{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KA3ACDQLNN5WQF4KRJVN2VGOXZ","short_pith_number":"pith:KA3ACDQL","schema_version":"1.0","canonical_sha256":"5036010e0b6b7b68178a8a6add54cebe4e32456ae208e380650a995752024350","source":{"kind":"arxiv","id":"2509.04820","version":1},"attestation_state":"computed","paper":{"title":"Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gang Su, Huifeng Lin, Jintao Liang, Rui Zhao, You Wu, Ziyue Li","submitted_at":"2025-09-05T05:44:50Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) based on Large Language Models (LLMs) is a powerful solution to understand and query the industry's closed-source documents. However, basic RAG often struggles with complex QA tasks in legal and regulatory domains, particularly when dealing with numerous government documents. The top-$k$ strategy frequently misses golden chunks, leading to incomplete or inaccurate answers. To address these retrieval bottlenecks, we explore two strategies to improve evidence coverage and answer quality. The first is a One-SHOT retrieval method that adaptively selects chunks "},"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":"2509.04820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-09-05T05:44:50Z","cross_cats_sorted":[],"title_canon_sha256":"4888e0f8cbc36f5309720ad674e0cff2b599c8f2eea99e3ec6c10ab230f4c57b","abstract_canon_sha256":"d58a36933b2440b5df73db8eff02fef6b1fbf0df773f3d231f791881b9d97ff8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:30.298157Z","signature_b64":"ALmoex8FGFWNdo3dYE9olisdhGoCx1a0tUZqUfG/ikeE7At3G1tTuxxezpL54Z99yN2ZbhcxWM3z7ksKzmV+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5036010e0b6b7b68178a8a6add54cebe4e32456ae208e380650a995752024350","last_reissued_at":"2026-07-05T12:05:30.297694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:30.297694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gang Su, Huifeng Lin, Jintao Liang, Rui Zhao, You Wu, Ziyue Li","submitted_at":"2025-09-05T05:44:50Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) based on Large Language Models (LLMs) is a powerful solution to understand and query the industry's closed-source documents. However, basic RAG often struggles with complex QA tasks in legal and regulatory domains, particularly when dealing with numerous government documents. The top-$k$ strategy frequently misses golden chunks, leading to incomplete or inaccurate answers. To address these retrieval bottlenecks, we explore two strategies to improve evidence coverage and answer quality. The first is a One-SHOT retrieval method that adaptively selects chunks "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04820","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/2509.04820/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":"2509.04820","created_at":"2026-07-05T12:05:30.297755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04820v1","created_at":"2026-07-05T12:05:30.297755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04820","created_at":"2026-07-05T12:05:30.297755+00:00"},{"alias_kind":"pith_short_12","alias_value":"KA3ACDQLNN5W","created_at":"2026-07-05T12:05:30.297755+00:00"},{"alias_kind":"pith_short_16","alias_value":"KA3ACDQLNN5WQF4K","created_at":"2026-07-05T12:05:30.297755+00:00"},{"alias_kind":"pith_short_8","alias_value":"KA3ACDQL","created_at":"2026-07-05T12:05:30.297755+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/KA3ACDQLNN5WQF4KRJVN2VGOXZ","json":"https://pith.science/pith/KA3ACDQLNN5WQF4KRJVN2VGOXZ.json","graph_json":"https://pith.science/api/pith-number/KA3ACDQLNN5WQF4KRJVN2VGOXZ/graph.json","events_json":"https://pith.science/api/pith-number/KA3ACDQLNN5WQF4KRJVN2VGOXZ/events.json","paper":"https://pith.science/paper/KA3ACDQL"},"agent_actions":{"view_html":"https://pith.science/pith/KA3ACDQLNN5WQF4KRJVN2VGOXZ","download_json":"https://pith.science/pith/KA3ACDQLNN5WQF4KRJVN2VGOXZ.json","view_paper":"https://pith.science/paper/KA3ACDQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04820&json=true","fetch_graph":"https://pith.science/api/pith-number/KA3ACDQLNN5WQF4KRJVN2VGOXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KA3ACDQLNN5WQF4KRJVN2VGOXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KA3ACDQLNN5WQF4KRJVN2VGOXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KA3ACDQLNN5WQF4KRJVN2VGOXZ/action/storage_attestation","attest_author":"https://pith.science/pith/KA3ACDQLNN5WQF4KRJVN2VGOXZ/action/author_attestation","sign_citation":"https://pith.science/pith/KA3ACDQLNN5WQF4KRJVN2VGOXZ/action/citation_signature","submit_replication":"https://pith.science/pith/KA3ACDQLNN5WQF4KRJVN2VGOXZ/action/replication_record"}},"created_at":"2026-07-05T12:05:30.297755+00:00","updated_at":"2026-07-05T12:05:30.297755+00:00"}