{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:73F5BZZXAOTM7FJ4KBMY7HUFOD","short_pith_number":"pith:73F5BZZX","schema_version":"1.0","canonical_sha256":"fecbd0e73703a6cf953c50598f9e8570f7286155da2d943b39154687aee842a3","source":{"kind":"arxiv","id":"2504.14530","version":1},"attestation_state":"computed","paper":{"title":"Causality for Natural Language Processing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Zhijing Jin","submitted_at":"2025-04-20T08:11:11Z","abstract_excerpt":"Causal reasoning is a cornerstone of human intelligence and a critical capability for artificial systems aiming to achieve advanced understanding and decision-making. This thesis delves into various dimensions of causal reasoning and understanding in large language models (LLMs). It encompasses a series of studies that explore the causal inference skills of LLMs, the mechanisms behind their performance, and the implications of causal and anticausal learning for natural language processing (NLP) tasks. Additionally, it investigates the application of causal reasoning in text-based computational"},"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":"2504.14530","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-20T08:11:11Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"a2f54ab26a4b6ceab952c5557bd6d73de9bdc4907f8ae6f9c30ae04c7245e15d","abstract_canon_sha256":"fe2fc35ab4ce56421866177c6727167156574bae4788dc285bb632299a7aeeba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:44.887012Z","signature_b64":"iQ76lTgPQG2ue7Owna7+wP1HXDKfs+UD6veYkNL6QMzWcp1Ic4Oc6zC1E5rtpQxIwVqU0fhLuMzvpF1s7OrrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fecbd0e73703a6cf953c50598f9e8570f7286155da2d943b39154687aee842a3","last_reissued_at":"2026-07-05T10:51:44.886399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:44.886399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causality for Natural Language Processing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Zhijing Jin","submitted_at":"2025-04-20T08:11:11Z","abstract_excerpt":"Causal reasoning is a cornerstone of human intelligence and a critical capability for artificial systems aiming to achieve advanced understanding and decision-making. This thesis delves into various dimensions of causal reasoning and understanding in large language models (LLMs). It encompasses a series of studies that explore the causal inference skills of LLMs, the mechanisms behind their performance, and the implications of causal and anticausal learning for natural language processing (NLP) tasks. Additionally, it investigates the application of causal reasoning in text-based computational"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14530","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/2504.14530/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":"2504.14530","created_at":"2026-07-05T10:51:44.886467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14530v1","created_at":"2026-07-05T10:51:44.886467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14530","created_at":"2026-07-05T10:51:44.886467+00:00"},{"alias_kind":"pith_short_12","alias_value":"73F5BZZXAOTM","created_at":"2026-07-05T10:51:44.886467+00:00"},{"alias_kind":"pith_short_16","alias_value":"73F5BZZXAOTM7FJ4","created_at":"2026-07-05T10:51:44.886467+00:00"},{"alias_kind":"pith_short_8","alias_value":"73F5BZZX","created_at":"2026-07-05T10:51:44.886467+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/73F5BZZXAOTM7FJ4KBMY7HUFOD","json":"https://pith.science/pith/73F5BZZXAOTM7FJ4KBMY7HUFOD.json","graph_json":"https://pith.science/api/pith-number/73F5BZZXAOTM7FJ4KBMY7HUFOD/graph.json","events_json":"https://pith.science/api/pith-number/73F5BZZXAOTM7FJ4KBMY7HUFOD/events.json","paper":"https://pith.science/paper/73F5BZZX"},"agent_actions":{"view_html":"https://pith.science/pith/73F5BZZXAOTM7FJ4KBMY7HUFOD","download_json":"https://pith.science/pith/73F5BZZXAOTM7FJ4KBMY7HUFOD.json","view_paper":"https://pith.science/paper/73F5BZZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14530&json=true","fetch_graph":"https://pith.science/api/pith-number/73F5BZZXAOTM7FJ4KBMY7HUFOD/graph.json","fetch_events":"https://pith.science/api/pith-number/73F5BZZXAOTM7FJ4KBMY7HUFOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73F5BZZXAOTM7FJ4KBMY7HUFOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73F5BZZXAOTM7FJ4KBMY7HUFOD/action/storage_attestation","attest_author":"https://pith.science/pith/73F5BZZXAOTM7FJ4KBMY7HUFOD/action/author_attestation","sign_citation":"https://pith.science/pith/73F5BZZXAOTM7FJ4KBMY7HUFOD/action/citation_signature","submit_replication":"https://pith.science/pith/73F5BZZXAOTM7FJ4KBMY7HUFOD/action/replication_record"}},"created_at":"2026-07-05T10:51:44.886467+00:00","updated_at":"2026-07-05T10:51:44.886467+00:00"}