{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L6KJOTXUKW72R6FUVS2XWDA7BL","short_pith_number":"pith:L6KJOTXU","schema_version":"1.0","canonical_sha256":"5f94974ef455bfa8f8b4acb57b0c1f0ae5c90b85f59548896c92ff40869b4ecf","source":{"kind":"arxiv","id":"2407.13101","version":2},"attestation_state":"computed","paper":{"title":"Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lei Liang, Mengshu Sun, Zhiqiang Zhang, Zhouyu Jiang","submitted_at":"2024-07-18T02:19:00Z","abstract_excerpt":"Multi-hop question answering is a challenging task with distinct industrial relevance, and Retrieval-Augmented Generation (RAG) methods based on large language models (LLMs) have become a popular approach to tackle this task. Owing to the potential inability to retrieve all necessary information in a single iteration, a series of iterative RAG methods has been recently developed, showing significant performance improvements. However, existing methods still face two critical challenges: context overload resulting from multiple rounds of retrieval, and over-planning and repetitive planning due t"},"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":"2407.13101","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T02:19:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4ec82508203be73af2efbf3d709d1b5398ebc664264074289c58dbf868010ad8","abstract_canon_sha256":"32d42fce3108bfc065ae9003167ff1a532256f10dd04c3e83b98449d353fd4f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:01.487844Z","signature_b64":"Qdyvj2fVYnrWf/q5hnoDR2OzDGmEbYEvkhmBWFf/jdLiB9tdHpM0f5za9yhPkjkq6vhThHVJsQAv9d+ImknRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f94974ef455bfa8f8b4acb57b0c1f0ae5c90b85f59548896c92ff40869b4ecf","last_reissued_at":"2026-07-05T10:07:01.487375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:01.487375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lei Liang, Mengshu Sun, Zhiqiang Zhang, Zhouyu Jiang","submitted_at":"2024-07-18T02:19:00Z","abstract_excerpt":"Multi-hop question answering is a challenging task with distinct industrial relevance, and Retrieval-Augmented Generation (RAG) methods based on large language models (LLMs) have become a popular approach to tackle this task. Owing to the potential inability to retrieve all necessary information in a single iteration, a series of iterative RAG methods has been recently developed, showing significant performance improvements. However, existing methods still face two critical challenges: context overload resulting from multiple rounds of retrieval, and over-planning and repetitive planning due t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13101","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/2407.13101/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":"2407.13101","created_at":"2026-07-05T10:07:01.487433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13101v2","created_at":"2026-07-05T10:07:01.487433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13101","created_at":"2026-07-05T10:07:01.487433+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6KJOTXUKW72","created_at":"2026-07-05T10:07:01.487433+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6KJOTXUKW72R6FU","created_at":"2026-07-05T10:07:01.487433+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6KJOTXU","created_at":"2026-07-05T10:07:01.487433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.17086","citing_title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00798","citing_title":"Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L6KJOTXUKW72R6FUVS2XWDA7BL","json":"https://pith.science/pith/L6KJOTXUKW72R6FUVS2XWDA7BL.json","graph_json":"https://pith.science/api/pith-number/L6KJOTXUKW72R6FUVS2XWDA7BL/graph.json","events_json":"https://pith.science/api/pith-number/L6KJOTXUKW72R6FUVS2XWDA7BL/events.json","paper":"https://pith.science/paper/L6KJOTXU"},"agent_actions":{"view_html":"https://pith.science/pith/L6KJOTXUKW72R6FUVS2XWDA7BL","download_json":"https://pith.science/pith/L6KJOTXUKW72R6FUVS2XWDA7BL.json","view_paper":"https://pith.science/paper/L6KJOTXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13101&json=true","fetch_graph":"https://pith.science/api/pith-number/L6KJOTXUKW72R6FUVS2XWDA7BL/graph.json","fetch_events":"https://pith.science/api/pith-number/L6KJOTXUKW72R6FUVS2XWDA7BL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6KJOTXUKW72R6FUVS2XWDA7BL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6KJOTXUKW72R6FUVS2XWDA7BL/action/storage_attestation","attest_author":"https://pith.science/pith/L6KJOTXUKW72R6FUVS2XWDA7BL/action/author_attestation","sign_citation":"https://pith.science/pith/L6KJOTXUKW72R6FUVS2XWDA7BL/action/citation_signature","submit_replication":"https://pith.science/pith/L6KJOTXUKW72R6FUVS2XWDA7BL/action/replication_record"}},"created_at":"2026-07-05T10:07:01.487433+00:00","updated_at":"2026-07-05T10:07:01.487433+00:00"}