{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TRBVILJW2TUBB5S2ZXUNEHB4TH","short_pith_number":"pith:TRBVILJW","schema_version":"1.0","canonical_sha256":"9c43542d36d4e810f65acde8d21c3c99f6eb3cc33e9f5c900569a3eb8ea0cd3a","source":{"kind":"arxiv","id":"2312.16054","version":2},"attestation_state":"computed","paper":{"title":"A Logically Consistent Chain-of-Thought Approach for Stance Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Zhang, Daijun Ding, Hu Huang, Liwen Jing","submitted_at":"2023-12-26T13:54:00Z","abstract_excerpt":"Zero-shot stance detection (ZSSD) aims to detect stances toward unseen targets. Incorporating background knowledge to enhance transferability between seen and unseen targets constitutes the primary approach of ZSSD. However, these methods often struggle with a knowledge-task disconnect and lack logical consistency in their predictions. To address these issues, we introduce a novel approach named Logically Consistent Chain-of-Thought (LC-CoT) for ZSSD, which improves stance detection by ensuring relevant and logically sound knowledge extraction. LC-CoT employs a three-step process. Initially, i"},"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":"2312.16054","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-26T13:54:00Z","cross_cats_sorted":[],"title_canon_sha256":"b4c4b3472be3736384a53365f67051d9bb280196d2d7b525e2b3d5deaa921091","abstract_canon_sha256":"2d56abd28e7051d70e3483d62b0503ff1b6eb5155bc2afae8a51824b216775ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:22.421543Z","signature_b64":"IoDLXvTlmgN06/4qx6yj/cC6v5Ci0TguqIpip0P0Xjoxt8iHsZWcVD4P/e/CljrvRuPeaeAflCVzM2q90GEDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c43542d36d4e810f65acde8d21c3c99f6eb3cc33e9f5c900569a3eb8ea0cd3a","last_reissued_at":"2026-07-05T11:38:22.420887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:22.420887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Logically Consistent Chain-of-Thought Approach for Stance Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Zhang, Daijun Ding, Hu Huang, Liwen Jing","submitted_at":"2023-12-26T13:54:00Z","abstract_excerpt":"Zero-shot stance detection (ZSSD) aims to detect stances toward unseen targets. Incorporating background knowledge to enhance transferability between seen and unseen targets constitutes the primary approach of ZSSD. However, these methods often struggle with a knowledge-task disconnect and lack logical consistency in their predictions. To address these issues, we introduce a novel approach named Logically Consistent Chain-of-Thought (LC-CoT) for ZSSD, which improves stance detection by ensuring relevant and logically sound knowledge extraction. LC-CoT employs a three-step process. Initially, i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16054","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/2312.16054/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":"2312.16054","created_at":"2026-07-05T11:38:22.420953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16054v2","created_at":"2026-07-05T11:38:22.420953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16054","created_at":"2026-07-05T11:38:22.420953+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRBVILJW2TUB","created_at":"2026-07-05T11:38:22.420953+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRBVILJW2TUBB5S2","created_at":"2026-07-05T11:38:22.420953+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRBVILJW","created_at":"2026-07-05T11:38:22.420953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02074","citing_title":"Rethinking stance detection: A theoretically-informed research agenda for user-level inference using language models","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TRBVILJW2TUBB5S2ZXUNEHB4TH","json":"https://pith.science/pith/TRBVILJW2TUBB5S2ZXUNEHB4TH.json","graph_json":"https://pith.science/api/pith-number/TRBVILJW2TUBB5S2ZXUNEHB4TH/graph.json","events_json":"https://pith.science/api/pith-number/TRBVILJW2TUBB5S2ZXUNEHB4TH/events.json","paper":"https://pith.science/paper/TRBVILJW"},"agent_actions":{"view_html":"https://pith.science/pith/TRBVILJW2TUBB5S2ZXUNEHB4TH","download_json":"https://pith.science/pith/TRBVILJW2TUBB5S2ZXUNEHB4TH.json","view_paper":"https://pith.science/paper/TRBVILJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16054&json=true","fetch_graph":"https://pith.science/api/pith-number/TRBVILJW2TUBB5S2ZXUNEHB4TH/graph.json","fetch_events":"https://pith.science/api/pith-number/TRBVILJW2TUBB5S2ZXUNEHB4TH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRBVILJW2TUBB5S2ZXUNEHB4TH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRBVILJW2TUBB5S2ZXUNEHB4TH/action/storage_attestation","attest_author":"https://pith.science/pith/TRBVILJW2TUBB5S2ZXUNEHB4TH/action/author_attestation","sign_citation":"https://pith.science/pith/TRBVILJW2TUBB5S2ZXUNEHB4TH/action/citation_signature","submit_replication":"https://pith.science/pith/TRBVILJW2TUBB5S2ZXUNEHB4TH/action/replication_record"}},"created_at":"2026-07-05T11:38:22.420953+00:00","updated_at":"2026-07-05T11:38:22.420953+00:00"}