{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FRTDQNNGMVGD4JK7LKEJ2LKSCM","short_pith_number":"pith:FRTDQNNG","schema_version":"1.0","canonical_sha256":"2c663835a6654c3e255f5a889d2d52133deb7d427cd0ea4d7f0b8b89d752d3b8","source":{"kind":"arxiv","id":"2503.02922","version":1},"attestation_state":"computed","paper":{"title":"Optimizing open-domain question answering with graph-based retrieval augmented generation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andreas Mueller, Carlo Curino, Fotis Psallidas, Ha Trinh, Jonathan Larson, Joyce Cahoon, Nick Litombe, Prerna Singh, Yiwen Zhu","submitted_at":"2025-03-04T18:47:17Z","abstract_excerpt":"In this work, we benchmark various graph-based retrieval-augmented generation (RAG) systems across a broad spectrum of query types, including OLTP-style (fact-based) and OLAP-style (thematic) queries, to address the complex demands of open-domain question answering (QA). Traditional RAG methods often fall short in handling nuanced, multi-document synthesis tasks. By structuring knowledge as graphs, we can facilitate the retrieval of context that captures greater semantic depth and enhances language model operations. We explore graph-based RAG methodologies and introduce TREX, a novel, cost-eff"},"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":"2503.02922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2025-03-04T18:47:17Z","cross_cats_sorted":[],"title_canon_sha256":"eda91e5b1cb7c9defbf2a672ecd98ec0279d1fec47f92f222199dd91b843f858","abstract_canon_sha256":"7023abd5385f6ba7cbee96e019a74891b95eebfb8a90718bff1db92e0a3e8fdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:35.146922Z","signature_b64":"EhYHA0OxF+qNrV0W6RwCSV69uTg+U6cCezx0ntx/Q9M08grB4wAzPo/WbI6By8EBo8F094wM4eU73fd6JHJpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c663835a6654c3e255f5a889d2d52133deb7d427cd0ea4d7f0b8b89d752d3b8","last_reissued_at":"2026-07-05T10:24:35.146071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:35.146071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing open-domain question answering with graph-based retrieval augmented generation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andreas Mueller, Carlo Curino, Fotis Psallidas, Ha Trinh, Jonathan Larson, Joyce Cahoon, Nick Litombe, Prerna Singh, Yiwen Zhu","submitted_at":"2025-03-04T18:47:17Z","abstract_excerpt":"In this work, we benchmark various graph-based retrieval-augmented generation (RAG) systems across a broad spectrum of query types, including OLTP-style (fact-based) and OLAP-style (thematic) queries, to address the complex demands of open-domain question answering (QA). Traditional RAG methods often fall short in handling nuanced, multi-document synthesis tasks. By structuring knowledge as graphs, we can facilitate the retrieval of context that captures greater semantic depth and enhances language model operations. We explore graph-based RAG methodologies and introduce TREX, a novel, cost-eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02922","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/2503.02922/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":"2503.02922","created_at":"2026-07-05T10:24:35.146225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02922v1","created_at":"2026-07-05T10:24:35.146225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02922","created_at":"2026-07-05T10:24:35.146225+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRTDQNNGMVGD","created_at":"2026-07-05T10:24:35.146225+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRTDQNNGMVGD4JK7","created_at":"2026-07-05T10:24:35.146225+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRTDQNNG","created_at":"2026-07-05T10:24:35.146225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.13334","citing_title":"A Survey of Context Engineering for Large Language Models","ref_index":106,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FRTDQNNGMVGD4JK7LKEJ2LKSCM","json":"https://pith.science/pith/FRTDQNNGMVGD4JK7LKEJ2LKSCM.json","graph_json":"https://pith.science/api/pith-number/FRTDQNNGMVGD4JK7LKEJ2LKSCM/graph.json","events_json":"https://pith.science/api/pith-number/FRTDQNNGMVGD4JK7LKEJ2LKSCM/events.json","paper":"https://pith.science/paper/FRTDQNNG"},"agent_actions":{"view_html":"https://pith.science/pith/FRTDQNNGMVGD4JK7LKEJ2LKSCM","download_json":"https://pith.science/pith/FRTDQNNGMVGD4JK7LKEJ2LKSCM.json","view_paper":"https://pith.science/paper/FRTDQNNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02922&json=true","fetch_graph":"https://pith.science/api/pith-number/FRTDQNNGMVGD4JK7LKEJ2LKSCM/graph.json","fetch_events":"https://pith.science/api/pith-number/FRTDQNNGMVGD4JK7LKEJ2LKSCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRTDQNNGMVGD4JK7LKEJ2LKSCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRTDQNNGMVGD4JK7LKEJ2LKSCM/action/storage_attestation","attest_author":"https://pith.science/pith/FRTDQNNGMVGD4JK7LKEJ2LKSCM/action/author_attestation","sign_citation":"https://pith.science/pith/FRTDQNNGMVGD4JK7LKEJ2LKSCM/action/citation_signature","submit_replication":"https://pith.science/pith/FRTDQNNGMVGD4JK7LKEJ2LKSCM/action/replication_record"}},"created_at":"2026-07-05T10:24:35.146225+00:00","updated_at":"2026-07-05T10:24:35.146225+00:00"}