{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WGRJXBIQCNJRFRB3X524ASSECF","short_pith_number":"pith:WGRJXBIQ","schema_version":"1.0","canonical_sha256":"b1a29b8510135312c43bbf75c04a44114d27d3d22a66b2392c92a6aaa480b12d","source":{"kind":"arxiv","id":"2605.15373","version":1},"attestation_state":"computed","paper":{"title":"Nonparametric inference for sublevel-set probabilities of conditional average treatment effect functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The probability that a conditional average treatment effect falls below a given threshold produces a monotone curve summarizing treatment heterogeneity.","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Anders Munch, Thomas A. Gerds","submitted_at":"2026-05-14T20:01:21Z","abstract_excerpt":"The average treatment effect can obscure important heterogeneity when individuals respond differently to a treatment. While the conditional average treatment effect (CATE) function captures such heterogeneity, it is difficult to communicate when it depends on many covariates. Sublevels sets of a multivariate CATE function are equally complicated objects, but the probability of a sublevel set of a CATE function is a single number with a simple interpretation as the proportion of individuals whose expected treatment effect does not exceed a prespecified threshold. By varying the threshold, a uni"},"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":"2605.15373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-05-14T20:01:21Z","cross_cats_sorted":[],"title_canon_sha256":"31486c61816a560bc6952bfaf978eb18ed15e3116ed6aa91c5ab60e54f8ef541","abstract_canon_sha256":"cecc431fb007406f9897ace16ef658ac8a3f341c383f73d4950587ef5c5f8205"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:55.115578Z","signature_b64":"atZL0Lwe05lSDmUz5G51Tu9fVFCdJcduBv++dBp4TLvrfDdY64x5mHJNAaxfiI6v4PBOELkOaUK/POMT0QsBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1a29b8510135312c43bbf75c04a44114d27d3d22a66b2392c92a6aaa480b12d","last_reissued_at":"2026-05-20T00:00:55.114656Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:55.114656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonparametric inference for sublevel-set probabilities of conditional average treatment effect functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The probability that a conditional average treatment effect falls below a given threshold produces a monotone curve summarizing treatment heterogeneity.","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Anders Munch, Thomas A. Gerds","submitted_at":"2026-05-14T20:01:21Z","abstract_excerpt":"The average treatment effect can obscure important heterogeneity when individuals respond differently to a treatment. While the conditional average treatment effect (CATE) function captures such heterogeneity, it is difficult to communicate when it depends on many covariates. Sublevels sets of a multivariate CATE function are equally complicated objects, but the probability of a sublevel set of a CATE function is a single number with a simple interpretation as the proportion of individuals whose expected treatment effect does not exceed a prespecified threshold. By varying the threshold, a uni"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The probability of a sublevel set of a CATE function is a single number with a simple interpretation as the proportion of individuals whose expected treatment effect does not exceed a prespecified threshold. By varying the threshold, a univariate monotone curve appears which can be used to visualize the overall type and degree of heterogeneity in a population. We formalize this curve as a target parameter and show that it is not pathwise differentiable under a nonparametric model.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The CATE function is identifiable from observed data under randomized treatment assignment, allowing the sublevel-set probabilities to be targeted and estimated via monotone function techniques combined with machine learning, as used in the numerical studies based on synthesized randomized trial data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Develops Grenander-type and debiased machine learning estimators for the sublevel-set probability curve of the CATE function, shown to be non-pathwise differentiable, along with its piecewise linear approximation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The probability that a conditional average treatment effect falls below a given threshold produces a monotone curve summarizing treatment heterogeneity.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f1b8615aa20373a341b9f791e53533917e1ab5a9f3b7f6c12cbb9ce11868e170"},"source":{"id":"2605.15373","kind":"arxiv","version":1},"verdict":{"id":"d17e324e-ea83-4eb8-b14d-e702e3d1769a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T15:22:24.254666Z","strongest_claim":"The probability of a sublevel set of a CATE function is a single number with a simple interpretation as the proportion of individuals whose expected treatment effect does not exceed a prespecified threshold. By varying the threshold, a univariate monotone curve appears which can be used to visualize the overall type and degree of heterogeneity in a population. We formalize this curve as a target parameter and show that it is not pathwise differentiable under a nonparametric model.","one_line_summary":"Develops Grenander-type and debiased machine learning estimators for the sublevel-set probability curve of the CATE function, shown to be non-pathwise differentiable, along with its piecewise linear approximation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The CATE function is identifiable from observed data under randomized treatment assignment, allowing the sublevel-set probabilities to be targeted and estimated via monotone function techniques combined with machine learning, as used in the numerical studies based on synthesized randomized trial data.","pith_extraction_headline":"The probability that a conditional average treatment effect falls below a given threshold produces a monotone curve summarizing treatment heterogeneity."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15373/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T15:31:17.878883Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:30:47.442164Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.184111Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.734431Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6f4de12924b6a0ef4145800e6eafde2bc122d7c8e6ed3b83e2952ed3668691d3"},"references":{"count":64,"sample":[{"doi":"","year":2007,"title":"J.-Y. Audibert and A. B. Tsybakov. Fast learning rates for plug-in classifiers. The Annals of Statistics, 2007","work_id":"a2f6f1f8-177c-4003-a661-a2e0eeea535e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1993,"title":"P. J. Bickel, C. A. Klaassen, Y. Ritov, and J. A. Wellner. Efficient and adaptive estimation for semiparametric models, volume 4. Johns Hopkins University Press Baltimore, 1993","work_id":"f9059465-a088-4281-9266-68183b4e3859","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"arXiv preprint arXiv:2306.17464 , year=","work_id":"8b536b3b-76db-491a-93f6-1c1b1d1b7aae","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1996,"title":"L. Breiman. Stacked regressions. Machine learning, 24 0 (1): 0 49--64, 1996","work_id":"0d865e48-18ea-413b-bb13-4c65e4990cec","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1023/a:1010933404324","year":2001,"title":"Random forests","work_id":"97aa461d-2b3e-47c1-a511-e57dccddeff4","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":64,"snapshot_sha256":"e9cc86856da9affe8ac81746b2b653bde2428f3660cc29896531d90a5f049109","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e2b240a26f55dc0e3aaa5d050d01acbb1f76c3973297e198e4a814032f965943"},"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":"2605.15373","created_at":"2026-05-20T00:00:55.114808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15373v1","created_at":"2026-05-20T00:00:55.114808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15373","created_at":"2026-05-20T00:00:55.114808+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGRJXBIQCNJR","created_at":"2026-05-20T00:00:55.114808+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGRJXBIQCNJRFRB3","created_at":"2026-05-20T00:00:55.114808+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGRJXBIQ","created_at":"2026-05-20T00:00:55.114808+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/WGRJXBIQCNJRFRB3X524ASSECF","json":"https://pith.science/pith/WGRJXBIQCNJRFRB3X524ASSECF.json","graph_json":"https://pith.science/api/pith-number/WGRJXBIQCNJRFRB3X524ASSECF/graph.json","events_json":"https://pith.science/api/pith-number/WGRJXBIQCNJRFRB3X524ASSECF/events.json","paper":"https://pith.science/paper/WGRJXBIQ"},"agent_actions":{"view_html":"https://pith.science/pith/WGRJXBIQCNJRFRB3X524ASSECF","download_json":"https://pith.science/pith/WGRJXBIQCNJRFRB3X524ASSECF.json","view_paper":"https://pith.science/paper/WGRJXBIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15373&json=true","fetch_graph":"https://pith.science/api/pith-number/WGRJXBIQCNJRFRB3X524ASSECF/graph.json","fetch_events":"https://pith.science/api/pith-number/WGRJXBIQCNJRFRB3X524ASSECF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGRJXBIQCNJRFRB3X524ASSECF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGRJXBIQCNJRFRB3X524ASSECF/action/storage_attestation","attest_author":"https://pith.science/pith/WGRJXBIQCNJRFRB3X524ASSECF/action/author_attestation","sign_citation":"https://pith.science/pith/WGRJXBIQCNJRFRB3X524ASSECF/action/citation_signature","submit_replication":"https://pith.science/pith/WGRJXBIQCNJRFRB3X524ASSECF/action/replication_record"}},"created_at":"2026-05-20T00:00:55.114808+00:00","updated_at":"2026-05-20T00:00:55.114808+00:00"}