{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YX3QY3K3VRMUNVMQXWYOHPYVXE","short_pith_number":"pith:YX3QY3K3","schema_version":"1.0","canonical_sha256":"c5f70c6d5bac5946d590bdb0e3bf15b903d417d9ce94c4438b75de3b91111c29","source":{"kind":"arxiv","id":"2410.11385","version":1},"attestation_state":"computed","paper":{"title":"Do LLMs Have the Generalization Ability in Conducting Causal Inference?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Wang, Chen Wang, Dongming Zhao, Ruifang He, Yuexian Hou","submitted_at":"2024-10-15T08:23:31Z","abstract_excerpt":"In causal inference, generalization capability refers to the ability to conduct causal inference methods on new data to estimate the causal-effect between unknown phenomenon, which is crucial for expanding the boundaries of knowledge. Studies have evaluated the causal inference capabilities of Large Language Models (LLMs) concerning known phenomena, yet the generalization capabilities of LLMs concerning unseen phenomena remain unexplored. In this paper, we selected four tasks: Causal Path Discovery (CP), Backdoor Adjustment (BA), Factual Inference (FI), and Counterfactual Inference (CI) as rep"},"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":"2410.11385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T08:23:31Z","cross_cats_sorted":[],"title_canon_sha256":"99652352a87b54bab45da64593995c335aae0d262dec83f3e26f6c41f18c53cf","abstract_canon_sha256":"5a0521d1eb21037881ba8bbd5e17bfcfdd9e57a4fe5f9d23f3371268c9d8b889"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:52.720736Z","signature_b64":"hOxEHVJzAAFvnhYPUTOG+f7frwOWQ0m8bxSJPzRW7fB6W+1v5Op/5Y+fV50z/mGTZV1YHG5Y38wDVfcgW0HVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5f70c6d5bac5946d590bdb0e3bf15b903d417d9ce94c4438b75de3b91111c29","last_reissued_at":"2026-07-05T09:20:52.720019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:52.720019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do LLMs Have the Generalization Ability in Conducting Causal Inference?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Wang, Chen Wang, Dongming Zhao, Ruifang He, Yuexian Hou","submitted_at":"2024-10-15T08:23:31Z","abstract_excerpt":"In causal inference, generalization capability refers to the ability to conduct causal inference methods on new data to estimate the causal-effect between unknown phenomenon, which is crucial for expanding the boundaries of knowledge. Studies have evaluated the causal inference capabilities of Large Language Models (LLMs) concerning known phenomena, yet the generalization capabilities of LLMs concerning unseen phenomena remain unexplored. In this paper, we selected four tasks: Causal Path Discovery (CP), Backdoor Adjustment (BA), Factual Inference (FI), and Counterfactual Inference (CI) as rep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11385","kind":"arxiv","version":1},"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/2410.11385/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":"2410.11385","created_at":"2026-07-05T09:20:52.720097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11385v1","created_at":"2026-07-05T09:20:52.720097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11385","created_at":"2026-07-05T09:20:52.720097+00:00"},{"alias_kind":"pith_short_12","alias_value":"YX3QY3K3VRMU","created_at":"2026-07-05T09:20:52.720097+00:00"},{"alias_kind":"pith_short_16","alias_value":"YX3QY3K3VRMUNVMQ","created_at":"2026-07-05T09:20:52.720097+00:00"},{"alias_kind":"pith_short_8","alias_value":"YX3QY3K3","created_at":"2026-07-05T09:20:52.720097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09433","citing_title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YX3QY3K3VRMUNVMQXWYOHPYVXE","json":"https://pith.science/pith/YX3QY3K3VRMUNVMQXWYOHPYVXE.json","graph_json":"https://pith.science/api/pith-number/YX3QY3K3VRMUNVMQXWYOHPYVXE/graph.json","events_json":"https://pith.science/api/pith-number/YX3QY3K3VRMUNVMQXWYOHPYVXE/events.json","paper":"https://pith.science/paper/YX3QY3K3"},"agent_actions":{"view_html":"https://pith.science/pith/YX3QY3K3VRMUNVMQXWYOHPYVXE","download_json":"https://pith.science/pith/YX3QY3K3VRMUNVMQXWYOHPYVXE.json","view_paper":"https://pith.science/paper/YX3QY3K3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11385&json=true","fetch_graph":"https://pith.science/api/pith-number/YX3QY3K3VRMUNVMQXWYOHPYVXE/graph.json","fetch_events":"https://pith.science/api/pith-number/YX3QY3K3VRMUNVMQXWYOHPYVXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YX3QY3K3VRMUNVMQXWYOHPYVXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YX3QY3K3VRMUNVMQXWYOHPYVXE/action/storage_attestation","attest_author":"https://pith.science/pith/YX3QY3K3VRMUNVMQXWYOHPYVXE/action/author_attestation","sign_citation":"https://pith.science/pith/YX3QY3K3VRMUNVMQXWYOHPYVXE/action/citation_signature","submit_replication":"https://pith.science/pith/YX3QY3K3VRMUNVMQXWYOHPYVXE/action/replication_record"}},"created_at":"2026-07-05T09:20:52.720097+00:00","updated_at":"2026-07-05T09:20:52.720097+00:00"}