{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VFDCYFPC7WPIUG3ZZXVJKWX53M","short_pith_number":"pith:VFDCYFPC","schema_version":"1.0","canonical_sha256":"a9462c15e2fd9e8a1b79cdea955afddb1f39cf2f0138d1f4fe2e952b1b5e98bf","source":{"kind":"arxiv","id":"2305.07375","version":4},"attestation_state":"computed","paper":{"title":"Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Qin, Jinglong Gao, Ting Liu, Xiao Ding","submitted_at":"2023-05-12T10:54:13Z","abstract_excerpt":"Causal reasoning ability is crucial for numerous NLP applications. Despite the impressive emerging ability of ChatGPT in various NLP tasks, it is unclear how well ChatGPT performs in causal reasoning. In this paper, we conduct the first comprehensive evaluation of the ChatGPT's causal reasoning capabilities. Experiments show that ChatGPT is not a good causal reasoner, but a good causal explainer. Besides, ChatGPT has a serious hallucination on causal reasoning, possibly due to the reporting biases between causal and non-causal relationships in natural language, as well as ChatGPT's upgrading p"},"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":"2305.07375","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-12T10:54:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"42d59a18a1efb485f61b9a875424540d2c224eda7f40aff08a4cfb1a45b8c2c4","abstract_canon_sha256":"b307fbd2735b99315973e8abc90e6ecca2c59ea50b67eaeb29a1f0fd9ac3be3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:52.216460Z","signature_b64":"3A7r2eJ8TVQNxzo5raQzcc/qvkclUZFtmAXMvGI38ditZS0YbBqnqleKLwUWyCjeHFPgG1LrIZNiUugWkhmjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9462c15e2fd9e8a1b79cdea955afddb1f39cf2f0138d1f4fe2e952b1b5e98bf","last_reissued_at":"2026-07-05T06:59:52.216027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:52.216027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Qin, Jinglong Gao, Ting Liu, Xiao Ding","submitted_at":"2023-05-12T10:54:13Z","abstract_excerpt":"Causal reasoning ability is crucial for numerous NLP applications. Despite the impressive emerging ability of ChatGPT in various NLP tasks, it is unclear how well ChatGPT performs in causal reasoning. In this paper, we conduct the first comprehensive evaluation of the ChatGPT's causal reasoning capabilities. Experiments show that ChatGPT is not a good causal reasoner, but a good causal explainer. Besides, ChatGPT has a serious hallucination on causal reasoning, possibly due to the reporting biases between causal and non-causal relationships in natural language, as well as ChatGPT's upgrading p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07375","kind":"arxiv","version":4},"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/2305.07375/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":"2305.07375","created_at":"2026-07-05T06:59:52.216075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.07375v4","created_at":"2026-07-05T06:59:52.216075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07375","created_at":"2026-07-05T06:59:52.216075+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFDCYFPC7WPI","created_at":"2026-07-05T06:59:52.216075+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFDCYFPC7WPIUG3Z","created_at":"2026-07-05T06:59:52.216075+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFDCYFPC","created_at":"2026-07-05T06:59:52.216075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18054","citing_title":"AI-based Cognitive-linguistic Features for Dementia Assessment in Picture Description","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11348","citing_title":"Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12748","citing_title":"Generating Effective CoT Traces for Mitigating Causal Hallucination","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VFDCYFPC7WPIUG3ZZXVJKWX53M","json":"https://pith.science/pith/VFDCYFPC7WPIUG3ZZXVJKWX53M.json","graph_json":"https://pith.science/api/pith-number/VFDCYFPC7WPIUG3ZZXVJKWX53M/graph.json","events_json":"https://pith.science/api/pith-number/VFDCYFPC7WPIUG3ZZXVJKWX53M/events.json","paper":"https://pith.science/paper/VFDCYFPC"},"agent_actions":{"view_html":"https://pith.science/pith/VFDCYFPC7WPIUG3ZZXVJKWX53M","download_json":"https://pith.science/pith/VFDCYFPC7WPIUG3ZZXVJKWX53M.json","view_paper":"https://pith.science/paper/VFDCYFPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.07375&json=true","fetch_graph":"https://pith.science/api/pith-number/VFDCYFPC7WPIUG3ZZXVJKWX53M/graph.json","fetch_events":"https://pith.science/api/pith-number/VFDCYFPC7WPIUG3ZZXVJKWX53M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFDCYFPC7WPIUG3ZZXVJKWX53M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFDCYFPC7WPIUG3ZZXVJKWX53M/action/storage_attestation","attest_author":"https://pith.science/pith/VFDCYFPC7WPIUG3ZZXVJKWX53M/action/author_attestation","sign_citation":"https://pith.science/pith/VFDCYFPC7WPIUG3ZZXVJKWX53M/action/citation_signature","submit_replication":"https://pith.science/pith/VFDCYFPC7WPIUG3ZZXVJKWX53M/action/replication_record"}},"created_at":"2026-07-05T06:59:52.216075+00:00","updated_at":"2026-07-05T06:59:52.216075+00:00"}