{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3IUFTXGEERJUUOH25DGUUIZPIF","short_pith_number":"pith:3IUFTXGE","schema_version":"1.0","canonical_sha256":"da2859dcc424534a38fae8cd4a232f4165d69ac9d57eab0522f098d9b26f2675","source":{"kind":"arxiv","id":"2406.11486","version":1},"attestation_state":"computed","paper":{"title":"Analysing zero-shot temporal relation extraction on clinical notes using temporal consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anastasiia Sedova, Andreas Stephan, Benjamin Roth, Klim Zaporojets, Vasiliki Kougia","submitted_at":"2024-06-17T12:53:21Z","abstract_excerpt":"This paper presents the first study for temporal relation extraction in a zero-shot setting focusing on biomedical text. We employ two types of prompts and five LLMs (GPT-3.5, Mixtral, Llama 2, Gemma, and PMC-LLaMA) to obtain responses about the temporal relations between two events. Our experiments demonstrate that LLMs struggle in the zero-shot setting performing worse than fine-tuned specialized models in terms of F1 score, showing that this is a challenging task for LLMs. We further contribute a novel comprehensive temporal analysis by calculating consistency scores for each LLM. Our findi"},"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":"2406.11486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T12:53:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4912fd67dc761d731dd693192c40f4d618dcf5d61c294627772b6ded4a5fc4fd","abstract_canon_sha256":"a097915e3b0d6758c6cef0e08d8994c82b280a631a02a27166249df54bfd8bcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:54.040440Z","signature_b64":"0PBALXUqNYDL7MZKLablqyjOmA+eJUVJmiglG4OIBkrT3+38SsqdXr1F4nPuxk1TdrERH/F7ogJipsG3TKVDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da2859dcc424534a38fae8cd4a232f4165d69ac9d57eab0522f098d9b26f2675","last_reissued_at":"2026-07-05T08:32:54.039929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:54.039929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysing zero-shot temporal relation extraction on clinical notes using temporal consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anastasiia Sedova, Andreas Stephan, Benjamin Roth, Klim Zaporojets, Vasiliki Kougia","submitted_at":"2024-06-17T12:53:21Z","abstract_excerpt":"This paper presents the first study for temporal relation extraction in a zero-shot setting focusing on biomedical text. We employ two types of prompts and five LLMs (GPT-3.5, Mixtral, Llama 2, Gemma, and PMC-LLaMA) to obtain responses about the temporal relations between two events. Our experiments demonstrate that LLMs struggle in the zero-shot setting performing worse than fine-tuned specialized models in terms of F1 score, showing that this is a challenging task for LLMs. We further contribute a novel comprehensive temporal analysis by calculating consistency scores for each LLM. Our findi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11486","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/2406.11486/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":"2406.11486","created_at":"2026-07-05T08:32:54.040003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11486v1","created_at":"2026-07-05T08:32:54.040003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11486","created_at":"2026-07-05T08:32:54.040003+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IUFTXGEERJU","created_at":"2026-07-05T08:32:54.040003+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IUFTXGEERJUUOH2","created_at":"2026-07-05T08:32:54.040003+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IUFTXGE","created_at":"2026-07-05T08:32:54.040003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07421","citing_title":"SynthEHR-Eviction: Enhancing Eviction SDoH Detection with LLM-Augmented Synthetic EHR Data","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3IUFTXGEERJUUOH25DGUUIZPIF","json":"https://pith.science/pith/3IUFTXGEERJUUOH25DGUUIZPIF.json","graph_json":"https://pith.science/api/pith-number/3IUFTXGEERJUUOH25DGUUIZPIF/graph.json","events_json":"https://pith.science/api/pith-number/3IUFTXGEERJUUOH25DGUUIZPIF/events.json","paper":"https://pith.science/paper/3IUFTXGE"},"agent_actions":{"view_html":"https://pith.science/pith/3IUFTXGEERJUUOH25DGUUIZPIF","download_json":"https://pith.science/pith/3IUFTXGEERJUUOH25DGUUIZPIF.json","view_paper":"https://pith.science/paper/3IUFTXGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11486&json=true","fetch_graph":"https://pith.science/api/pith-number/3IUFTXGEERJUUOH25DGUUIZPIF/graph.json","fetch_events":"https://pith.science/api/pith-number/3IUFTXGEERJUUOH25DGUUIZPIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IUFTXGEERJUUOH25DGUUIZPIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IUFTXGEERJUUOH25DGUUIZPIF/action/storage_attestation","attest_author":"https://pith.science/pith/3IUFTXGEERJUUOH25DGUUIZPIF/action/author_attestation","sign_citation":"https://pith.science/pith/3IUFTXGEERJUUOH25DGUUIZPIF/action/citation_signature","submit_replication":"https://pith.science/pith/3IUFTXGEERJUUOH25DGUUIZPIF/action/replication_record"}},"created_at":"2026-07-05T08:32:54.040003+00:00","updated_at":"2026-07-05T08:32:54.040003+00:00"}