{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O2UVXUWCA3YAQKTOX7ZT3HYI3O","short_pith_number":"pith:O2UVXUWC","schema_version":"1.0","canonical_sha256":"76a95bd2c206f0082a6ebff33d9f08db9666342750bd1c2c89de3d78e497e51c","source":{"kind":"arxiv","id":"2606.29328","version":1},"attestation_state":"computed","paper":{"title":"Covering the Unseen: Information Demand Coverage Optimization for Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bingxue Zhang, Feida Zhu, Jianying Jia","submitted_at":"2026-06-28T10:49:04Z","abstract_excerpt":"Retrieval-augmented generation (RAG) typically treats context selection as ranking chunks against a single query embedding. This assumption breaks down for complex queries, such as multi-hop or ambiguous questions, where top-k selection tends to over-cover one semantic aspect while ignoring critical sub-questions. We propose GeoRAG, which recasts context selection as Information Demand Coverage Optimization. GeoRAG builds a multi-dimensional demand distribution through diverse sub-query generation and reverse-validation weighting, then selects context by minimizing the Sinkhorn-Wasserstein dis"},"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":"2606.29328","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-28T10:49:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d696ba3bb55721998e782103d162eb6fbb00d90d29620bf120d7ee7431e40fbc","abstract_canon_sha256":"1ba5e121dc4c9d6b3980328208f1e8faef669f32a78f180cc1dc05e6447fb758"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:01.656000Z","signature_b64":"WXm0Ta+xt8yZSb/kin4pmvGh+HUv9t6zHsX8s+O+kU39OAhewEJxMwARDqvF0tjr6lFE7JvIG0A74AU0AdsYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76a95bd2c206f0082a6ebff33d9f08db9666342750bd1c2c89de3d78e497e51c","last_reissued_at":"2026-06-30T01:18:01.655407Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:01.655407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Covering the Unseen: Information Demand Coverage Optimization for Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bingxue Zhang, Feida Zhu, Jianying Jia","submitted_at":"2026-06-28T10:49:04Z","abstract_excerpt":"Retrieval-augmented generation (RAG) typically treats context selection as ranking chunks against a single query embedding. This assumption breaks down for complex queries, such as multi-hop or ambiguous questions, where top-k selection tends to over-cover one semantic aspect while ignoring critical sub-questions. We propose GeoRAG, which recasts context selection as Information Demand Coverage Optimization. GeoRAG builds a multi-dimensional demand distribution through diverse sub-query generation and reverse-validation weighting, then selects context by minimizing the Sinkhorn-Wasserstein dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29328","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/2606.29328/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":"2606.29328","created_at":"2026-06-30T01:18:01.655498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29328v1","created_at":"2026-06-30T01:18:01.655498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29328","created_at":"2026-06-30T01:18:01.655498+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2UVXUWCA3YA","created_at":"2026-06-30T01:18:01.655498+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2UVXUWCA3YAQKTO","created_at":"2026-06-30T01:18:01.655498+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2UVXUWC","created_at":"2026-06-30T01:18:01.655498+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/O2UVXUWCA3YAQKTOX7ZT3HYI3O","json":"https://pith.science/pith/O2UVXUWCA3YAQKTOX7ZT3HYI3O.json","graph_json":"https://pith.science/api/pith-number/O2UVXUWCA3YAQKTOX7ZT3HYI3O/graph.json","events_json":"https://pith.science/api/pith-number/O2UVXUWCA3YAQKTOX7ZT3HYI3O/events.json","paper":"https://pith.science/paper/O2UVXUWC"},"agent_actions":{"view_html":"https://pith.science/pith/O2UVXUWCA3YAQKTOX7ZT3HYI3O","download_json":"https://pith.science/pith/O2UVXUWCA3YAQKTOX7ZT3HYI3O.json","view_paper":"https://pith.science/paper/O2UVXUWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29328&json=true","fetch_graph":"https://pith.science/api/pith-number/O2UVXUWCA3YAQKTOX7ZT3HYI3O/graph.json","fetch_events":"https://pith.science/api/pith-number/O2UVXUWCA3YAQKTOX7ZT3HYI3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2UVXUWCA3YAQKTOX7ZT3HYI3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2UVXUWCA3YAQKTOX7ZT3HYI3O/action/storage_attestation","attest_author":"https://pith.science/pith/O2UVXUWCA3YAQKTOX7ZT3HYI3O/action/author_attestation","sign_citation":"https://pith.science/pith/O2UVXUWCA3YAQKTOX7ZT3HYI3O/action/citation_signature","submit_replication":"https://pith.science/pith/O2UVXUWCA3YAQKTOX7ZT3HYI3O/action/replication_record"}},"created_at":"2026-06-30T01:18:01.655498+00:00","updated_at":"2026-06-30T01:18:01.655498+00:00"}