{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TDN3ASGWEAEV4DRHKPLG7JW36H","short_pith_number":"pith:TDN3ASGW","schema_version":"1.0","canonical_sha256":"98dbb048d620095e0e2753d66fa6dbf1c1692ec6eae16f072930b031cad75422","source":{"kind":"arxiv","id":"2605.03406","version":2},"attestation_state":"computed","paper":{"title":"A General Framework for Optimal Group Sequential Testing via Mixed-Integer Linear Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Mixed-integer linear programming finds optimal rejection boundaries for group sequential tests that allow earlier stopping than standard methods.","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Dae Woong Ham, Stefanus Jasin, Xuejun Zhao","submitted_at":"2026-05-05T06:25:52Z","abstract_excerpt":"Sequential hypothesis tests are widely adopted as a principled way to perform multiple tests on data that arrives over time. In particular, researchers frequently utilize group sequential hypothesis tests (GST) to test the same hypotheses at K times or \"groups\" while data arrives sequentially. In this setting, many methods have been proposed to allow researchers to uniformly control type-1 error across K checks (often known as various alpha-spending budgets). Although these methods are all successfully valid in controlling uniform type-1 error, it is not clear which of these methods are optima"},"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":"2605.03406","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2026-05-05T06:25:52Z","cross_cats_sorted":[],"title_canon_sha256":"adf1c18d83ed7be9b921b162b48cac2988fe566873e4061c4c45289134cd20e9","abstract_canon_sha256":"b86cc1617bf7f2dc2a31a1a614b162d674c0bfbc553e5a26f0394c3958235a40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:42.614127Z","signature_b64":"DRVouWLYjUnCRfuKFJ7KgycuETgdPezozo138qZWY9iAHpxIFB+KXZXTwmXXmRbKGiH0iKaRRaRqh2KRrmmFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98dbb048d620095e0e2753d66fa6dbf1c1692ec6eae16f072930b031cad75422","last_reissued_at":"2026-05-20T00:01:42.613524Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:42.613524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A General Framework for Optimal Group Sequential Testing via Mixed-Integer Linear Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Mixed-integer linear programming finds optimal rejection boundaries for group sequential tests that allow earlier stopping than standard methods.","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Dae Woong Ham, Stefanus Jasin, Xuejun Zhao","submitted_at":"2026-05-05T06:25:52Z","abstract_excerpt":"Sequential hypothesis tests are widely adopted as a principled way to perform multiple tests on data that arrives over time. In particular, researchers frequently utilize group sequential hypothesis tests (GST) to test the same hypotheses at K times or \"groups\" while data arrives sequentially. In this setting, many methods have been proposed to allow researchers to uniformly control type-1 error across K checks (often known as various alpha-spending budgets). Although these methods are all successfully valid in controlling uniform type-1 error, it is not clear which of these methods are optima"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We use a sample average approximation combined with mixed integer linear programming (S-MILP) approach for this problem and show how our S-MILP approach dominates classical GST procedures such as Lan-DeMets, Pocock, and O'Brien-Fleming methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The sample average approximation provides a sufficiently accurate representation of the true type-1 and type-2 error probabilities for the optimized boundaries to maintain the desired error control in practice.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The authors propose an S-MILP framework that optimizes group sequential testing boundaries to achieve faster rejection of the null hypothesis compared to traditional methods while controlling type I and type II errors.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Mixed-integer linear programming finds optimal rejection boundaries for group sequential tests that allow earlier stopping than standard methods.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ca32b4c015ddb2a98f96cfdca2e3c1693765024ee73bc7113de1b1910f918073"},"source":{"id":"2605.03406","kind":"arxiv","version":2},"verdict":{"id":"e7410fb2-c40e-4bba-9545-49fe7e082953","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T18:12:45.296775Z","strongest_claim":"We use a sample average approximation combined with mixed integer linear programming (S-MILP) approach for this problem and show how our S-MILP approach dominates classical GST procedures such as Lan-DeMets, Pocock, and O'Brien-Fleming methods.","one_line_summary":"The authors propose an S-MILP framework that optimizes group sequential testing boundaries to achieve faster rejection of the null hypothesis compared to traditional methods while controlling type I and type II errors.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The sample average approximation provides a sufficiently accurate representation of the true type-1 and type-2 error probabilities for the optimized boundaries to maintain the desired error control in practice.","pith_extraction_headline":"Mixed-integer linear programming finds optimal rejection boundaries for group sequential tests that allow earlier stopping than standard methods."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.03406/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T15:26:23.807489Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ab30930f3262d499199f9a07bb6fb13240d953934136ec317b67c2097cc3e9a5"},"references":{"count":179,"sample":[{"doi":"","year":1992,"title":"Eales, J. D. and Jennison, C. , title =. Biometrika , volume =. 1992 , doi =","work_id":"ad1d664f-b0b6-458b-ac37-9771d493fdae","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"Hampson, L. V. and Jennison, C. , title =. Journal of the Royal Statistical Society, Series B , volume =. 2013 , doi =","work_id":"47a09662-fbaa-41da-9c27-e7327e91173b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Lectures on stochastic programming: modeling and theory , author=. 2021 , publisher=","work_id":"e4ef80c4-907f-415d-952c-42ead03a2c08","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Introduction to sample size determination and power analysis for clinical trials. , author=. Controlled clinical trials , year=","work_id":"8c71a3f8-6cab-4459-a2ae-15078ab942b7","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Cohen, J. , biburl =","work_id":"3850d5e9-63b9-4f25-9838-0e46793c1502","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":179,"snapshot_sha256":"2a8d99a912b3e4d642b1abb65706975e7efcc563de7e5eec3ad8525d2b6d94e0","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8e80ffc10d579b63c9887bd008bbc7bfb9a518b4059c4fc1a9a9922d100544d3"},"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":"2605.03406","created_at":"2026-05-20T00:01:42.613616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.03406v2","created_at":"2026-05-20T00:01:42.613616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03406","created_at":"2026-05-20T00:01:42.613616+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDN3ASGWEAEV","created_at":"2026-05-20T00:01:42.613616+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDN3ASGWEAEV4DRH","created_at":"2026-05-20T00:01:42.613616+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDN3ASGW","created_at":"2026-05-20T00:01:42.613616+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/TDN3ASGWEAEV4DRHKPLG7JW36H","json":"https://pith.science/pith/TDN3ASGWEAEV4DRHKPLG7JW36H.json","graph_json":"https://pith.science/api/pith-number/TDN3ASGWEAEV4DRHKPLG7JW36H/graph.json","events_json":"https://pith.science/api/pith-number/TDN3ASGWEAEV4DRHKPLG7JW36H/events.json","paper":"https://pith.science/paper/TDN3ASGW"},"agent_actions":{"view_html":"https://pith.science/pith/TDN3ASGWEAEV4DRHKPLG7JW36H","download_json":"https://pith.science/pith/TDN3ASGWEAEV4DRHKPLG7JW36H.json","view_paper":"https://pith.science/paper/TDN3ASGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.03406&json=true","fetch_graph":"https://pith.science/api/pith-number/TDN3ASGWEAEV4DRHKPLG7JW36H/graph.json","fetch_events":"https://pith.science/api/pith-number/TDN3ASGWEAEV4DRHKPLG7JW36H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDN3ASGWEAEV4DRHKPLG7JW36H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDN3ASGWEAEV4DRHKPLG7JW36H/action/storage_attestation","attest_author":"https://pith.science/pith/TDN3ASGWEAEV4DRHKPLG7JW36H/action/author_attestation","sign_citation":"https://pith.science/pith/TDN3ASGWEAEV4DRHKPLG7JW36H/action/citation_signature","submit_replication":"https://pith.science/pith/TDN3ASGWEAEV4DRHKPLG7JW36H/action/replication_record"}},"created_at":"2026-05-20T00:01:42.613616+00:00","updated_at":"2026-05-20T00:01:42.613616+00:00"}