{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4ZDTJYPX4CA2AMIJZDVRJG6OL2","short_pith_number":"pith:4ZDTJYPX","schema_version":"1.0","canonical_sha256":"e64734e1f7e081a03109c8eb149bce5e9ce36f697ea4de67929f36a6967e02e6","source":{"kind":"arxiv","id":"2606.31600","version":1},"attestation_state":"computed","paper":{"title":"On Optimal Data Splitting for Split Conformal Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Bahram Yaghooti, Sayan Das, Soumendra N. Lahiri, Todd A. Kuffner","submitted_at":"2026-06-30T12:49:44Z","abstract_excerpt":"Conformal prediction and its variants, including the split conformal prediction, provide a distribution-free framework for uncertainty quantification by constructing prediction intervals or sets with finite-sample coverage guarantees. The statistical efficiency of these intervals depends critically on how the data are split into training and calibration samples. Despite its practical importance, a principled characterization of the training-calibration split that minimizes prediction interval length while maintaining coverage has remained largely unresolved. In this paper, we develop a theoret"},"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":"2606.31600","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2026-06-30T12:49:44Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"2f1bd8da74057e93aa328fb0e90ddefe116835a8b605d505dce0042a8f4bf934","abstract_canon_sha256":"d0468bed50003d5b00f2b3d536cf8bf8a614018ba13a9619f022eb931a0517a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:08.765834Z","signature_b64":"scutwAtx/Uwq5k31BXnuDzS8AKg35PkqpNDkvPfv6u0E9YiFwHQ6Q/ogLPpU207aq+3f0RQqmeaiSJZIYxe6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e64734e1f7e081a03109c8eb149bce5e9ce36f697ea4de67929f36a6967e02e6","last_reissued_at":"2026-07-01T01:18:08.765364Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:08.765364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Optimal Data Splitting for Split Conformal Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Bahram Yaghooti, Sayan Das, Soumendra N. Lahiri, Todd A. Kuffner","submitted_at":"2026-06-30T12:49:44Z","abstract_excerpt":"Conformal prediction and its variants, including the split conformal prediction, provide a distribution-free framework for uncertainty quantification by constructing prediction intervals or sets with finite-sample coverage guarantees. The statistical efficiency of these intervals depends critically on how the data are split into training and calibration samples. Despite its practical importance, a principled characterization of the training-calibration split that minimizes prediction interval length while maintaining coverage has remained largely unresolved. In this paper, we develop a theoret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31600","kind":"arxiv","version":1},"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/2606.31600/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":"2606.31600","created_at":"2026-07-01T01:18:08.765426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31600v1","created_at":"2026-07-01T01:18:08.765426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31600","created_at":"2026-07-01T01:18:08.765426+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZDTJYPX4CA2","created_at":"2026-07-01T01:18:08.765426+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZDTJYPX4CA2AMIJ","created_at":"2026-07-01T01:18:08.765426+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZDTJYPX","created_at":"2026-07-01T01:18:08.765426+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/4ZDTJYPX4CA2AMIJZDVRJG6OL2","json":"https://pith.science/pith/4ZDTJYPX4CA2AMIJZDVRJG6OL2.json","graph_json":"https://pith.science/api/pith-number/4ZDTJYPX4CA2AMIJZDVRJG6OL2/graph.json","events_json":"https://pith.science/api/pith-number/4ZDTJYPX4CA2AMIJZDVRJG6OL2/events.json","paper":"https://pith.science/paper/4ZDTJYPX"},"agent_actions":{"view_html":"https://pith.science/pith/4ZDTJYPX4CA2AMIJZDVRJG6OL2","download_json":"https://pith.science/pith/4ZDTJYPX4CA2AMIJZDVRJG6OL2.json","view_paper":"https://pith.science/paper/4ZDTJYPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31600&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZDTJYPX4CA2AMIJZDVRJG6OL2/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZDTJYPX4CA2AMIJZDVRJG6OL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZDTJYPX4CA2AMIJZDVRJG6OL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZDTJYPX4CA2AMIJZDVRJG6OL2/action/storage_attestation","attest_author":"https://pith.science/pith/4ZDTJYPX4CA2AMIJZDVRJG6OL2/action/author_attestation","sign_citation":"https://pith.science/pith/4ZDTJYPX4CA2AMIJZDVRJG6OL2/action/citation_signature","submit_replication":"https://pith.science/pith/4ZDTJYPX4CA2AMIJZDVRJG6OL2/action/replication_record"}},"created_at":"2026-07-01T01:18:08.765426+00:00","updated_at":"2026-07-01T01:18:08.765426+00:00"}