2502.03029","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03029","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03029v3","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03029","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"pith_short_12","alias_value":"QRZVECMPSOKA","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"pith_short_16","alias_value":"QRZVECMPSOKANJJI","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"pith_short_8","alias_value":"QRZVECMP","created_at":"2026-07-05T11:23:23Z"}],"graph_snapshots":[{"event_id":"sha256:aa96949a7f1a78f88007c36ae74e09a6a0e2ce15510a60ebcc60c9ededfa9618","target":"graph","created_at":"2026-07-05T11:23:23Z","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/2502.03029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The LLaMA-Adapter has recently emerged as an efficient fine-tuning technique for LLaMA models, leveraging zero-initialized attention to stabilize training and enhance performance. However, despite its empirical success, the theoretical foundations of zero-initialized attention remain largely unexplored. In this paper, we provide a rigorous theoretical analysis, establishing a connection between zero-initialized attention and mixture-of-expert models. We prove that both linear and non-linear prompts, along with gating functions, can be optimally estimated, with non-linear prompts offering great","authors_text":"Chau Nguyen, Daniel Sonntag, Duy M. H. Nguyen, Huy Nguyen, Mathias Niepert, Minh Le, Nghiem T. Diep, Nhat Ho","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T09:31:27Z","title":"On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03029","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":"sha256:35171cde17937828c682050a8cf53edfdac63d706759f25ea4acae0abb987fcc","target":"record","created_at":"2026-07-05T11:23:23Z","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":"14de0cd5b16221fecbf79843c8a5464aeacd17ea7bcc8408ee094eb1e8274801","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T09:31:27Z","title_canon_sha256":"f24f663a01ced2bf48f6caa8e14a9b7c582c9ecf8317b1d9e34d4858447e9794"},"schema_version":"1.0","source":{"id":"2502.03029","kind":"arxiv","version":3}},"canonical_sha256":"847352098f939406a528d2e26f817b0893d9e58feba2979edc7efa1e18049d9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"847352098f939406a528d2e26f817b0893d9e58feba2979edc7efa1e18049d9f","first_computed_at":"2026-07-05T11:23:23.095082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:23.095082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IC7EijnmckDBqMG2rFkKQ2w0sxSDd/ZCyuJqKTnwPlToX8UVdEnvGuHIzX0vtQlondCm8EplFOsbHG+YTETJCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:23.095611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03029","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35171cde17937828c682050a8cf53edfdac63d706759f25ea4acae0abb987fcc","sha256:aa96949a7f1a78f88007c36ae74e09a6a0e2ce15510a60ebcc60c9ededfa9618"],"state_sha256":"6c9c34e44b0e4b2a85fd861096dcf32612ee0681fbbf24a94f52a6b3d4c82ccc"}