{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6ROXNFMDEZZM4BL7NE63FVXIAJ","short_pith_number":"pith:6ROXNFMD","schema_version":"1.0","canonical_sha256":"f45d7695832672ce057f693db2d6e8027884da5ecf99105350eca293fdf7614c","source":{"kind":"arxiv","id":"2501.17731","version":1},"attestation_state":"computed","paper":{"title":"Exact characterization of {\\epsilon}-Safe Decision Regions for exponential family distributions and Multi Cost SVM approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alberto Carlevaro, Fabrizio Dabbene, Maurizio Mongelli, Teodoro Alamo","submitted_at":"2025-01-29T16:14:35Z","abstract_excerpt":"Probabilistic guarantees on the prediction of data-driven classifiers are necessary to define models that can be considered reliable. This is a key requirement for modern machine learning in which the goodness of a system is measured in terms of trustworthiness, clearly dividing what is safe from what is unsafe. The spirit of this paper is exactly in this direction. First, we introduce a formal definition of {\\epsilon}-Safe Decision Region, a subset of the input space in which the prediction of a target (safe) class is probabilistically guaranteed. Second, we prove that, when data come from ex"},"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":"2501.17731","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-29T16:14:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fa86361e82bafb0d6e8cc90b6d67fe9334dbf7da1c8ca3c39b0b8c9898babd28","abstract_canon_sha256":"1d819be2f89987f94be2e34af1f4707f425e53e5897e5ae1e7787aef6530c5d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:57.076749Z","signature_b64":"WYrsUKUyvE5XUL++U7/q2Uu3fkHmqcjnjur9w49Gi8OOxoIrrVaQ8N0lbydIbUUS3erYdGi/lXIoR5ogHzkjCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f45d7695832672ce057f693db2d6e8027884da5ecf99105350eca293fdf7614c","last_reissued_at":"2026-07-05T10:06:57.076334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:57.076334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exact characterization of {\\epsilon}-Safe Decision Regions for exponential family distributions and Multi Cost SVM approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alberto Carlevaro, Fabrizio Dabbene, Maurizio Mongelli, Teodoro Alamo","submitted_at":"2025-01-29T16:14:35Z","abstract_excerpt":"Probabilistic guarantees on the prediction of data-driven classifiers are necessary to define models that can be considered reliable. This is a key requirement for modern machine learning in which the goodness of a system is measured in terms of trustworthiness, clearly dividing what is safe from what is unsafe. The spirit of this paper is exactly in this direction. First, we introduce a formal definition of {\\epsilon}-Safe Decision Region, a subset of the input space in which the prediction of a target (safe) class is probabilistically guaranteed. Second, we prove that, when data come from ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17731","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/2501.17731/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":"2501.17731","created_at":"2026-07-05T10:06:57.076395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.17731v1","created_at":"2026-07-05T10:06:57.076395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17731","created_at":"2026-07-05T10:06:57.076395+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ROXNFMDEZZM","created_at":"2026-07-05T10:06:57.076395+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ROXNFMDEZZM4BL7","created_at":"2026-07-05T10:06:57.076395+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ROXNFMD","created_at":"2026-07-05T10:06:57.076395+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/6ROXNFMDEZZM4BL7NE63FVXIAJ","json":"https://pith.science/pith/6ROXNFMDEZZM4BL7NE63FVXIAJ.json","graph_json":"https://pith.science/api/pith-number/6ROXNFMDEZZM4BL7NE63FVXIAJ/graph.json","events_json":"https://pith.science/api/pith-number/6ROXNFMDEZZM4BL7NE63FVXIAJ/events.json","paper":"https://pith.science/paper/6ROXNFMD"},"agent_actions":{"view_html":"https://pith.science/pith/6ROXNFMDEZZM4BL7NE63FVXIAJ","download_json":"https://pith.science/pith/6ROXNFMDEZZM4BL7NE63FVXIAJ.json","view_paper":"https://pith.science/paper/6ROXNFMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.17731&json=true","fetch_graph":"https://pith.science/api/pith-number/6ROXNFMDEZZM4BL7NE63FVXIAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6ROXNFMDEZZM4BL7NE63FVXIAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ROXNFMDEZZM4BL7NE63FVXIAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ROXNFMDEZZM4BL7NE63FVXIAJ/action/storage_attestation","attest_author":"https://pith.science/pith/6ROXNFMDEZZM4BL7NE63FVXIAJ/action/author_attestation","sign_citation":"https://pith.science/pith/6ROXNFMDEZZM4BL7NE63FVXIAJ/action/citation_signature","submit_replication":"https://pith.science/pith/6ROXNFMDEZZM4BL7NE63FVXIAJ/action/replication_record"}},"created_at":"2026-07-05T10:06:57.076395+00:00","updated_at":"2026-07-05T10:06:57.076395+00:00"}