{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LCALJJ6GJB673XVXNJVTUBTXR4","short_pith_number":"pith:LCALJJ6G","schema_version":"1.0","canonical_sha256":"5880b4a7c6487dfddeb76a6b3a06778f14585498f9622b89c09de65ea84948de","source":{"kind":"arxiv","id":"2507.13396","version":1},"attestation_state":"computed","paper":{"title":"DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Haonan Yuan, Jianxin Li, Jiaqi Yuan, Philip S. Yu, Qingyun Sun, Shan He, Xiao Guan, Xingcheng Fu","submitted_at":"2025-07-16T10:22:35Z","abstract_excerpt":"Graph Retrieval-Augmented Generation has emerged as a powerful paradigm for grounding large language models with external structured knowledge. However, existing Graph RAG methods struggle with temporal reasoning, due to their inability to model the evolving structure and order of real-world events. In this work, we introduce DyG-RAG, a novel event-centric dynamic graph retrieval-augmented generation framework designed to capture and reason over temporal knowledge embedded in unstructured text. To eliminate temporal ambiguity in traditional retrieval units, DyG-RAG proposes Dynamic Event Units"},"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":"2507.13396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-07-16T10:22:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d2fe3632badab0a86495ac52a8e43104630c97110b36b341aa6e5eb20c7c8bd0","abstract_canon_sha256":"586db7acd4330ef5a324d666a1bdc9d95eed9ba56c1e90adfb21a4b9a9b60899"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:16.765396Z","signature_b64":"JdoWkrjGfR0l9/HHf4xrJtj9384Hztu6gc7sI87v5bVMX9u92bwoidsTrMPqcSME6PPFAGnt1m8pxQzmMJO1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5880b4a7c6487dfddeb76a6b3a06778f14585498f9622b89c09de65ea84948de","last_reissued_at":"2026-07-05T11:39:16.764914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:16.764914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Haonan Yuan, Jianxin Li, Jiaqi Yuan, Philip S. Yu, Qingyun Sun, Shan He, Xiao Guan, Xingcheng Fu","submitted_at":"2025-07-16T10:22:35Z","abstract_excerpt":"Graph Retrieval-Augmented Generation has emerged as a powerful paradigm for grounding large language models with external structured knowledge. However, existing Graph RAG methods struggle with temporal reasoning, due to their inability to model the evolving structure and order of real-world events. In this work, we introduce DyG-RAG, a novel event-centric dynamic graph retrieval-augmented generation framework designed to capture and reason over temporal knowledge embedded in unstructured text. To eliminate temporal ambiguity in traditional retrieval units, DyG-RAG proposes Dynamic Event Units"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13396","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/2507.13396/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":"2507.13396","created_at":"2026-07-05T11:39:16.764973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13396v1","created_at":"2026-07-05T11:39:16.764973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13396","created_at":"2026-07-05T11:39:16.764973+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCALJJ6GJB67","created_at":"2026-07-05T11:39:16.764973+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCALJJ6GJB673XVX","created_at":"2026-07-05T11:39:16.764973+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCALJJ6G","created_at":"2026-07-05T11:39:16.764973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21124","citing_title":"PulseCX: Breaking the Closed-World Assumption in Real-Time CX","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06044","citing_title":"IA-RAG: Interval-Algebra-Driven Temporal Reasoning for Dynamic Knowledge Retrieval","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14169","citing_title":"Chronological Knowledge Retrieval: A Retrieval-Augmented Generation Approach to Construction Project Documentation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12185","citing_title":"Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07392","citing_title":"Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCALJJ6GJB673XVXNJVTUBTXR4","json":"https://pith.science/pith/LCALJJ6GJB673XVXNJVTUBTXR4.json","graph_json":"https://pith.science/api/pith-number/LCALJJ6GJB673XVXNJVTUBTXR4/graph.json","events_json":"https://pith.science/api/pith-number/LCALJJ6GJB673XVXNJVTUBTXR4/events.json","paper":"https://pith.science/paper/LCALJJ6G"},"agent_actions":{"view_html":"https://pith.science/pith/LCALJJ6GJB673XVXNJVTUBTXR4","download_json":"https://pith.science/pith/LCALJJ6GJB673XVXNJVTUBTXR4.json","view_paper":"https://pith.science/paper/LCALJJ6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13396&json=true","fetch_graph":"https://pith.science/api/pith-number/LCALJJ6GJB673XVXNJVTUBTXR4/graph.json","fetch_events":"https://pith.science/api/pith-number/LCALJJ6GJB673XVXNJVTUBTXR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCALJJ6GJB673XVXNJVTUBTXR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCALJJ6GJB673XVXNJVTUBTXR4/action/storage_attestation","attest_author":"https://pith.science/pith/LCALJJ6GJB673XVXNJVTUBTXR4/action/author_attestation","sign_citation":"https://pith.science/pith/LCALJJ6GJB673XVXNJVTUBTXR4/action/citation_signature","submit_replication":"https://pith.science/pith/LCALJJ6GJB673XVXNJVTUBTXR4/action/replication_record"}},"created_at":"2026-07-05T11:39:16.764973+00:00","updated_at":"2026-07-05T11:39:16.764973+00:00"}