{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XCYILPD3OIOZDYD3EBAKVPJZG5","short_pith_number":"pith:XCYILPD3","schema_version":"1.0","canonical_sha256":"b8b085bc7b721d91e07b2040aabd39375b3f60eaeb865b92ef74220b2e969838","source":{"kind":"arxiv","id":"2505.15215","version":3},"attestation_state":"computed","paper":{"title":"Clustering and Pruning in Causal Data Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Juha Karvanen, Otto Tabell, Santtu Tikka","submitted_at":"2025-05-21T07:44:39Z","abstract_excerpt":"Data fusion, the process of combining observational and experimental data, can enable the identification of causal effects that would otherwise remain non-identifiable. Although identification algorithms have been developed for specific scenarios, do-calculus remains the only general-purpose tool for causal data fusion, particularly when variables are present in some data sources but not others. However, approaches based on do-calculus may encounter computational challenges as the number of variables increases and the causal graph grows in complexity. Consequently, there exists a need to reduc"},"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":"2505.15215","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-21T07:44:39Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"653ee826750d8587defc5d193bc476e86af5829c98645dafab3ad305b5fe62d6","abstract_canon_sha256":"cb06692a641eb8720cd960c494182dd41d199f39d350d89db446c580bb8fadb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:10.951850Z","signature_b64":"2TdadNFhJ53H1TDVNZeSWKVvDVZB8TdZJukWO4ZFJvo0auYfqJjMmVTwNuvctPak0DX+3jV8pZoeGvv3zVIaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8b085bc7b721d91e07b2040aabd39375b3f60eaeb865b92ef74220b2e969838","last_reissued_at":"2026-06-19T16:11:10.951509Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:10.951509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clustering and Pruning in Causal Data Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Juha Karvanen, Otto Tabell, Santtu Tikka","submitted_at":"2025-05-21T07:44:39Z","abstract_excerpt":"Data fusion, the process of combining observational and experimental data, can enable the identification of causal effects that would otherwise remain non-identifiable. Although identification algorithms have been developed for specific scenarios, do-calculus remains the only general-purpose tool for causal data fusion, particularly when variables are present in some data sources but not others. However, approaches based on do-calculus may encounter computational challenges as the number of variables increases and the causal graph grows in complexity. Consequently, there exists a need to reduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15215","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/2505.15215/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":"2505.15215","created_at":"2026-06-19T16:11:10.951565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15215v3","created_at":"2026-06-19T16:11:10.951565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15215","created_at":"2026-06-19T16:11:10.951565+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCYILPD3OIOZ","created_at":"2026-06-19T16:11:10.951565+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCYILPD3OIOZDYD3","created_at":"2026-06-19T16:11:10.951565+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCYILPD3","created_at":"2026-06-19T16:11:10.951565+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/XCYILPD3OIOZDYD3EBAKVPJZG5","json":"https://pith.science/pith/XCYILPD3OIOZDYD3EBAKVPJZG5.json","graph_json":"https://pith.science/api/pith-number/XCYILPD3OIOZDYD3EBAKVPJZG5/graph.json","events_json":"https://pith.science/api/pith-number/XCYILPD3OIOZDYD3EBAKVPJZG5/events.json","paper":"https://pith.science/paper/XCYILPD3"},"agent_actions":{"view_html":"https://pith.science/pith/XCYILPD3OIOZDYD3EBAKVPJZG5","download_json":"https://pith.science/pith/XCYILPD3OIOZDYD3EBAKVPJZG5.json","view_paper":"https://pith.science/paper/XCYILPD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15215&json=true","fetch_graph":"https://pith.science/api/pith-number/XCYILPD3OIOZDYD3EBAKVPJZG5/graph.json","fetch_events":"https://pith.science/api/pith-number/XCYILPD3OIOZDYD3EBAKVPJZG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCYILPD3OIOZDYD3EBAKVPJZG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCYILPD3OIOZDYD3EBAKVPJZG5/action/storage_attestation","attest_author":"https://pith.science/pith/XCYILPD3OIOZDYD3EBAKVPJZG5/action/author_attestation","sign_citation":"https://pith.science/pith/XCYILPD3OIOZDYD3EBAKVPJZG5/action/citation_signature","submit_replication":"https://pith.science/pith/XCYILPD3OIOZDYD3EBAKVPJZG5/action/replication_record"}},"created_at":"2026-06-19T16:11:10.951565+00:00","updated_at":"2026-06-19T16:11:10.951565+00:00"}