{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TPQWBXF7ORZP7C4ZDJQFEANWNM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6dfa3210baed528db536bbd52e1ec16853b5e7a32dca7f89bce191ed2410e7ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-03T12:30:15Z","title_canon_sha256":"7b912831a2aac1f62b93f8fbbd19e92e18a3b7c3accb08fc1a253f03d3e45b79"},"schema_version":"1.0","source":{"id":"2605.12518","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12518","created_at":"2026-05-18T03:10:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12518v1","created_at":"2026-05-18T03:10:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12518","created_at":"2026-05-18T03:10:02Z"},{"alias_kind":"pith_short_12","alias_value":"TPQWBXF7ORZP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TPQWBXF7ORZP7C4Z","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TPQWBXF7","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c31eb0d0728a2d6efbc9845be2c9d23e63857e9572518f9bb460355eaad072eb","target":"graph","created_at":"2026-05-18T03:10:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experimental results on open-domain TLS datasets demonstrate that TimelineReasoner significantly outperforms existing LLM-based TLS methods in terms of timeline accuracy, coverage, and coherence."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the specialized mechanisms (Event Scraper, Timeline Updater, Supervisor) and the two-stage reasoning process can be implemented reliably on top of existing large reasoning models without introducing new hallucinations or retrieval errors that undermine the claimed gains."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TimelineReasoner applies large reasoning models in a Global Cognition plus Detail Exploration loop to produce more accurate, complete, and coherent timelines from news than prior LLM-based methods."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"TimelineReasoner uses large reasoning models to actively track events globally and fill gaps through targeted retrieval, producing more accurate and coherent timelines than passive LLM approaches."}],"snapshot_sha256":"cb2422a2ef1b160c85681aec727e2fe4abb9cbbeaaca92f7825c06f47cb454ac"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7507869a215cf65b904b15a0f51f0844763dbd9658d54e19c807d576728b2f16"},"paper":{"abstract_excerpt":"The proliferation of online news poses a challenge to extracting structured timelines from unstructured content. While recent studies have shown that Large Language Models (LLMs) can assist Timeline Summarization (TLS), these approaches primarily treat models as passive generators. The emergence of Large Reasoning Models (LRMs) presents an opportunity to reason over events actively, enabling iterative evidence acquisition, the detection of missing events, and the validation of temporal consistency. To systematically leverage the reasoning capabilities of LRMs, we propose TimelineReasoner, a no","authors_text":"Liancheng Zhang, Xiaoxi Li, Zhicheng Dou","cross_cats":["cs.AI"],"headline":"TimelineReasoner uses large reasoning models to actively track events globally and fill gaps through targeted retrieval, producing more accurate and coherent timelines than passive LLM approaches.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-03T12:30:15Z","title":"TimelineReasoner: Advancing Timeline Summarization with Large Reasoning Models"},"references":{"count":44,"internal_anchors":14,"resolved_work":44,"sample":[{"cited_arxiv_id":"","doi":"10.1145/383952.383954","is_internal_anchor":false,"ref_index":1,"title":"James Allan, Rahul Gupta, and Vikas Khandelwal. 2001. Temporal Summaries of News Topics. InSIGIR 2001: Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in ","work_id":"6b0c498c-a36d-42e9-bcdb-967a3d5e501a","year":2001},{"cited_arxiv_id":"2309.16609","doi":"10.48550/arxiv.2309","is_internal_anchor":true,"ref_index":2,"title":"Qwen Technical Report","work_id":"bb1fd52f-6b2f-437c-9516-37bdf6eb9be8","year":2023},{"cited_arxiv_id":"2503.09567","doi":"10.48550/arxiv.2503.09567","is_internal_anchor":true,"ref_index":3,"title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","work_id":"0b361fed-cf2a-4b90-b61a-de88de4b8840","year":2025},{"cited_arxiv_id":"","doi":"10.24963/ijcai.2019/686","is_internal_anchor":false,"ref_index":4,"title":"Xiuying Chen, Zhangming Chan, Shen Gao, Meng-Hsuan Yu, Dongyan Zhao, and Rui Yan. 2019. Learning towards Abstractive Timeline Summarization. In Proceedings of the Twenty-Eighth International Joint Con","work_id":"159b9bf0-d36a-48b7-942a-9e7779d6db36","year":2019},{"cited_arxiv_id":"","doi":"10.1145/3517221","is_internal_anchor":false,"ref_index":5,"title":"Xiuying Chen, Mingzhe Li, Shen Gao, Zhangming Chan, Dongyan Zhao, Xin Gao, Xiangliang Zhang, and Rui Yan. 2023. Follow the Timeline! Generating an Abstractive and Extractive Timeline Summary in Chrono","work_id":"cf626b84-a24b-4df1-b9ba-7ee605a4bf2e","year":2023}],"snapshot_sha256":"74dde0860105c0da3f96ac7e79a62211c0a073ddec34bd73227613bf26331d91"},"source":{"id":"2605.12518","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T21:29:55.639080Z","id":"ac3e8eae-e43e-4f7e-923b-97c1a80e5c92","model_set":{"reader":"grok-4.3"},"one_line_summary":"TimelineReasoner applies large reasoning models in a Global Cognition plus Detail Exploration loop to produce more accurate, complete, and coherent timelines from news than prior LLM-based methods.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"TimelineReasoner uses large reasoning models to actively track events globally and fill gaps through targeted retrieval, producing more accurate and coherent timelines than passive LLM approaches.","strongest_claim":"Experimental results on open-domain TLS datasets demonstrate that TimelineReasoner significantly outperforms existing LLM-based TLS methods in terms of timeline accuracy, coverage, and coherence.","weakest_assumption":"That the specialized mechanisms (Event Scraper, Timeline Updater, Supervisor) and the two-stage reasoning process can be implemented reliably on top of existing large reasoning models without introducing new hallucinations or retrieval errors that undermine the claimed gains."}},"verdict_id":"ac3e8eae-e43e-4f7e-923b-97c1a80e5c92"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:482ba2b888cfe7535b80e3dcc8a586f31101d8a0979fe5ba883ef75cffb24810","target":"record","created_at":"2026-05-18T03:10:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6dfa3210baed528db536bbd52e1ec16853b5e7a32dca7f89bce191ed2410e7ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-03T12:30:15Z","title_canon_sha256":"7b912831a2aac1f62b93f8fbbd19e92e18a3b7c3accb08fc1a253f03d3e45b79"},"schema_version":"1.0","source":{"id":"2605.12518","kind":"arxiv","version":1}},"canonical_sha256":"9be160dcbf7472ff8b991a605201b66b3b1465c4be16648e64e8d007f4bc885a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9be160dcbf7472ff8b991a605201b66b3b1465c4be16648e64e8d007f4bc885a","first_computed_at":"2026-05-18T03:10:02.891762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:02.891762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QkUmqT67yubUH+UF//Szgdl2/8qBhe8kl3j9LjEJ1b2W+obUbZglGs5LTeD2q2ZxIJ937aP63sVVfXdsbNXyAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:02.892353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12518","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:482ba2b888cfe7535b80e3dcc8a586f31101d8a0979fe5ba883ef75cffb24810","sha256:c31eb0d0728a2d6efbc9845be2c9d23e63857e9572518f9bb460355eaad072eb"],"state_sha256":"40f8d6c67d06b74be211d1c291cd12b5910061d7ace5b798aaa44e6f1dbf9a53"}