{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZYZJCU5OXM455IHG66OQBXNSKP","short_pith_number":"pith:ZYZJCU5O","schema_version":"1.0","canonical_sha256":"ce329153aebb39dea0e6f79d00ddb253cbd318f243e406d3e2484111ff1520a3","source":{"kind":"arxiv","id":"2605.17352","version":1},"attestation_state":"computed","paper":{"title":"AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Chen, Chengyu Wang, Dongyang Li, Jiuheng Wan, Qizhou Chen, Richang Hong, Taolin Zhang, Xiaofeng He","submitted_at":"2026-05-17T09:45:24Z","abstract_excerpt":"Despite substantial advances in large language models (LLMs), generating factually consistent responses for knowledge-intensive question answering remains challenging. These difficulties are primarily due to hallucinations and the limitations of LLMs in bridging long-tail knowledge gaps. To address this, we propose AMATA, an Adaptive Multi-Agent Trajectory Alignment framework that dynamically integrates external knowledge to improve response interpretability and factual grounding. Our architecture leverages six specialized agents that collaboratively perform structured actions for complex ques"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.17352","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-17T09:45:24Z","cross_cats_sorted":[],"title_canon_sha256":"9f4a253d770d3b3b4a80874b6513cb2bc2ea0bb05ff6d7c90aa7ac7c0de06d46","abstract_canon_sha256":"424ea3a180da8a21a60f487a43c0ac9ecec437d87fd5d733da11357849d8659c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:53.718586Z","signature_b64":"qBQg7OeA1EynwZhIjmWgqPeiW7cc7pIqMDUBD9/RkN+qqNpu43LCZIIhWdIYVKdKi//EZ/JI7xjAvMJmJQ4FDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce329153aebb39dea0e6f79d00ddb253cbd318f243e406d3e2484111ff1520a3","last_reissued_at":"2026-05-20T00:03:53.717702Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:53.717702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Chen, Chengyu Wang, Dongyang Li, Jiuheng Wan, Qizhou Chen, Richang Hong, Taolin Zhang, Xiaofeng He","submitted_at":"2026-05-17T09:45:24Z","abstract_excerpt":"Despite substantial advances in large language models (LLMs), generating factually consistent responses for knowledge-intensive question answering remains challenging. These difficulties are primarily due to hallucinations and the limitations of LLMs in bridging long-tail knowledge gaps. To address this, we propose AMATA, an Adaptive Multi-Agent Trajectory Alignment framework that dynamically integrates external knowledge to improve response interpretability and factual grounding. Our architecture leverages six specialized agents that collaboratively perform structured actions for complex ques"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17352","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17352/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.793107Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.725646Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"aaa5bbe50280e25ebf9f359ece76bad67dbd6e0333ffef295c679be6cb45a8a6"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.17352","created_at":"2026-05-20T00:03:53.717840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17352v1","created_at":"2026-05-20T00:03:53.717840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17352","created_at":"2026-05-20T00:03:53.717840+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZYZJCU5OXM45","created_at":"2026-05-20T00:03:53.717840+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZYZJCU5OXM455IHG","created_at":"2026-05-20T00:03:53.717840+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZYZJCU5O","created_at":"2026-05-20T00:03:53.717840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZYZJCU5OXM455IHG66OQBXNSKP","json":"https://pith.science/pith/ZYZJCU5OXM455IHG66OQBXNSKP.json","graph_json":"https://pith.science/api/pith-number/ZYZJCU5OXM455IHG66OQBXNSKP/graph.json","events_json":"https://pith.science/api/pith-number/ZYZJCU5OXM455IHG66OQBXNSKP/events.json","paper":"https://pith.science/paper/ZYZJCU5O"},"agent_actions":{"view_html":"https://pith.science/pith/ZYZJCU5OXM455IHG66OQBXNSKP","download_json":"https://pith.science/pith/ZYZJCU5OXM455IHG66OQBXNSKP.json","view_paper":"https://pith.science/paper/ZYZJCU5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17352&json=true","fetch_graph":"https://pith.science/api/pith-number/ZYZJCU5OXM455IHG66OQBXNSKP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZYZJCU5OXM455IHG66OQBXNSKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZYZJCU5OXM455IHG66OQBXNSKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZYZJCU5OXM455IHG66OQBXNSKP/action/storage_attestation","attest_author":"https://pith.science/pith/ZYZJCU5OXM455IHG66OQBXNSKP/action/author_attestation","sign_citation":"https://pith.science/pith/ZYZJCU5OXM455IHG66OQBXNSKP/action/citation_signature","submit_replication":"https://pith.science/pith/ZYZJCU5OXM455IHG66OQBXNSKP/action/replication_record"}},"created_at":"2026-05-20T00:03:53.717840+00:00","updated_at":"2026-05-20T00:03:53.717840+00:00"}