{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UDD4BIWH46V3JQDYRZCWULZT4U","short_pith_number":"pith:UDD4BIWH","schema_version":"1.0","canonical_sha256":"a0c7c0a2c7e7abb4c0788e456a2f33e5327cc2b79bf02cb1f3848ab1dd74bd4d","source":{"kind":"arxiv","id":"2406.06227","version":2},"attestation_state":"computed","paper":{"title":"PAC-Bayes Analysis for Recalibration in Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Futoshi Futami, Masahiro Fujisawa","submitted_at":"2024-06-10T12:53:13Z","abstract_excerpt":"Nonparametric estimation using uniform-width binning is a standard approach for evaluating the calibration performance of machine learning models. However, existing theoretical analyses of the bias induced by binning are limited to binary classification, creating a significant gap with practical applications such as multiclass classification. Additionally, many parametric recalibration algorithms lack theoretical guarantees for their generalization performance. To address these issues, we conduct a generalization analysis of calibration error using the probably approximately correct Bayes fram"},"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":"2406.06227","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T12:53:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5d1137edbcb143ab058b78c3f466843fe0cb5615d5706446c6ed25da2b40ea6e","abstract_canon_sha256":"aa22bcdc6ccdd933d400175f6b2d67030f839d6d1aa3351fbf32fbd36547ac07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:10.103970Z","signature_b64":"0W0GpDDkylLFxcThiu43pPhGRcsjmEc9O9KqIyipB5sDB3EVKnyVgGIBTTIH8TK3G+w4vcppPuRxsgsjFvcDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0c7c0a2c7e7abb4c0788e456a2f33e5327cc2b79bf02cb1f3848ab1dd74bd4d","last_reissued_at":"2026-07-05T11:35:10.103471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:10.103471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAC-Bayes Analysis for Recalibration in Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Futoshi Futami, Masahiro Fujisawa","submitted_at":"2024-06-10T12:53:13Z","abstract_excerpt":"Nonparametric estimation using uniform-width binning is a standard approach for evaluating the calibration performance of machine learning models. However, existing theoretical analyses of the bias induced by binning are limited to binary classification, creating a significant gap with practical applications such as multiclass classification. Additionally, many parametric recalibration algorithms lack theoretical guarantees for their generalization performance. To address these issues, we conduct a generalization analysis of calibration error using the probably approximately correct Bayes fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06227","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/2406.06227/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":"2406.06227","created_at":"2026-07-05T11:35:10.103523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06227v2","created_at":"2026-07-05T11:35:10.103523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06227","created_at":"2026-07-05T11:35:10.103523+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDD4BIWH46V3","created_at":"2026-07-05T11:35:10.103523+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDD4BIWH46V3JQDY","created_at":"2026-07-05T11:35:10.103523+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDD4BIWH","created_at":"2026-07-05T11:35:10.103523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.07419","citing_title":"Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration","ref_index":284,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDD4BIWH46V3JQDYRZCWULZT4U","json":"https://pith.science/pith/UDD4BIWH46V3JQDYRZCWULZT4U.json","graph_json":"https://pith.science/api/pith-number/UDD4BIWH46V3JQDYRZCWULZT4U/graph.json","events_json":"https://pith.science/api/pith-number/UDD4BIWH46V3JQDYRZCWULZT4U/events.json","paper":"https://pith.science/paper/UDD4BIWH"},"agent_actions":{"view_html":"https://pith.science/pith/UDD4BIWH46V3JQDYRZCWULZT4U","download_json":"https://pith.science/pith/UDD4BIWH46V3JQDYRZCWULZT4U.json","view_paper":"https://pith.science/paper/UDD4BIWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06227&json=true","fetch_graph":"https://pith.science/api/pith-number/UDD4BIWH46V3JQDYRZCWULZT4U/graph.json","fetch_events":"https://pith.science/api/pith-number/UDD4BIWH46V3JQDYRZCWULZT4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDD4BIWH46V3JQDYRZCWULZT4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDD4BIWH46V3JQDYRZCWULZT4U/action/storage_attestation","attest_author":"https://pith.science/pith/UDD4BIWH46V3JQDYRZCWULZT4U/action/author_attestation","sign_citation":"https://pith.science/pith/UDD4BIWH46V3JQDYRZCWULZT4U/action/citation_signature","submit_replication":"https://pith.science/pith/UDD4BIWH46V3JQDYRZCWULZT4U/action/replication_record"}},"created_at":"2026-07-05T11:35:10.103523+00:00","updated_at":"2026-07-05T11:35:10.103523+00:00"}