{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CXS4ADK75S3QIE2AHUSJGFTRJQ","short_pith_number":"pith:CXS4ADK7","schema_version":"1.0","canonical_sha256":"15e5c00d5fecb70413403d249316714c14936d3fa1ca1f8faadc18905b9258c7","source":{"kind":"arxiv","id":"2509.01535","version":2},"attestation_state":"computed","paper":{"title":"CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junjian Ye, Kairong Han, Kun Kuang, Lujia Pan, Wenshuo Zhao, Ziyu Zhao","submitted_at":"2025-09-01T15:13:15Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable success across various domains. However, a fundamental question remains: Can LLMs effectively utilize causal knowledge for prediction and generation? Through empirical studies, we find that LLMs trained directly on large-scale data often capture spurious correlations rather than true causal relationships, leading to suboptimal performance, especially in out-of-distribution (OOD) scenarios. To address this challenge, we propose Causal Attention Tuning (CAT), a novel approach that injects fine-grained causal knowledge into the attention mecha"},"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":"2509.01535","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T15:13:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"04578fc105a2fbb2e42f0c29cd83126d8797fc295fd198a97dc8c6b0e2de8776","abstract_canon_sha256":"a18c2ff7cfbe935c171b91f9ca0e50f0be8ba37540ae6ff6e8b906a61bf142c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:11.418802Z","signature_b64":"k9dnwmDP+1p32v4zfOySfOpP1mTVsPazd/Ea43CSCB365idJ2TvuMdx2NpwDOR2HPuSx/kqb+ladwfYVunRfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15e5c00d5fecb70413403d249316714c14936d3fa1ca1f8faadc18905b9258c7","last_reissued_at":"2026-07-05T12:07:11.418374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:11.418374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junjian Ye, Kairong Han, Kun Kuang, Lujia Pan, Wenshuo Zhao, Ziyu Zhao","submitted_at":"2025-09-01T15:13:15Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable success across various domains. However, a fundamental question remains: Can LLMs effectively utilize causal knowledge for prediction and generation? Through empirical studies, we find that LLMs trained directly on large-scale data often capture spurious correlations rather than true causal relationships, leading to suboptimal performance, especially in out-of-distribution (OOD) scenarios. To address this challenge, we propose Causal Attention Tuning (CAT), a novel approach that injects fine-grained causal knowledge into the attention mecha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01535","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/2509.01535/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":"2509.01535","created_at":"2026-07-05T12:07:11.418433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01535v2","created_at":"2026-07-05T12:07:11.418433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01535","created_at":"2026-07-05T12:07:11.418433+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXS4ADK75S3Q","created_at":"2026-07-05T12:07:11.418433+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXS4ADK75S3QIE2A","created_at":"2026-07-05T12:07:11.418433+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXS4ADK7","created_at":"2026-07-05T12:07:11.418433+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/CXS4ADK75S3QIE2AHUSJGFTRJQ","json":"https://pith.science/pith/CXS4ADK75S3QIE2AHUSJGFTRJQ.json","graph_json":"https://pith.science/api/pith-number/CXS4ADK75S3QIE2AHUSJGFTRJQ/graph.json","events_json":"https://pith.science/api/pith-number/CXS4ADK75S3QIE2AHUSJGFTRJQ/events.json","paper":"https://pith.science/paper/CXS4ADK7"},"agent_actions":{"view_html":"https://pith.science/pith/CXS4ADK75S3QIE2AHUSJGFTRJQ","download_json":"https://pith.science/pith/CXS4ADK75S3QIE2AHUSJGFTRJQ.json","view_paper":"https://pith.science/paper/CXS4ADK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01535&json=true","fetch_graph":"https://pith.science/api/pith-number/CXS4ADK75S3QIE2AHUSJGFTRJQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CXS4ADK75S3QIE2AHUSJGFTRJQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXS4ADK75S3QIE2AHUSJGFTRJQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXS4ADK75S3QIE2AHUSJGFTRJQ/action/storage_attestation","attest_author":"https://pith.science/pith/CXS4ADK75S3QIE2AHUSJGFTRJQ/action/author_attestation","sign_citation":"https://pith.science/pith/CXS4ADK75S3QIE2AHUSJGFTRJQ/action/citation_signature","submit_replication":"https://pith.science/pith/CXS4ADK75S3QIE2AHUSJGFTRJQ/action/replication_record"}},"created_at":"2026-07-05T12:07:11.418433+00:00","updated_at":"2026-07-05T12:07:11.418433+00:00"}