{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NQXPT2EZGKYKTNEY2SPKXD2Y6Y","short_pith_number":"pith:NQXPT2EZ","schema_version":"1.0","canonical_sha256":"6c2ef9e89932b0a9b498d49eab8f58f627f5e0d9d0bf67cf050573459af3a81b","source":{"kind":"arxiv","id":"2501.00152","version":3},"attestation_state":"computed","paper":{"title":"Temporal reasoning for timeline summarisation in social media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dana Atzil Slonim, Jiayu Song, Mahmud Elahi Akhter, Maria Liakata","submitted_at":"2024-12-30T21:54:33Z","abstract_excerpt":"This paper explores whether enhancing temporal reasoning capabilities in Large Language Models (LLMs) can improve the quality of timeline summarisation, the task of summarising long texts containing sequences of events, such as social media threads. We first introduce NarrativeReason, a novel dataset focused on temporal relationships among sequential events within narratives, distinguishing it from existing temporal reasoning datasets that primarily address pair-wise event relationships. Our approach then combines temporal reasoning with timeline summarisation through a knowledge distillation "},"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":"2501.00152","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-30T21:54:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3b9657b07a929bcbf6b03e3a42970b8838e44bc9ff49cfe282d2180d6a330c34","abstract_canon_sha256":"2687eb2d10819ac396b1442941fc6c1d45e23888638b9e4f04e1a94748f536b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:06.259439Z","signature_b64":"i/DCSz0pYs/zOxZ7FX+fi2D9NO7ImOuyMqxhi/Jx9kaD7/byhrM43dR40jtCB7U5Uad4BfFVT6OXODXXKZ7NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c2ef9e89932b0a9b498d49eab8f58f627f5e0d9d0bf67cf050573459af3a81b","last_reissued_at":"2026-07-05T11:39:06.258937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:06.258937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal reasoning for timeline summarisation in social media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dana Atzil Slonim, Jiayu Song, Mahmud Elahi Akhter, Maria Liakata","submitted_at":"2024-12-30T21:54:33Z","abstract_excerpt":"This paper explores whether enhancing temporal reasoning capabilities in Large Language Models (LLMs) can improve the quality of timeline summarisation, the task of summarising long texts containing sequences of events, such as social media threads. We first introduce NarrativeReason, a novel dataset focused on temporal relationships among sequential events within narratives, distinguishing it from existing temporal reasoning datasets that primarily address pair-wise event relationships. Our approach then combines temporal reasoning with timeline summarisation through a knowledge distillation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00152","kind":"arxiv","version":3},"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/2501.00152/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":"2501.00152","created_at":"2026-07-05T11:39:06.258994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00152v3","created_at":"2026-07-05T11:39:06.258994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00152","created_at":"2026-07-05T11:39:06.258994+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQXPT2EZGKYK","created_at":"2026-07-05T11:39:06.258994+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQXPT2EZGKYKTNEY","created_at":"2026-07-05T11:39:06.258994+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQXPT2EZ","created_at":"2026-07-05T11:39:06.258994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21616","citing_title":"TIM: A Large-Scale Dataset and large Timeline Intelligence Model for Open-domain Timeline Summarization","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NQXPT2EZGKYKTNEY2SPKXD2Y6Y","json":"https://pith.science/pith/NQXPT2EZGKYKTNEY2SPKXD2Y6Y.json","graph_json":"https://pith.science/api/pith-number/NQXPT2EZGKYKTNEY2SPKXD2Y6Y/graph.json","events_json":"https://pith.science/api/pith-number/NQXPT2EZGKYKTNEY2SPKXD2Y6Y/events.json","paper":"https://pith.science/paper/NQXPT2EZ"},"agent_actions":{"view_html":"https://pith.science/pith/NQXPT2EZGKYKTNEY2SPKXD2Y6Y","download_json":"https://pith.science/pith/NQXPT2EZGKYKTNEY2SPKXD2Y6Y.json","view_paper":"https://pith.science/paper/NQXPT2EZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00152&json=true","fetch_graph":"https://pith.science/api/pith-number/NQXPT2EZGKYKTNEY2SPKXD2Y6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/NQXPT2EZGKYKTNEY2SPKXD2Y6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQXPT2EZGKYKTNEY2SPKXD2Y6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQXPT2EZGKYKTNEY2SPKXD2Y6Y/action/storage_attestation","attest_author":"https://pith.science/pith/NQXPT2EZGKYKTNEY2SPKXD2Y6Y/action/author_attestation","sign_citation":"https://pith.science/pith/NQXPT2EZGKYKTNEY2SPKXD2Y6Y/action/citation_signature","submit_replication":"https://pith.science/pith/NQXPT2EZGKYKTNEY2SPKXD2Y6Y/action/replication_record"}},"created_at":"2026-07-05T11:39:06.258994+00:00","updated_at":"2026-07-05T11:39:06.258994+00:00"}