{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3IC5RDZBRMGSB6TTG7FAQT4PUS","short_pith_number":"pith:3IC5RDZB","schema_version":"1.0","canonical_sha256":"da05d88f218b0d20fa7337ca084f8fa4999ffbe331a45a6645e63a881d29167b","source":{"kind":"arxiv","id":"2407.18607","version":2},"attestation_state":"computed","paper":{"title":"Using GPT-4 to guide causal machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Alessio Zanga, Anthony C. Constantinou, Neville K. Kitson","submitted_at":"2024-07-26T08:59:26Z","abstract_excerpt":"Since its introduction to the public, ChatGPT has had an unprecedented impact. While some experts praised AI advancements and highlighted their potential risks, others have been critical about the accuracy and usefulness of Large Language Models (LLMs). In this paper, we are interested in the ability of LLMs to identify causal relationships. We focus on the well-established GPT-4 (Turbo) and evaluate its performance under the most restrictive conditions, by isolating its ability to infer causal relationships based solely on the variable labels without being given any other context by humans, d"},"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":"2407.18607","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-26T08:59:26Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"1f596fbad210ca5bddb5208ca2ce57eb0ae284d77603a943748642dbd890b088","abstract_canon_sha256":"fe6691ed5cb5fca75402a85631dfebf46ecfe87477f9a7429906dac18479984b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:56.152429Z","signature_b64":"KDNPvu5CFWdwcoKCNswxHMzVGVN+EBacoBwRFrfkQoIi0jAHl4HDBHkWD7e5GJFhE+2EfUAE1wnJYqpkFa+TDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da05d88f218b0d20fa7337ca084f8fa4999ffbe331a45a6645e63a881d29167b","last_reissued_at":"2026-07-05T09:47:56.151944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:56.151944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using GPT-4 to guide causal machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Alessio Zanga, Anthony C. Constantinou, Neville K. Kitson","submitted_at":"2024-07-26T08:59:26Z","abstract_excerpt":"Since its introduction to the public, ChatGPT has had an unprecedented impact. While some experts praised AI advancements and highlighted their potential risks, others have been critical about the accuracy and usefulness of Large Language Models (LLMs). In this paper, we are interested in the ability of LLMs to identify causal relationships. We focus on the well-established GPT-4 (Turbo) and evaluate its performance under the most restrictive conditions, by isolating its ability to infer causal relationships based solely on the variable labels without being given any other context by humans, d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18607","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/2407.18607/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":"2407.18607","created_at":"2026-07-05T09:47:56.152000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18607v2","created_at":"2026-07-05T09:47:56.152000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18607","created_at":"2026-07-05T09:47:56.152000+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IC5RDZBRMGS","created_at":"2026-07-05T09:47:56.152000+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IC5RDZBRMGSB6TT","created_at":"2026-07-05T09:47:56.152000+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IC5RDZB","created_at":"2026-07-05T09:47:56.152000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3IC5RDZBRMGSB6TTG7FAQT4PUS","json":"https://pith.science/pith/3IC5RDZBRMGSB6TTG7FAQT4PUS.json","graph_json":"https://pith.science/api/pith-number/3IC5RDZBRMGSB6TTG7FAQT4PUS/graph.json","events_json":"https://pith.science/api/pith-number/3IC5RDZBRMGSB6TTG7FAQT4PUS/events.json","paper":"https://pith.science/paper/3IC5RDZB"},"agent_actions":{"view_html":"https://pith.science/pith/3IC5RDZBRMGSB6TTG7FAQT4PUS","download_json":"https://pith.science/pith/3IC5RDZBRMGSB6TTG7FAQT4PUS.json","view_paper":"https://pith.science/paper/3IC5RDZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18607&json=true","fetch_graph":"https://pith.science/api/pith-number/3IC5RDZBRMGSB6TTG7FAQT4PUS/graph.json","fetch_events":"https://pith.science/api/pith-number/3IC5RDZBRMGSB6TTG7FAQT4PUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IC5RDZBRMGSB6TTG7FAQT4PUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IC5RDZBRMGSB6TTG7FAQT4PUS/action/storage_attestation","attest_author":"https://pith.science/pith/3IC5RDZBRMGSB6TTG7FAQT4PUS/action/author_attestation","sign_citation":"https://pith.science/pith/3IC5RDZBRMGSB6TTG7FAQT4PUS/action/citation_signature","submit_replication":"https://pith.science/pith/3IC5RDZBRMGSB6TTG7FAQT4PUS/action/replication_record"}},"created_at":"2026-07-05T09:47:56.152000+00:00","updated_at":"2026-07-05T09:47:56.152000+00:00"}