{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L4HUQNFGGX2RMSHGL2ENUSDROA","short_pith_number":"pith:L4HUQNFG","schema_version":"1.0","canonical_sha256":"5f0f4834a635f51648e65e88da4871703225702fa72d814a6793991b676aa5c1","source":{"kind":"arxiv","id":"2605.13430","version":1},"attestation_state":"computed","paper":{"title":"Towards a holistic understanding of Selection Bias for Causal Effect Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Necessary and sufficient conditions identify the average treatment effect under selection bias via weak assumptions on probability classes.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ME","authors_text":"Filip Kovacevic, Francesco Locatello, Peter Spirtes, Shimeng Huang, Yiwen Qiu","submitted_at":"2026-05-13T12:24:34Z","abstract_excerpt":"Selection bias is pervasive in observational studies. For example, large scale biobanks data can exhibit ``healthy volunteer bias'' when respondents are healthier and of higher socio-economic status than the population they are meant to represent. Recovering causal effects from such sub-population is an important problem in causal inference, as estimating average treatment effects (ATE) from selected populations can result in a severely biased estimate of the ATE from the whole population.\n  In this paper, we investigate the identifiability of the ATE under selection bias. We provide necessary"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.13430","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2026-05-13T12:24:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d817ef54ccd0653c1fcbe50a34e3768273a314dca05a052eb52a003dd0432c45","abstract_canon_sha256":"4538e55dd25b1612bb612f24952653ec437f34d73916b11213ef0304cf8be11e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:47.193095Z","signature_b64":"4b8ZvcZE2KhMflAZUR0iIx7saocxDwzSoN9p1Zu+0MsxjX6yLpD782Apm9+TisrquAB+iCl76lWYnzzKIxumBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f0f4834a635f51648e65e88da4871703225702fa72d814a6793991b676aa5c1","last_reissued_at":"2026-05-18T02:44:47.192685Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:47.192685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards a holistic understanding of Selection Bias for Causal Effect Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Necessary and sufficient conditions identify the average treatment effect under selection bias via weak assumptions on probability classes.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ME","authors_text":"Filip Kovacevic, Francesco Locatello, Peter Spirtes, Shimeng Huang, Yiwen Qiu","submitted_at":"2026-05-13T12:24:34Z","abstract_excerpt":"Selection bias is pervasive in observational studies. For example, large scale biobanks data can exhibit ``healthy volunteer bias'' when respondents are healthier and of higher socio-economic status than the population they are meant to represent. Recovering causal effects from such sub-population is an important problem in causal inference, as estimating average treatment effects (ATE) from selected populations can result in a severely biased estimate of the ATE from the whole population.\n  In this paper, we investigate the identifiability of the ATE under selection bias. We provide necessary"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We provide necessary and sufficient conditions for ATE identifiability, leveraging weak assumptions on probability classes to characterize propensity score and selection probability. Compared to previous works, our results extend existing graphical identifiability criteria and offer a more comprehensive understanding of causal effect identification with strictly weaker conditions in the presence of selection bias.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The weak assumptions on probability classes that allow characterization of the propensity score and selection probability (stated in the abstract as the basis for the necessary and sufficient conditions).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Necessary and sufficient conditions for ATE identifiability under selection bias using weaker assumptions on probability classes than prior graphical criteria.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Necessary and sufficient conditions identify the average treatment effect under selection bias via weak assumptions on probability classes.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"635abfd68065ead1a59123997fef4b72fe0e6a44a1b52846858d9664592eb086"},"source":{"id":"2605.13430","kind":"arxiv","version":1},"verdict":{"id":"3d5fd522-7d5e-4a0d-8730-a76df4bb633a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:20:22.430075Z","strongest_claim":"We provide necessary and sufficient conditions for ATE identifiability, leveraging weak assumptions on probability classes to characterize propensity score and selection probability. Compared to previous works, our results extend existing graphical identifiability criteria and offer a more comprehensive understanding of causal effect identification with strictly weaker conditions in the presence of selection bias.","one_line_summary":"Necessary and sufficient conditions for ATE identifiability under selection bias using weaker assumptions on probability classes than prior graphical criteria.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The weak assumptions on probability classes that allow characterization of the propensity score and selection probability (stated in the abstract as the basis for the necessary and sufficient conditions).","pith_extraction_headline":"Necessary and sufficient conditions identify the average treatment effect under selection bias via weak assumptions on probability classes."},"references":{"count":85,"sample":[{"doi":"","year":2015,"title":"Causal inference in statistics, social, and biomedical sciences , author=. 2015 , publisher=","work_id":"965ef5ad-5e9d-4649-b964-b9d809a8f5e2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Abouei, Amir Mohammad and Mokhtarian, Ehsan and Kiyavash, Negar and Grossglauser, Matthias , langid =. Causal","work_id":"d1133cfa-8aa8-45ab-accd-0d8c0fea37d5","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.48550/arxiv.2309.02281","year":2024,"title":"Abouei, Amir Mohammad and Mokhtarian, Ehsan and Kiyavash, Negar , year = 2024, month = jan, number =. S-. doi:10.48550/arXiv.2309.02281 , urldate =. 2309.02281 , primaryclass =","work_id":"9d6cd419-c45c-424b-9d3f-50bd5884eb6d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1609/aaai.v25i1.8056","year":2011,"title":"Bareinboim, Elias and Pearl, Judea , year = 2011, month = aug, journal =. Controlling. doi:10.1609/aaai.v25i1.8056 , urldate =","work_id":"4d61d94f-5369-4b40-a190-7ecc01ac6388","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Bellot, Alexis , langid =. Towards","work_id":"b60fa5e3-48c1-4be6-b83f-d8b9562880bc","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":85,"snapshot_sha256":"b851e1caadf688b65ec83532adfae94768bd900e3b5972232f040d33b85687b3","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"dcd8c02d36f53df6c182926f4a29077f196988db6600877173a54569c5259c4f"},"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":"2605.13430","created_at":"2026-05-18T02:44:47.192750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13430v1","created_at":"2026-05-18T02:44:47.192750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13430","created_at":"2026-05-18T02:44:47.192750+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4HUQNFGGX2R","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4HUQNFGGX2RMSHG","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4HUQNFG","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4HUQNFGGX2RMSHGL2ENUSDROA","json":"https://pith.science/pith/L4HUQNFGGX2RMSHGL2ENUSDROA.json","graph_json":"https://pith.science/api/pith-number/L4HUQNFGGX2RMSHGL2ENUSDROA/graph.json","events_json":"https://pith.science/api/pith-number/L4HUQNFGGX2RMSHGL2ENUSDROA/events.json","paper":"https://pith.science/paper/L4HUQNFG"},"agent_actions":{"view_html":"https://pith.science/pith/L4HUQNFGGX2RMSHGL2ENUSDROA","download_json":"https://pith.science/pith/L4HUQNFGGX2RMSHGL2ENUSDROA.json","view_paper":"https://pith.science/paper/L4HUQNFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13430&json=true","fetch_graph":"https://pith.science/api/pith-number/L4HUQNFGGX2RMSHGL2ENUSDROA/graph.json","fetch_events":"https://pith.science/api/pith-number/L4HUQNFGGX2RMSHGL2ENUSDROA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4HUQNFGGX2RMSHGL2ENUSDROA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4HUQNFGGX2RMSHGL2ENUSDROA/action/storage_attestation","attest_author":"https://pith.science/pith/L4HUQNFGGX2RMSHGL2ENUSDROA/action/author_attestation","sign_citation":"https://pith.science/pith/L4HUQNFGGX2RMSHGL2ENUSDROA/action/citation_signature","submit_replication":"https://pith.science/pith/L4HUQNFGGX2RMSHGL2ENUSDROA/action/replication_record"}},"created_at":"2026-05-18T02:44:47.192750+00:00","updated_at":"2026-05-18T02:44:47.192750+00:00"}