{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PIDIHPJDIOIYCRYW7QXEWC3QLS","short_pith_number":"pith:PIDIHPJD","schema_version":"1.0","canonical_sha256":"7a0683bd234391814716fc2e4b0b705cb9dd1688880e1702a36aa6fc09c804c9","source":{"kind":"arxiv","id":"2403.17359","version":2},"attestation_state":"computed","paper":{"title":"Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Liu, Haozheng Luo, Manling Li, Zhenyu Pan","submitted_at":"2024-03-26T03:51:01Z","abstract_excerpt":"We present a Chain-of-Action (CoA) framework for multimodal and retrieval-augmented Question-Answering (QA). Compared to the literature, CoA overcomes two major challenges of current QA applications: (i) unfaithful hallucination that is inconsistent with real-time or domain facts and (ii) weak reasoning performance over compositional information. Our key contribution is a novel reasoning-retrieval mechanism that decomposes a complex question into a reasoning chain via systematic prompting and pre-designed actions. Methodologically, we propose three types of domain-adaptable `Plug-and-Play' act"},"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":"2403.17359","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T03:51:01Z","cross_cats_sorted":[],"title_canon_sha256":"414e73338138f97e415e127d172202c538c5d07761e85315830495ae3b10224a","abstract_canon_sha256":"4a7b50bb71390678a1cb52bad2c1a339a55661adc0485d2a8c19412d347a9dce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:46.659974Z","signature_b64":"yE/r6pQ262kjOL0gZ6TZZDnTzslFSfNg4vY1q+DSkKOCrUF01Meziu5GxL4ZaMxC6gt9KL6V3OwvEH309cAUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a0683bd234391814716fc2e4b0b705cb9dd1688880e1702a36aa6fc09c804c9","last_reissued_at":"2026-07-05T10:17:46.659453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:46.659453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Liu, Haozheng Luo, Manling Li, Zhenyu Pan","submitted_at":"2024-03-26T03:51:01Z","abstract_excerpt":"We present a Chain-of-Action (CoA) framework for multimodal and retrieval-augmented Question-Answering (QA). Compared to the literature, CoA overcomes two major challenges of current QA applications: (i) unfaithful hallucination that is inconsistent with real-time or domain facts and (ii) weak reasoning performance over compositional information. Our key contribution is a novel reasoning-retrieval mechanism that decomposes a complex question into a reasoning chain via systematic prompting and pre-designed actions. Methodologically, we propose three types of domain-adaptable `Plug-and-Play' act"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17359","kind":"arxiv","version":2},"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/2403.17359/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2403.17359","created_at":"2026-07-05T10:17:46.659526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17359v2","created_at":"2026-07-05T10:17:46.659526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17359","created_at":"2026-07-05T10:17:46.659526+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIDIHPJDIOIY","created_at":"2026-07-05T10:17:46.659526+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIDIHPJDIOIYCRYW","created_at":"2026-07-05T10:17:46.659526+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIDIHPJD","created_at":"2026-07-05T10:17:46.659526+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01284","citing_title":"Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00959","citing_title":"Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18027","citing_title":"PDF Retrieval Augmented Question Answering","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2504.14239","citing_title":"InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2503.16419","citing_title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06165","citing_title":"Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost","ref_index":186,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01284","citing_title":"Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PIDIHPJDIOIYCRYW7QXEWC3QLS","json":"https://pith.science/pith/PIDIHPJDIOIYCRYW7QXEWC3QLS.json","graph_json":"https://pith.science/api/pith-number/PIDIHPJDIOIYCRYW7QXEWC3QLS/graph.json","events_json":"https://pith.science/api/pith-number/PIDIHPJDIOIYCRYW7QXEWC3QLS/events.json","paper":"https://pith.science/paper/PIDIHPJD"},"agent_actions":{"view_html":"https://pith.science/pith/PIDIHPJDIOIYCRYW7QXEWC3QLS","download_json":"https://pith.science/pith/PIDIHPJDIOIYCRYW7QXEWC3QLS.json","view_paper":"https://pith.science/paper/PIDIHPJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17359&json=true","fetch_graph":"https://pith.science/api/pith-number/PIDIHPJDIOIYCRYW7QXEWC3QLS/graph.json","fetch_events":"https://pith.science/api/pith-number/PIDIHPJDIOIYCRYW7QXEWC3QLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIDIHPJDIOIYCRYW7QXEWC3QLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIDIHPJDIOIYCRYW7QXEWC3QLS/action/storage_attestation","attest_author":"https://pith.science/pith/PIDIHPJDIOIYCRYW7QXEWC3QLS/action/author_attestation","sign_citation":"https://pith.science/pith/PIDIHPJDIOIYCRYW7QXEWC3QLS/action/citation_signature","submit_replication":"https://pith.science/pith/PIDIHPJDIOIYCRYW7QXEWC3QLS/action/replication_record"}},"created_at":"2026-07-05T10:17:46.659526+00:00","updated_at":"2026-07-05T10:17:46.659526+00:00"}