{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KDBLNNFTWIEM5C3MG4OCHUBWP7","short_pith_number":"pith:KDBLNNFT","schema_version":"1.0","canonical_sha256":"50c2b6b4b3b208ce8b6c371c23d0367fcf9be368ece853676adf486c8ea1195b","source":{"kind":"arxiv","id":"2503.01695","version":1},"attestation_state":"computed","paper":{"title":"Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdalla Moustafa, Helen Meng, Hongyin Luo, James Glass, Kun Li, Tianhua Zhang, Xixin Wu, Yunxiang Li","submitted_at":"2025-03-03T16:08:33Z","abstract_excerpt":"Improving context faithfulness in large language models is essential for developing trustworthy retrieval augmented generation systems and mitigating hallucinations, especially in long-form question answering (LFQA) tasks or scenarios involving knowledge conflicts. Existing methods either intervene LLMs only at inference without addressing their inherent limitations or overlook the potential for self-improvement. In this paper, we introduce GenDiE (Generate, Discriminate, Evolve), a novel self-evolving framework that enhances context faithfulness through fine-grained sentence-level optimizatio"},"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":"2503.01695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T16:08:33Z","cross_cats_sorted":[],"title_canon_sha256":"7d08e4d0c79c8d038a1239a33d31d9676310a22d13c991720a9d8cd7ac1570c9","abstract_canon_sha256":"f98f25a09f108d79cb99c0412d5d1e6441b6dc195879365455e462c55e493a09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:12.647889Z","signature_b64":"9gzhfs9oMyEfU/MEI2/1ezyMLaGBQZwB2jU0DYbJtJg6LjE3szzQoYnO8XmwE5nF4Azww3cu7c6x+oTzCCSCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50c2b6b4b3b208ce8b6c371c23d0367fcf9be368ece853676adf486c8ea1195b","last_reissued_at":"2026-07-05T10:23:12.647307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:12.647307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdalla Moustafa, Helen Meng, Hongyin Luo, James Glass, Kun Li, Tianhua Zhang, Xixin Wu, Yunxiang Li","submitted_at":"2025-03-03T16:08:33Z","abstract_excerpt":"Improving context faithfulness in large language models is essential for developing trustworthy retrieval augmented generation systems and mitigating hallucinations, especially in long-form question answering (LFQA) tasks or scenarios involving knowledge conflicts. Existing methods either intervene LLMs only at inference without addressing their inherent limitations or overlook the potential for self-improvement. In this paper, we introduce GenDiE (Generate, Discriminate, Evolve), a novel self-evolving framework that enhances context faithfulness through fine-grained sentence-level optimizatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01695","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/2503.01695/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":"2503.01695","created_at":"2026-07-05T10:23:12.647397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01695v1","created_at":"2026-07-05T10:23:12.647397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01695","created_at":"2026-07-05T10:23:12.647397+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDBLNNFTWIEM","created_at":"2026-07-05T10:23:12.647397+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDBLNNFTWIEM5C3M","created_at":"2026-07-05T10:23:12.647397+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDBLNNFT","created_at":"2026-07-05T10:23:12.647397+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/KDBLNNFTWIEM5C3MG4OCHUBWP7","json":"https://pith.science/pith/KDBLNNFTWIEM5C3MG4OCHUBWP7.json","graph_json":"https://pith.science/api/pith-number/KDBLNNFTWIEM5C3MG4OCHUBWP7/graph.json","events_json":"https://pith.science/api/pith-number/KDBLNNFTWIEM5C3MG4OCHUBWP7/events.json","paper":"https://pith.science/paper/KDBLNNFT"},"agent_actions":{"view_html":"https://pith.science/pith/KDBLNNFTWIEM5C3MG4OCHUBWP7","download_json":"https://pith.science/pith/KDBLNNFTWIEM5C3MG4OCHUBWP7.json","view_paper":"https://pith.science/paper/KDBLNNFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01695&json=true","fetch_graph":"https://pith.science/api/pith-number/KDBLNNFTWIEM5C3MG4OCHUBWP7/graph.json","fetch_events":"https://pith.science/api/pith-number/KDBLNNFTWIEM5C3MG4OCHUBWP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDBLNNFTWIEM5C3MG4OCHUBWP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDBLNNFTWIEM5C3MG4OCHUBWP7/action/storage_attestation","attest_author":"https://pith.science/pith/KDBLNNFTWIEM5C3MG4OCHUBWP7/action/author_attestation","sign_citation":"https://pith.science/pith/KDBLNNFTWIEM5C3MG4OCHUBWP7/action/citation_signature","submit_replication":"https://pith.science/pith/KDBLNNFTWIEM5C3MG4OCHUBWP7/action/replication_record"}},"created_at":"2026-07-05T10:23:12.647397+00:00","updated_at":"2026-07-05T10:23:12.647397+00:00"}