{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PDYQU3MIQQHLC6G2DEBAWD4RQP","short_pith_number":"pith:PDYQU3MI","schema_version":"1.0","canonical_sha256":"78f10a6d88840eb178da19020b0f9183c498fea841d7bad55edad84e83eeb496","source":{"kind":"arxiv","id":"2607.24781","version":1},"attestation_state":"computed","paper":{"title":"Three Sides of Retrieval: Factorial Evidence for Document-Side, Query-Side, and Answer-Side Complementarity in RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Ng S. T. Chong","submitted_at":"2026-06-19T14:33:01Z","abstract_excerpt":"RAG systems rely on chunking, which destroys structural information in documents. Existing heading-based retrieval (Jeong et al., 2025) requires multiple LLM calls per document and returns sub-chunks within matched sections. We introduce ToC-guided page retrieval, which infers headings from visual formatting without LLM calls, embeds them as a parallel index, and loads full page sections. Across 1,280 conditions on 8 enterprise documents (5 to 195 pages), we find: (1) ToC is a significant main effect on answer quality (d = +0.41, p = 0.031), with the largest gains in completeness (+0.40) and u"},"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":"2607.24781","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-19T14:33:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"981887a525a9343b79f6939a3fcd5cf280bc7ba3d1af7546590b2b4470e70aff","abstract_canon_sha256":"3323e3f8c1eec9c029ec2eb7bc85e88eb8fa9de23e7b113e08ac1c1f6ff74a48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:43.686220Z","signature_b64":"+bBYhSO6/rQqSnzFbkD4Ahgq40sDiSvnO2pY2SUMA07ZoMEMzgk4V+T6WBZ2TZmYPPdeYWfvmj201yAbyuVUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78f10a6d88840eb178da19020b0f9183c498fea841d7bad55edad84e83eeb496","last_reissued_at":"2026-07-29T00:24:43.685387Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:43.685387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Three Sides of Retrieval: Factorial Evidence for Document-Side, Query-Side, and Answer-Side Complementarity in RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Ng S. T. Chong","submitted_at":"2026-06-19T14:33:01Z","abstract_excerpt":"RAG systems rely on chunking, which destroys structural information in documents. Existing heading-based retrieval (Jeong et al., 2025) requires multiple LLM calls per document and returns sub-chunks within matched sections. We introduce ToC-guided page retrieval, which infers headings from visual formatting without LLM calls, embeds them as a parallel index, and loads full page sections. Across 1,280 conditions on 8 enterprise documents (5 to 195 pages), we find: (1) ToC is a significant main effect on answer quality (d = +0.41, p = 0.031), with the largest gains in completeness (+0.40) and u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24781","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/2607.24781/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":"2607.24781","created_at":"2026-07-29T00:24:43.685821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24781v1","created_at":"2026-07-29T00:24:43.685821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24781","created_at":"2026-07-29T00:24:43.685821+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDYQU3MIQQHL","created_at":"2026-07-29T00:24:43.685821+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDYQU3MIQQHLC6G2","created_at":"2026-07-29T00:24:43.685821+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDYQU3MI","created_at":"2026-07-29T00:24:43.685821+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/PDYQU3MIQQHLC6G2DEBAWD4RQP","json":"https://pith.science/pith/PDYQU3MIQQHLC6G2DEBAWD4RQP.json","graph_json":"https://pith.science/api/pith-number/PDYQU3MIQQHLC6G2DEBAWD4RQP/graph.json","events_json":"https://pith.science/api/pith-number/PDYQU3MIQQHLC6G2DEBAWD4RQP/events.json","paper":"https://pith.science/paper/PDYQU3MI"},"agent_actions":{"view_html":"https://pith.science/pith/PDYQU3MIQQHLC6G2DEBAWD4RQP","download_json":"https://pith.science/pith/PDYQU3MIQQHLC6G2DEBAWD4RQP.json","view_paper":"https://pith.science/paper/PDYQU3MI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24781&json=true","fetch_graph":"https://pith.science/api/pith-number/PDYQU3MIQQHLC6G2DEBAWD4RQP/graph.json","fetch_events":"https://pith.science/api/pith-number/PDYQU3MIQQHLC6G2DEBAWD4RQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDYQU3MIQQHLC6G2DEBAWD4RQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDYQU3MIQQHLC6G2DEBAWD4RQP/action/storage_attestation","attest_author":"https://pith.science/pith/PDYQU3MIQQHLC6G2DEBAWD4RQP/action/author_attestation","sign_citation":"https://pith.science/pith/PDYQU3MIQQHLC6G2DEBAWD4RQP/action/citation_signature","submit_replication":"https://pith.science/pith/PDYQU3MIQQHLC6G2DEBAWD4RQP/action/replication_record"}},"created_at":"2026-07-29T00:24:43.685821+00:00","updated_at":"2026-07-29T00:24:43.685821+00:00"}