{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KLEIEJ5XSW6IA4S2Z75LJDTW72","short_pith_number":"pith:KLEIEJ5X","schema_version":"1.0","canonical_sha256":"52c88227b795bc80725acffab48e76feb36d995591235eb56162e2a3708e0977","source":{"kind":"arxiv","id":"2607.22706","version":1},"attestation_state":"computed","paper":{"title":"MPR-CiteG: Enhancing RAG with Multi-Portfolio Retrieval and Citation-Grounded Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Hyewon Lee, Junghyun Oh, Minkyung Song, Seunghoon Han, Sungsu Lim","submitted_at":"2026-07-20T08:17:12Z","abstract_excerpt":"This paper presents the MPR-CiteG framework, which achieved second place in the ScienceON AI Challenge by addressing two fundamental challenges in generative AI: inefficient retrieval and the absence of source verification. We propose a dual-component system, termed MPR-CiteG, in which the Multi-Portfolio Retriever (MPR) efficiently retrieves diverse and relevant information, while the Citation-Grounded Generation (CiteG) module ensures that every generated output remains factually consistent and explicitly attributed to its source. MPR-CiteG represents a significant step toward building more "},"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":"2607.22706","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T08:17:12Z","cross_cats_sorted":["cs.DL","cs.IR"],"title_canon_sha256":"9a03fc2c038c61eed26467f3f4f468c30a9543eb5d389bf11d7460bed1054cd9","abstract_canon_sha256":"d0acd46142157a162866456c53b43ecc441c5e93b3ffd9290d8499284e5a8a44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:50.156754Z","signature_b64":"XJZnI5c9Tf5FvOThomH0GSeS3NxvHi08jxqBaTEbIZz3DEBWzmlWoEkdroNpUwZG4foxFPcQDOWsByynLg8gAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52c88227b795bc80725acffab48e76feb36d995591235eb56162e2a3708e0977","last_reissued_at":"2026-07-28T00:21:50.155829Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:50.155829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MPR-CiteG: Enhancing RAG with Multi-Portfolio Retrieval and Citation-Grounded Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Hyewon Lee, Junghyun Oh, Minkyung Song, Seunghoon Han, Sungsu Lim","submitted_at":"2026-07-20T08:17:12Z","abstract_excerpt":"This paper presents the MPR-CiteG framework, which achieved second place in the ScienceON AI Challenge by addressing two fundamental challenges in generative AI: inefficient retrieval and the absence of source verification. We propose a dual-component system, termed MPR-CiteG, in which the Multi-Portfolio Retriever (MPR) efficiently retrieves diverse and relevant information, while the Citation-Grounded Generation (CiteG) module ensures that every generated output remains factually consistent and explicitly attributed to its source. MPR-CiteG represents a significant step toward building more "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22706","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/2607.22706/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":"2607.22706","created_at":"2026-07-28T00:21:50.156310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22706v1","created_at":"2026-07-28T00:21:50.156310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22706","created_at":"2026-07-28T00:21:50.156310+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLEIEJ5XSW6I","created_at":"2026-07-28T00:21:50.156310+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLEIEJ5XSW6IA4S2","created_at":"2026-07-28T00:21:50.156310+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLEIEJ5X","created_at":"2026-07-28T00:21:50.156310+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/KLEIEJ5XSW6IA4S2Z75LJDTW72","json":"https://pith.science/pith/KLEIEJ5XSW6IA4S2Z75LJDTW72.json","graph_json":"https://pith.science/api/pith-number/KLEIEJ5XSW6IA4S2Z75LJDTW72/graph.json","events_json":"https://pith.science/api/pith-number/KLEIEJ5XSW6IA4S2Z75LJDTW72/events.json","paper":"https://pith.science/paper/KLEIEJ5X"},"agent_actions":{"view_html":"https://pith.science/pith/KLEIEJ5XSW6IA4S2Z75LJDTW72","download_json":"https://pith.science/pith/KLEIEJ5XSW6IA4S2Z75LJDTW72.json","view_paper":"https://pith.science/paper/KLEIEJ5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22706&json=true","fetch_graph":"https://pith.science/api/pith-number/KLEIEJ5XSW6IA4S2Z75LJDTW72/graph.json","fetch_events":"https://pith.science/api/pith-number/KLEIEJ5XSW6IA4S2Z75LJDTW72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLEIEJ5XSW6IA4S2Z75LJDTW72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLEIEJ5XSW6IA4S2Z75LJDTW72/action/storage_attestation","attest_author":"https://pith.science/pith/KLEIEJ5XSW6IA4S2Z75LJDTW72/action/author_attestation","sign_citation":"https://pith.science/pith/KLEIEJ5XSW6IA4S2Z75LJDTW72/action/citation_signature","submit_replication":"https://pith.science/pith/KLEIEJ5XSW6IA4S2Z75LJDTW72/action/replication_record"}},"created_at":"2026-07-28T00:21:50.156310+00:00","updated_at":"2026-07-28T00:21:50.156310+00:00"}