{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T3K63JFFFL4JUGAB564HVDLA7X","short_pith_number":"pith:T3K63JFF","schema_version":"1.0","canonical_sha256":"9ed5eda4a52af89a1801efb87a8d60fdd85f74969397277d121777fa6b9e7625","source":{"kind":"arxiv","id":"2303.06273","version":3},"attestation_state":"computed","paper":{"title":"Consistency Analysis of ChatGPT","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Myeongjun Erik Jang, Thomas Lukasiewicz","submitted_at":"2023-03-11T01:19:01Z","abstract_excerpt":"ChatGPT has gained a huge popularity since its introduction. Its positive aspects have been reported through many media platforms, and some analyses even showed that ChatGPT achieved a decent grade in professional exams, adding extra support to the claim that AI can now assist and even replace humans in industrial fields. Others, however, doubt its reliability and trustworthiness. This paper investigates the trustworthiness of ChatGPT and GPT-4 regarding logically consistent behaviour, focusing specifically on semantic consistency and the properties of negation, symmetric, and transitive consi"},"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":"2303.06273","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-11T01:19:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a35d81a6bcba33c047411912e5683e2b04148a7a5cea904ed70664e8b921ab28","abstract_canon_sha256":"9c9198f2341e92d3570b802a8e5c00ecb996ffbefe9e0c5dbb0fbdfa8bde0442"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:16.249006Z","signature_b64":"mdLx3XnRx7hVlIin32IckHxZGxHrRtt3jHTO9yg08+pa9BldT8EZyydof0ud3FzLBu2AfqO/gskulTxnnAzzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ed5eda4a52af89a1801efb87a8d60fdd85f74969397277d121777fa6b9e7625","last_reissued_at":"2026-07-05T07:12:16.248554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:16.248554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistency Analysis of ChatGPT","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Myeongjun Erik Jang, Thomas Lukasiewicz","submitted_at":"2023-03-11T01:19:01Z","abstract_excerpt":"ChatGPT has gained a huge popularity since its introduction. Its positive aspects have been reported through many media platforms, and some analyses even showed that ChatGPT achieved a decent grade in professional exams, adding extra support to the claim that AI can now assist and even replace humans in industrial fields. Others, however, doubt its reliability and trustworthiness. This paper investigates the trustworthiness of ChatGPT and GPT-4 regarding logically consistent behaviour, focusing specifically on semantic consistency and the properties of negation, symmetric, and transitive consi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06273","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/2303.06273/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":"2303.06273","created_at":"2026-07-05T07:12:16.248607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.06273v3","created_at":"2026-07-05T07:12:16.248607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06273","created_at":"2026-07-05T07:12:16.248607+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3K63JFFFL4J","created_at":"2026-07-05T07:12:16.248607+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3K63JFFFL4JUGAB","created_at":"2026-07-05T07:12:16.248607+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3K63JFF","created_at":"2026-07-05T07:12:16.248607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.05374","citing_title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13875","citing_title":"Common-agency Games for Multi-Objective Test-Time Alignment","ref_index":204,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3K63JFFFL4JUGAB564HVDLA7X","json":"https://pith.science/pith/T3K63JFFFL4JUGAB564HVDLA7X.json","graph_json":"https://pith.science/api/pith-number/T3K63JFFFL4JUGAB564HVDLA7X/graph.json","events_json":"https://pith.science/api/pith-number/T3K63JFFFL4JUGAB564HVDLA7X/events.json","paper":"https://pith.science/paper/T3K63JFF"},"agent_actions":{"view_html":"https://pith.science/pith/T3K63JFFFL4JUGAB564HVDLA7X","download_json":"https://pith.science/pith/T3K63JFFFL4JUGAB564HVDLA7X.json","view_paper":"https://pith.science/paper/T3K63JFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.06273&json=true","fetch_graph":"https://pith.science/api/pith-number/T3K63JFFFL4JUGAB564HVDLA7X/graph.json","fetch_events":"https://pith.science/api/pith-number/T3K63JFFFL4JUGAB564HVDLA7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3K63JFFFL4JUGAB564HVDLA7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3K63JFFFL4JUGAB564HVDLA7X/action/storage_attestation","attest_author":"https://pith.science/pith/T3K63JFFFL4JUGAB564HVDLA7X/action/author_attestation","sign_citation":"https://pith.science/pith/T3K63JFFFL4JUGAB564HVDLA7X/action/citation_signature","submit_replication":"https://pith.science/pith/T3K63JFFFL4JUGAB564HVDLA7X/action/replication_record"}},"created_at":"2026-07-05T07:12:16.248607+00:00","updated_at":"2026-07-05T07:12:16.248607+00:00"}