{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DH2V34HK7NIX3ZKVUCIA5P5IG4","short_pith_number":"pith:DH2V34HK","schema_version":"1.0","canonical_sha256":"19f55df0eafb517de555a0900ebfa8371354e74f1d01b6a6325c001d8ef378a6","source":{"kind":"arxiv","id":"2507.22917","version":1},"attestation_state":"computed","paper":{"title":"Reading Between the Timelines: RAG for Answering Diachronic Questions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Kwun Hang Lau, Ruiyuan Zhang, Weijie Shi, Xiaofang Zhou, Xiaojun Cheng","submitted_at":"2025-07-21T05:19:41Z","abstract_excerpt":"While Retrieval-Augmented Generation (RAG) excels at injecting static, factual knowledge into Large Language Models (LLMs), it exhibits a critical deficit in handling longitudinal queries that require tracking entities and phenomena across time. This blind spot arises because conventional, semantically-driven retrieval methods are not equipped to gather evidence that is both topically relevant and temporally coherent for a specified duration. We address this challenge by proposing a new framework that fundamentally redesigns the RAG pipeline to infuse temporal logic. Our methodology begins by "},"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":"2507.22917","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-21T05:19:41Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"796decd3fa4c4584a21ca63b8f98264af577df17db6da62a7719f74faaaeb374","abstract_canon_sha256":"b441e7c056ffee997ba84de330ad0126e66400c3ade03097d16b42cd10e91e5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:01.670322Z","signature_b64":"B3qNPXKZJQCUjjawE6t16l+odaMSQJlebVDA2y41mmU05829+w6EZOUQzM7lEg/Z3EZUMfA+9AdvEVaHdZZHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19f55df0eafb517de555a0900ebfa8371354e74f1d01b6a6325c001d8ef378a6","last_reissued_at":"2026-07-05T11:46:01.669796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:01.669796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reading Between the Timelines: RAG for Answering Diachronic Questions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Kwun Hang Lau, Ruiyuan Zhang, Weijie Shi, Xiaofang Zhou, Xiaojun Cheng","submitted_at":"2025-07-21T05:19:41Z","abstract_excerpt":"While Retrieval-Augmented Generation (RAG) excels at injecting static, factual knowledge into Large Language Models (LLMs), it exhibits a critical deficit in handling longitudinal queries that require tracking entities and phenomena across time. This blind spot arises because conventional, semantically-driven retrieval methods are not equipped to gather evidence that is both topically relevant and temporally coherent for a specified duration. We address this challenge by proposing a new framework that fundamentally redesigns the RAG pipeline to infuse temporal logic. Our methodology begins by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22917","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/2507.22917/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":"2507.22917","created_at":"2026-07-05T11:46:01.669870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22917v1","created_at":"2026-07-05T11:46:01.669870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22917","created_at":"2026-07-05T11:46:01.669870+00:00"},{"alias_kind":"pith_short_12","alias_value":"DH2V34HK7NIX","created_at":"2026-07-05T11:46:01.669870+00:00"},{"alias_kind":"pith_short_16","alias_value":"DH2V34HK7NIX3ZKV","created_at":"2026-07-05T11:46:01.669870+00:00"},{"alias_kind":"pith_short_8","alias_value":"DH2V34HK","created_at":"2026-07-05T11:46:01.669870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24204","citing_title":"Unified Dominance Graph for Interval-Predicate Approximate Nearest Neighbor Search","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06044","citing_title":"IA-RAG: Interval-Algebra-Driven Temporal Reasoning for Dynamic Knowledge Retrieval","ref_index":14,"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":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DH2V34HK7NIX3ZKVUCIA5P5IG4","json":"https://pith.science/pith/DH2V34HK7NIX3ZKVUCIA5P5IG4.json","graph_json":"https://pith.science/api/pith-number/DH2V34HK7NIX3ZKVUCIA5P5IG4/graph.json","events_json":"https://pith.science/api/pith-number/DH2V34HK7NIX3ZKVUCIA5P5IG4/events.json","paper":"https://pith.science/paper/DH2V34HK"},"agent_actions":{"view_html":"https://pith.science/pith/DH2V34HK7NIX3ZKVUCIA5P5IG4","download_json":"https://pith.science/pith/DH2V34HK7NIX3ZKVUCIA5P5IG4.json","view_paper":"https://pith.science/paper/DH2V34HK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22917&json=true","fetch_graph":"https://pith.science/api/pith-number/DH2V34HK7NIX3ZKVUCIA5P5IG4/graph.json","fetch_events":"https://pith.science/api/pith-number/DH2V34HK7NIX3ZKVUCIA5P5IG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DH2V34HK7NIX3ZKVUCIA5P5IG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DH2V34HK7NIX3ZKVUCIA5P5IG4/action/storage_attestation","attest_author":"https://pith.science/pith/DH2V34HK7NIX3ZKVUCIA5P5IG4/action/author_attestation","sign_citation":"https://pith.science/pith/DH2V34HK7NIX3ZKVUCIA5P5IG4/action/citation_signature","submit_replication":"https://pith.science/pith/DH2V34HK7NIX3ZKVUCIA5P5IG4/action/replication_record"}},"created_at":"2026-07-05T11:46:01.669870+00:00","updated_at":"2026-07-05T11:46:01.669870+00:00"}