{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GZT4H2SNPHWO7UFBCXSOKRQRIR","short_pith_number":"pith:GZT4H2SN","schema_version":"1.0","canonical_sha256":"3667c3ea4d79ecefd0a115e4e546114472a2b58cdd27744717196e89ff9394d5","source":{"kind":"arxiv","id":"2602.02285","version":2},"attestation_state":"computed","paper":{"title":"AI4SLT: Empirical Processes in Lean 4 for Formal Statistical Learning Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Fanghui Liu, Jason D. Lee, Yuanhe Zhang","submitted_at":"2026-02-02T16:24:53Z","abstract_excerpt":"We present the first comprehensive Lean 4 formalization of statistical learning theory (SLT) grounded in empirical process theory. Our en-to-end formal infrastructure implement the missing contents in latest Lean library, including a complete development of Gaussian Lipschitz concentration, Dudley's entropy integral theorem for sub-Gaussian processes, and an application to least-squares (sparse) regression with a sharp rate. The project was carried out using a human-AI collaborative workflow, in which humans design proof strategies and AI agents execute tactical proof construction, leading to "},"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":"2602.02285","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T16:24:53Z","cross_cats_sorted":["cs.CL","math.ST","stat.TH"],"title_canon_sha256":"8a1f45b3cdb81dbb42ca49aed3de83219d563dff0d6d5ff3deaa80576a9e6f1b","abstract_canon_sha256":"7ff31e4660645fe834590d74c14658b923b5e9bcff30d22a72c7a865bfa1bcad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:32.319015Z","signature_b64":"+YAtw+ghy9ugFjXBYxY3ynKaLdVbE9BNWvxlaYh3DKmj+t36feEfKoIRh2yn+H3IldaGsaeTK+DWhiJ3FrbHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3667c3ea4d79ecefd0a115e4e546114472a2b58cdd27744717196e89ff9394d5","last_reissued_at":"2026-06-11T01:10:32.317958Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:32.317958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI4SLT: Empirical Processes in Lean 4 for Formal Statistical Learning Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Fanghui Liu, Jason D. Lee, Yuanhe Zhang","submitted_at":"2026-02-02T16:24:53Z","abstract_excerpt":"We present the first comprehensive Lean 4 formalization of statistical learning theory (SLT) grounded in empirical process theory. Our en-to-end formal infrastructure implement the missing contents in latest Lean library, including a complete development of Gaussian Lipschitz concentration, Dudley's entropy integral theorem for sub-Gaussian processes, and an application to least-squares (sparse) regression with a sharp rate. The project was carried out using a human-AI collaborative workflow, in which humans design proof strategies and AI agents execute tactical proof construction, leading to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02285","kind":"arxiv","version":2},"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/2602.02285/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":"2602.02285","created_at":"2026-06-11T01:10:32.318094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.02285v2","created_at":"2026-06-11T01:10:32.318094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02285","created_at":"2026-06-11T01:10:32.318094+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZT4H2SNPHWO","created_at":"2026-06-11T01:10:32.318094+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZT4H2SNPHWO7UFB","created_at":"2026-06-11T01:10:32.318094+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZT4H2SN","created_at":"2026-06-11T01:10:32.318094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.21492","citing_title":"The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity","ref_index":81,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZT4H2SNPHWO7UFBCXSOKRQRIR","json":"https://pith.science/pith/GZT4H2SNPHWO7UFBCXSOKRQRIR.json","graph_json":"https://pith.science/api/pith-number/GZT4H2SNPHWO7UFBCXSOKRQRIR/graph.json","events_json":"https://pith.science/api/pith-number/GZT4H2SNPHWO7UFBCXSOKRQRIR/events.json","paper":"https://pith.science/paper/GZT4H2SN"},"agent_actions":{"view_html":"https://pith.science/pith/GZT4H2SNPHWO7UFBCXSOKRQRIR","download_json":"https://pith.science/pith/GZT4H2SNPHWO7UFBCXSOKRQRIR.json","view_paper":"https://pith.science/paper/GZT4H2SN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.02285&json=true","fetch_graph":"https://pith.science/api/pith-number/GZT4H2SNPHWO7UFBCXSOKRQRIR/graph.json","fetch_events":"https://pith.science/api/pith-number/GZT4H2SNPHWO7UFBCXSOKRQRIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZT4H2SNPHWO7UFBCXSOKRQRIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZT4H2SNPHWO7UFBCXSOKRQRIR/action/storage_attestation","attest_author":"https://pith.science/pith/GZT4H2SNPHWO7UFBCXSOKRQRIR/action/author_attestation","sign_citation":"https://pith.science/pith/GZT4H2SNPHWO7UFBCXSOKRQRIR/action/citation_signature","submit_replication":"https://pith.science/pith/GZT4H2SNPHWO7UFBCXSOKRQRIR/action/replication_record"}},"created_at":"2026-06-11T01:10:32.318094+00:00","updated_at":"2026-06-11T01:10:32.318094+00:00"}