{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V55XZYK2HASK3NDXNHQME2X2WL","short_pith_number":"pith:V55XZYK2","schema_version":"1.0","canonical_sha256":"af7b7ce15a3824adb47769e0c26afab2c733a8de9b0611a9b3cbb09193eb8ff5","source":{"kind":"arxiv","id":"2605.12947","version":1},"attestation_state":"computed","paper":{"title":"When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A hard-negative reference pool of high-scoring failures gives finite-sample control over when black-box AI workflows release outputs on infeasible tasks.","cross_cats":["cs.AI","cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Will Wei Sun, Young Hyun Cho","submitted_at":"2026-05-13T03:30:39Z","abstract_excerpt":"LLM-enabled AI workflows increasingly produce outputs through iterative generate-evaluate-revise loops. Each iteration can improve the candidate, but it also creates a release decision: when to stop and output the current result? This raises a statistical challenge because deployment-time evaluator scores are adaptively generated and repeatedly monitored, yet the likelihood models or exchangeability assumptions typically used for calibration are unavailable. We propose an always-valid release wrapper for existing generator-evaluator pipelines. The wrapper builds a hard-negative reference pool "},"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":"2605.12947","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-13T03:30:39Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ME"],"title_canon_sha256":"01075e14f89e8ed7c06fe2ba3ff7657279947c0f3ac38e7d7ff1adb4693fd8cd","abstract_canon_sha256":"72766323ae5962a588ec581f64b33632f7ee70c50106b8915a017a7757009e8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:09.474448Z","signature_b64":"VhUcEJ2HtzFKH4VOecOppQZVnieVbeFYJQDxPkNhqLtZwumnVFU6t0WADWBV5ARhSodVIdbB7iODD/WCXhaGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af7b7ce15a3824adb47769e0c26afab2c733a8de9b0611a9b3cbb09193eb8ff5","last_reissued_at":"2026-05-18T03:09:09.473696Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:09.473696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A hard-negative reference pool of high-scoring failures gives finite-sample control over when black-box AI workflows release outputs on infeasible tasks.","cross_cats":["cs.AI","cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Will Wei Sun, Young Hyun Cho","submitted_at":"2026-05-13T03:30:39Z","abstract_excerpt":"LLM-enabled AI workflows increasingly produce outputs through iterative generate-evaluate-revise loops. Each iteration can improve the candidate, but it also creates a release decision: when to stop and output the current result? This raises a statistical challenge because deployment-time evaluator scores are adaptively generated and repeatedly monitored, yet the likelihood models or exchangeability assumptions typically used for calibration are unavailable. We propose an always-valid release wrapper for existing generator-evaluator pipelines. The wrapper builds a hard-negative reference pool "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"a conservative reference pool yields finite-sample control of the probability of releasing on infeasible tasks, that is, tasks for which the given workflow is not capable of producing a reliable solution.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a hard-negative reference pool of high-scoring failures can be built that is sufficiently conservative to deliver finite-sample error control yet not so conservative that it blocks release on feasible tasks where moderate evidence accumulates.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A wrapper for black-box generate-verify AI pipelines that uses a conservative hard-negative reference pool and e-processes to control the probability of releasing on infeasible tasks while permitting release on feasible ones.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A hard-negative reference pool of high-scoring failures gives finite-sample control over when black-box AI workflows release outputs on infeasible tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d6ed464d3a0f39498e9767f82890870b38f93e78a07c32f1c91969d2c7d67ac9"},"source":{"id":"2605.12947","kind":"arxiv","version":1},"verdict":{"id":"759046d7-11ba-4f93-bfda-fcba9532a8d5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:57:54.318635Z","strongest_claim":"a conservative reference pool yields finite-sample control of the probability of releasing on infeasible tasks, that is, tasks for which the given workflow is not capable of producing a reliable solution.","one_line_summary":"A wrapper for black-box generate-verify AI pipelines that uses a conservative hard-negative reference pool and e-processes to control the probability of releasing on infeasible tasks while permitting release on feasible ones.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a hard-negative reference pool of high-scoring failures can be built that is sufficiently conservative to deliver finite-sample error control yet not so conservative that it blocks release on feasible tasks where moderate evidence accumulates.","pith_extraction_headline":"A hard-negative reference pool of high-scoring failures gives finite-sample control over when black-box AI workflows release outputs on infeasible tasks."},"references":{"count":34,"sample":[{"doi":"","year":2022,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","ref_index":1,"cited_arxiv_id":"2204.01691","is_internal_anchor":true},{"doi":"","year":2021,"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","ref_index":2,"cited_arxiv_id":"2108.07732","is_internal_anchor":true},{"doi":"","year":2023,"title":"Barber, R. F., Candes, E. J., Ramdas, A. & Tibshirani, R. J. (2023), ‘Conformal prediction beyond exchangeability’,The Annals of Statistics51(2), 816–845","work_id":"2a2aea3c-ed42-4bdb-9daa-3bbde6ab6f40","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","ref_index":4,"cited_arxiv_id":"2110.14168","is_internal_anchor":true},{"doi":"","year":1939,"title":"Doob, J. L. (1939), ‘Jean ville, étude critique de la notion de collectif’. Grünwald, P., de Heide, R. & Koolen, W. M. (2020), Safe testing,in‘2020 Information theory and applications workshop (ITA)’,","work_id":"06d30615-0172-4a24-9a77-3ec52e543bdf","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":34,"snapshot_sha256":"3363bb7ec6aeaad48b662dc5ad9acaca1e7cd8fb7ff7bf2e3f2f026903581a7e","internal_anchors":9},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6336e7875bc67fd09e05c2aaae5560c451ddb0f37d39978df76ba35831073bf4"},"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":"2605.12947","created_at":"2026-05-18T03:09:09.473796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12947v1","created_at":"2026-05-18T03:09:09.473796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12947","created_at":"2026-05-18T03:09:09.473796+00:00"},{"alias_kind":"pith_short_12","alias_value":"V55XZYK2HASK","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"V55XZYK2HASK3NDX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"V55XZYK2","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/V55XZYK2HASK3NDXNHQME2X2WL","json":"https://pith.science/pith/V55XZYK2HASK3NDXNHQME2X2WL.json","graph_json":"https://pith.science/api/pith-number/V55XZYK2HASK3NDXNHQME2X2WL/graph.json","events_json":"https://pith.science/api/pith-number/V55XZYK2HASK3NDXNHQME2X2WL/events.json","paper":"https://pith.science/paper/V55XZYK2"},"agent_actions":{"view_html":"https://pith.science/pith/V55XZYK2HASK3NDXNHQME2X2WL","download_json":"https://pith.science/pith/V55XZYK2HASK3NDXNHQME2X2WL.json","view_paper":"https://pith.science/paper/V55XZYK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12947&json=true","fetch_graph":"https://pith.science/api/pith-number/V55XZYK2HASK3NDXNHQME2X2WL/graph.json","fetch_events":"https://pith.science/api/pith-number/V55XZYK2HASK3NDXNHQME2X2WL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V55XZYK2HASK3NDXNHQME2X2WL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V55XZYK2HASK3NDXNHQME2X2WL/action/storage_attestation","attest_author":"https://pith.science/pith/V55XZYK2HASK3NDXNHQME2X2WL/action/author_attestation","sign_citation":"https://pith.science/pith/V55XZYK2HASK3NDXNHQME2X2WL/action/citation_signature","submit_replication":"https://pith.science/pith/V55XZYK2HASK3NDXNHQME2X2WL/action/replication_record"}},"created_at":"2026-05-18T03:09:09.473796+00:00","updated_at":"2026-05-18T03:09:09.473796+00:00"}