{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2ZHKSBQCCIMUL2ZL6DEVUOYEEQ","short_pith_number":"pith:2ZHKSBQC","schema_version":"1.0","canonical_sha256":"d64ea90602121945eb2bf0c95a3b0424012e7ec14880c0167d5a5d13a9803187","source":{"kind":"arxiv","id":"2508.01680","version":1},"attestation_state":"computed","paper":{"title":"T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Biqing Qi, Dong Li, Jianxing Liu, Xiang Zou, Yichen Niu, Ying Ai","submitted_at":"2025-08-03T09:15:36Z","abstract_excerpt":"Large language models (LLMs) have demonstrated strong performance in natural language generation but remain limited in knowle-\n  dge-intensive tasks due to outdated or incomplete internal knowledge. Retrieval-Augmented Generation (RAG) addresses this by incorporating external retrieval, with GraphRAG further enhancing performance through structured knowledge graphs and multi-hop reasoning. However, existing GraphRAG methods largely ignore the temporal dynamics of knowledge, leading to issues such as temporal ambiguity, time-insensitive retrieval, and semantic redundancy. To overcome these limi"},"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":"2508.01680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-03T09:15:36Z","cross_cats_sorted":[],"title_canon_sha256":"e52f068d2564045cc8bb4208627a9cb5b520ae7c8703313739485d2f9786b707","abstract_canon_sha256":"78adf14c1661e842db06d15a6490c0d4866f6e494f2767b76e245559d40cda0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:43.797767Z","signature_b64":"vYewAMHnecXGuLruZePdPfa4D2Xn5IFr6ACbw+mWy1lXF38KG6w9sOctuwx9T4zkL50reRCd3i1ultPkfKfZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d64ea90602121945eb2bf0c95a3b0424012e7ec14880c0167d5a5d13a9803187","last_reissued_at":"2026-07-05T11:47:43.797287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:43.797287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Biqing Qi, Dong Li, Jianxing Liu, Xiang Zou, Yichen Niu, Ying Ai","submitted_at":"2025-08-03T09:15:36Z","abstract_excerpt":"Large language models (LLMs) have demonstrated strong performance in natural language generation but remain limited in knowle-\n  dge-intensive tasks due to outdated or incomplete internal knowledge. Retrieval-Augmented Generation (RAG) addresses this by incorporating external retrieval, with GraphRAG further enhancing performance through structured knowledge graphs and multi-hop reasoning. However, existing GraphRAG methods largely ignore the temporal dynamics of knowledge, leading to issues such as temporal ambiguity, time-insensitive retrieval, and semantic redundancy. To overcome these limi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01680","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/2508.01680/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":"2508.01680","created_at":"2026-07-05T11:47:43.797352+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01680v1","created_at":"2026-07-05T11:47:43.797352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01680","created_at":"2026-07-05T11:47:43.797352+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZHKSBQCCIMU","created_at":"2026-07-05T11:47:43.797352+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZHKSBQCCIMUL2ZL","created_at":"2026-07-05T11:47:43.797352+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZHKSBQC","created_at":"2026-07-05T11:47:43.797352+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14488","citing_title":"Controlling Authority Retrieval: A Missing Retrieval Objective for Authority-Governed Knowledge","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZHKSBQCCIMUL2ZL6DEVUOYEEQ","json":"https://pith.science/pith/2ZHKSBQCCIMUL2ZL6DEVUOYEEQ.json","graph_json":"https://pith.science/api/pith-number/2ZHKSBQCCIMUL2ZL6DEVUOYEEQ/graph.json","events_json":"https://pith.science/api/pith-number/2ZHKSBQCCIMUL2ZL6DEVUOYEEQ/events.json","paper":"https://pith.science/paper/2ZHKSBQC"},"agent_actions":{"view_html":"https://pith.science/pith/2ZHKSBQCCIMUL2ZL6DEVUOYEEQ","download_json":"https://pith.science/pith/2ZHKSBQCCIMUL2ZL6DEVUOYEEQ.json","view_paper":"https://pith.science/paper/2ZHKSBQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01680&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZHKSBQCCIMUL2ZL6DEVUOYEEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZHKSBQCCIMUL2ZL6DEVUOYEEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZHKSBQCCIMUL2ZL6DEVUOYEEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZHKSBQCCIMUL2ZL6DEVUOYEEQ/action/storage_attestation","attest_author":"https://pith.science/pith/2ZHKSBQCCIMUL2ZL6DEVUOYEEQ/action/author_attestation","sign_citation":"https://pith.science/pith/2ZHKSBQCCIMUL2ZL6DEVUOYEEQ/action/citation_signature","submit_replication":"https://pith.science/pith/2ZHKSBQCCIMUL2ZL6DEVUOYEEQ/action/replication_record"}},"created_at":"2026-07-05T11:47:43.797352+00:00","updated_at":"2026-07-05T11:47:43.797352+00:00"}