{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YM7JWJ2GKW5Q6PVT47QOFPSZD4","short_pith_number":"pith:YM7JWJ2G","schema_version":"1.0","canonical_sha256":"c33e9b274655bb0f3eb3e7e0e2be591f01d1e0d32e52a15b6a6661db44ffbdea","source":{"kind":"arxiv","id":"2306.05836","version":3},"attestation_state":"computed","paper":{"title":"Can Large Language Models Infer Causation from Correlation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bernhard Sch\\\"olkopf, Jiarui Liu, Mona Diab, Mrinmaya Sachan, Rada Mihalcea, Spencer Poff, Zhiheng Lyu, Zhijing Jin","submitted_at":"2023-06-09T12:09:15Z","abstract_excerpt":"Causal inference is one of the hallmarks of human intelligence. While the field of CausalNLP has attracted much interest in the recent years, existing causal inference datasets in NLP primarily rely on discovering causality from empirical knowledge (e.g., commonsense knowledge). In this work, we propose the first benchmark dataset to test the pure causal inference skills of large language models (LLMs). Specifically, we formulate a novel task Corr2Cause, which takes a set of correlational statements and determines the causal relationship between the variables. We curate a large-scale dataset o"},"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":"2306.05836","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T12:09:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d145afc385925ec1474a666bc6a6c3deb2eb3c819b9aa7b426c6ae1eee80c57b","abstract_canon_sha256":"a05ad5d8c2d4a05f36144ad43f2e1504a698b2a21c388615a60e2ac07b5e3209"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:49.079718Z","signature_b64":"rtoF9xjsJU+/iebX4ztMjG3aOssIp7Q4xf4aiBk6fUEjRUEbelgh7BFqvEhnkKNVdhZ0HuaIJ26LGe+jQiYnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c33e9b274655bb0f3eb3e7e0e2be591f01d1e0d32e52a15b6a6661db44ffbdea","last_reissued_at":"2026-07-05T08:08:49.079215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:49.079215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Large Language Models Infer Causation from Correlation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bernhard Sch\\\"olkopf, Jiarui Liu, Mona Diab, Mrinmaya Sachan, Rada Mihalcea, Spencer Poff, Zhiheng Lyu, Zhijing Jin","submitted_at":"2023-06-09T12:09:15Z","abstract_excerpt":"Causal inference is one of the hallmarks of human intelligence. While the field of CausalNLP has attracted much interest in the recent years, existing causal inference datasets in NLP primarily rely on discovering causality from empirical knowledge (e.g., commonsense knowledge). In this work, we propose the first benchmark dataset to test the pure causal inference skills of large language models (LLMs). Specifically, we formulate a novel task Corr2Cause, which takes a set of correlational statements and determines the causal relationship between the variables. We curate a large-scale dataset o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05836","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/2306.05836/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":"2306.05836","created_at":"2026-07-05T08:08:49.079275+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05836v3","created_at":"2026-07-05T08:08:49.079275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05836","created_at":"2026-07-05T08:08:49.079275+00:00"},{"alias_kind":"pith_short_12","alias_value":"YM7JWJ2GKW5Q","created_at":"2026-07-05T08:08:49.079275+00:00"},{"alias_kind":"pith_short_16","alias_value":"YM7JWJ2GKW5Q6PVT","created_at":"2026-07-05T08:08:49.079275+00:00"},{"alias_kind":"pith_short_8","alias_value":"YM7JWJ2G","created_at":"2026-07-05T08:08:49.079275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25902","citing_title":"Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27567","citing_title":"Why LLMs Fail at Causal Discovery and How Interventional Agents Escape","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27022","citing_title":"ORCA: An End-to-End Interactive Copilot for Optimized Root Cause Analysis","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30346","citing_title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2401.00139","citing_title":"Enhancing Causal Reasoning in Large Language Models: A Causal Attribution Model for Precision Fine-Tuning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21821","citing_title":"A Large Language Model Approach to Generating Bypass Rules for Malware Evasion in Analysis Sandbox","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20571","citing_title":"CausalReasoningBenchmark: A Real-World Benchmark for Disentangled Evaluation of Causal Identification and Estimation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09079","citing_title":"CauSim: Scaling Causal Reasoning with Increasingly Complex Causal Simulators","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03045","citing_title":"TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations","ref_index":265,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YM7JWJ2GKW5Q6PVT47QOFPSZD4","json":"https://pith.science/pith/YM7JWJ2GKW5Q6PVT47QOFPSZD4.json","graph_json":"https://pith.science/api/pith-number/YM7JWJ2GKW5Q6PVT47QOFPSZD4/graph.json","events_json":"https://pith.science/api/pith-number/YM7JWJ2GKW5Q6PVT47QOFPSZD4/events.json","paper":"https://pith.science/paper/YM7JWJ2G"},"agent_actions":{"view_html":"https://pith.science/pith/YM7JWJ2GKW5Q6PVT47QOFPSZD4","download_json":"https://pith.science/pith/YM7JWJ2GKW5Q6PVT47QOFPSZD4.json","view_paper":"https://pith.science/paper/YM7JWJ2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05836&json=true","fetch_graph":"https://pith.science/api/pith-number/YM7JWJ2GKW5Q6PVT47QOFPSZD4/graph.json","fetch_events":"https://pith.science/api/pith-number/YM7JWJ2GKW5Q6PVT47QOFPSZD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YM7JWJ2GKW5Q6PVT47QOFPSZD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YM7JWJ2GKW5Q6PVT47QOFPSZD4/action/storage_attestation","attest_author":"https://pith.science/pith/YM7JWJ2GKW5Q6PVT47QOFPSZD4/action/author_attestation","sign_citation":"https://pith.science/pith/YM7JWJ2GKW5Q6PVT47QOFPSZD4/action/citation_signature","submit_replication":"https://pith.science/pith/YM7JWJ2GKW5Q6PVT47QOFPSZD4/action/replication_record"}},"created_at":"2026-07-05T08:08:49.079275+00:00","updated_at":"2026-07-05T08:08:49.079275+00:00"}