{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WC5QVFAEEULIVFOZ2CQ3KME263","short_pith_number":"pith:WC5QVFAE","schema_version":"1.0","canonical_sha256":"b0bb0a940425168a95d9d0a1b5309af6caa4aa0220fcda5b9669f53ff573d8e4","source":{"kind":"arxiv","id":"2401.06072","version":2},"attestation_state":"computed","paper":{"title":"Chain of History: Learning and Forecasting with LLMs for Temporal Knowledge Graph Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Haoling Li, Jiayi Li, Junzhe Li, Ruilin Luo, Tianle Gu, Yujiu Yang, Zicheng Lin","submitted_at":"2024-01-11T17:42:47Z","abstract_excerpt":"Temporal Knowledge Graph Completion (TKGC) is a complex task involving the prediction of missing event links at future timestamps by leveraging established temporal structural knowledge. This paper aims to provide a comprehensive perspective on harnessing the advantages of Large Language Models (LLMs) for reasoning in temporal knowledge graphs, presenting an easily transferable pipeline. In terms of graph modality, we underscore the LLMs' prowess in discerning the structural information of pivotal nodes within the historical chain. As for the generation mode of the LLMs utilized for inference,"},"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":"2401.06072","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-01-11T17:42:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"36ef4702477c2c3047a61b064402a8401b4f86a17a4b838efeeb04b40c65fd7a","abstract_canon_sha256":"08c4578abf1e2b3c86a5c3b48a1bda32e4e5ba305e660cf56983fe28dcaab6ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:58.929381Z","signature_b64":"dXn5A+XtmN16VurozW4LBBHMz8ayfDZVsGfyEZjpS1geYD+g+0wl2Ckx6jY4mE7Ljjs0Dn4OX2p39NndvmxoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0bb0a940425168a95d9d0a1b5309af6caa4aa0220fcda5b9669f53ff573d8e4","last_reissued_at":"2026-07-05T07:44:58.928873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:58.928873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain of History: Learning and Forecasting with LLMs for Temporal Knowledge Graph Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Haoling Li, Jiayi Li, Junzhe Li, Ruilin Luo, Tianle Gu, Yujiu Yang, Zicheng Lin","submitted_at":"2024-01-11T17:42:47Z","abstract_excerpt":"Temporal Knowledge Graph Completion (TKGC) is a complex task involving the prediction of missing event links at future timestamps by leveraging established temporal structural knowledge. This paper aims to provide a comprehensive perspective on harnessing the advantages of Large Language Models (LLMs) for reasoning in temporal knowledge graphs, presenting an easily transferable pipeline. In terms of graph modality, we underscore the LLMs' prowess in discerning the structural information of pivotal nodes within the historical chain. As for the generation mode of the LLMs utilized for inference,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06072","kind":"arxiv","version":2},"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/2401.06072/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":"2401.06072","created_at":"2026-07-05T07:44:58.928934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06072v2","created_at":"2026-07-05T07:44:58.928934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06072","created_at":"2026-07-05T07:44:58.928934+00:00"},{"alias_kind":"pith_short_12","alias_value":"WC5QVFAEEULI","created_at":"2026-07-05T07:44:58.928934+00:00"},{"alias_kind":"pith_short_16","alias_value":"WC5QVFAEEULIVFOZ","created_at":"2026-07-05T07:44:58.928934+00:00"},{"alias_kind":"pith_short_8","alias_value":"WC5QVFAE","created_at":"2026-07-05T07:44:58.928934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31665","citing_title":"ForecastAgentSearch: Towards a Multi-Expert Agent Search System for Geopolitical Event Forecasting","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19042","citing_title":"STK-Adapter: Incorporating Evolving Graph and Event Chain for Temporal Knowledge Graph Extrapolation","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WC5QVFAEEULIVFOZ2CQ3KME263","json":"https://pith.science/pith/WC5QVFAEEULIVFOZ2CQ3KME263.json","graph_json":"https://pith.science/api/pith-number/WC5QVFAEEULIVFOZ2CQ3KME263/graph.json","events_json":"https://pith.science/api/pith-number/WC5QVFAEEULIVFOZ2CQ3KME263/events.json","paper":"https://pith.science/paper/WC5QVFAE"},"agent_actions":{"view_html":"https://pith.science/pith/WC5QVFAEEULIVFOZ2CQ3KME263","download_json":"https://pith.science/pith/WC5QVFAEEULIVFOZ2CQ3KME263.json","view_paper":"https://pith.science/paper/WC5QVFAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06072&json=true","fetch_graph":"https://pith.science/api/pith-number/WC5QVFAEEULIVFOZ2CQ3KME263/graph.json","fetch_events":"https://pith.science/api/pith-number/WC5QVFAEEULIVFOZ2CQ3KME263/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WC5QVFAEEULIVFOZ2CQ3KME263/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WC5QVFAEEULIVFOZ2CQ3KME263/action/storage_attestation","attest_author":"https://pith.science/pith/WC5QVFAEEULIVFOZ2CQ3KME263/action/author_attestation","sign_citation":"https://pith.science/pith/WC5QVFAEEULIVFOZ2CQ3KME263/action/citation_signature","submit_replication":"https://pith.science/pith/WC5QVFAEEULIVFOZ2CQ3KME263/action/replication_record"}},"created_at":"2026-07-05T07:44:58.928934+00:00","updated_at":"2026-07-05T07:44:58.928934+00:00"}