{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:46UVSNZWTQQ4WTZBLA3GYVJB3P","short_pith_number":"pith:46UVSNZW","schema_version":"1.0","canonical_sha256":"e7a95937369c21cb4f2158366c5521dbd82164a097524cd7af55970d8f5e67bc","source":{"kind":"arxiv","id":"2503.17569","version":1},"attestation_state":"computed","paper":{"title":"Fairness-Driven LLM-based Causal Discovery with Active Learning and Dynamic Scoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akane Sano, Khadija Zanna","submitted_at":"2025-03-21T22:58:26Z","abstract_excerpt":"Causal discovery (CD) plays a pivotal role in numerous scientific fields by clarifying the causal relationships that underlie phenomena observed in diverse disciplines. Despite significant advancements in CD algorithms that enhance bias and fairness analyses in machine learning, their application faces challenges due to the high computational demands and complexities of large-scale data. This paper introduces a framework that leverages Large Language Models (LLMs) for CD, utilizing a metadata-based approach akin to the reasoning processes of human experts. By shifting from pairwise queries to "},"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":"2503.17569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-21T22:58:26Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f44c89781b27bacfa1e7f5e03cbebfabb6bc9e465958b1a9fe017209a90b1d5c","abstract_canon_sha256":"b88cbb9228c6647426c26278eca186855337dec0736da731471b435b8b7b33ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:49.597161Z","signature_b64":"/KabLTftwFshYLaPM/sp1ZQNE+O6VpoVVoVaRzh/3Bszvo3MwVjFyy+d1o8taiajGmS8pNsXij0+rX04RLuhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7a95937369c21cb4f2158366c5521dbd82164a097524cd7af55970d8f5e67bc","last_reissued_at":"2026-07-05T10:37:49.596605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:49.596605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fairness-Driven LLM-based Causal Discovery with Active Learning and Dynamic Scoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akane Sano, Khadija Zanna","submitted_at":"2025-03-21T22:58:26Z","abstract_excerpt":"Causal discovery (CD) plays a pivotal role in numerous scientific fields by clarifying the causal relationships that underlie phenomena observed in diverse disciplines. Despite significant advancements in CD algorithms that enhance bias and fairness analyses in machine learning, their application faces challenges due to the high computational demands and complexities of large-scale data. This paper introduces a framework that leverages Large Language Models (LLMs) for CD, utilizing a metadata-based approach akin to the reasoning processes of human experts. By shifting from pairwise queries to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17569","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/2503.17569/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":"2503.17569","created_at":"2026-07-05T10:37:49.596667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17569v1","created_at":"2026-07-05T10:37:49.596667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17569","created_at":"2026-07-05T10:37:49.596667+00:00"},{"alias_kind":"pith_short_12","alias_value":"46UVSNZWTQQ4","created_at":"2026-07-05T10:37:49.596667+00:00"},{"alias_kind":"pith_short_16","alias_value":"46UVSNZWTQQ4WTZB","created_at":"2026-07-05T10:37:49.596667+00:00"},{"alias_kind":"pith_short_8","alias_value":"46UVSNZW","created_at":"2026-07-05T10:37:49.596667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00844","citing_title":"LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discovery","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/46UVSNZWTQQ4WTZBLA3GYVJB3P","json":"https://pith.science/pith/46UVSNZWTQQ4WTZBLA3GYVJB3P.json","graph_json":"https://pith.science/api/pith-number/46UVSNZWTQQ4WTZBLA3GYVJB3P/graph.json","events_json":"https://pith.science/api/pith-number/46UVSNZWTQQ4WTZBLA3GYVJB3P/events.json","paper":"https://pith.science/paper/46UVSNZW"},"agent_actions":{"view_html":"https://pith.science/pith/46UVSNZWTQQ4WTZBLA3GYVJB3P","download_json":"https://pith.science/pith/46UVSNZWTQQ4WTZBLA3GYVJB3P.json","view_paper":"https://pith.science/paper/46UVSNZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17569&json=true","fetch_graph":"https://pith.science/api/pith-number/46UVSNZWTQQ4WTZBLA3GYVJB3P/graph.json","fetch_events":"https://pith.science/api/pith-number/46UVSNZWTQQ4WTZBLA3GYVJB3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46UVSNZWTQQ4WTZBLA3GYVJB3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46UVSNZWTQQ4WTZBLA3GYVJB3P/action/storage_attestation","attest_author":"https://pith.science/pith/46UVSNZWTQQ4WTZBLA3GYVJB3P/action/author_attestation","sign_citation":"https://pith.science/pith/46UVSNZWTQQ4WTZBLA3GYVJB3P/action/citation_signature","submit_replication":"https://pith.science/pith/46UVSNZWTQQ4WTZBLA3GYVJB3P/action/replication_record"}},"created_at":"2026-07-05T10:37:49.596667+00:00","updated_at":"2026-07-05T10:37:49.596667+00:00"}