{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BAKPWKLXR3ON5IBXEDU2FRWXJL","short_pith_number":"pith:BAKPWKLX","schema_version":"1.0","canonical_sha256":"0814fb29778edcdea03720e9a2c6d74aea806f2c8fbb7e270e3c5906f48e8146","source":{"kind":"arxiv","id":"2405.11533","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Selective Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ido Galil, Ran El-Yaniv, Shani Goren","submitted_at":"2024-05-19T12:24:30Z","abstract_excerpt":"Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces hierarchical selective classification, extending selective classification to a hierarchical setting. Our approach leverages the inherent structure of class relationships, enabling models to reduce the specificity of their predictions when faced with uncertainty. In this paper, we first formalize hierarchical risk and coverage, and introduce hierarchical risk-coverage curves. Next, we develop algorithms for hierarchical selective classification (which we refer to as \"i"},"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":"2405.11533","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T12:24:30Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ca867d533f25b43d4010da9bcd39f1be972b692f9b5ae01d63cedf4ae790647c","abstract_canon_sha256":"b16d27af12bf02597f2ad4fea70b8cbc5c3ef7088e49a6ab3027c95b8eefa3ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:51.540169Z","signature_b64":"pPKvrkK6Lp+5u6Ws+XSo/YsjGtzxcjTKfqBvgedG03/6jeElcouKRxzGSJLVZ+PWlBmZ01YpBhWj483dITU/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0814fb29778edcdea03720e9a2c6d74aea806f2c8fbb7e270e3c5906f48e8146","last_reissued_at":"2026-07-05T09:56:51.539632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:51.539632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Selective Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ido Galil, Ran El-Yaniv, Shani Goren","submitted_at":"2024-05-19T12:24:30Z","abstract_excerpt":"Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces hierarchical selective classification, extending selective classification to a hierarchical setting. Our approach leverages the inherent structure of class relationships, enabling models to reduce the specificity of their predictions when faced with uncertainty. In this paper, we first formalize hierarchical risk and coverage, and introduce hierarchical risk-coverage curves. Next, we develop algorithms for hierarchical selective classification (which we refer to as \"i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11533","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/2405.11533/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":"2405.11533","created_at":"2026-07-05T09:56:51.539704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11533v2","created_at":"2026-07-05T09:56:51.539704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11533","created_at":"2026-07-05T09:56:51.539704+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAKPWKLXR3ON","created_at":"2026-07-05T09:56:51.539704+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAKPWKLXR3ON5IBX","created_at":"2026-07-05T09:56:51.539704+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAKPWKLX","created_at":"2026-07-05T09:56:51.539704+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.14067","citing_title":"Online Conformal Abstention for Factuality Control Under Adversarial Bandit Feedback","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAKPWKLXR3ON5IBXEDU2FRWXJL","json":"https://pith.science/pith/BAKPWKLXR3ON5IBXEDU2FRWXJL.json","graph_json":"https://pith.science/api/pith-number/BAKPWKLXR3ON5IBXEDU2FRWXJL/graph.json","events_json":"https://pith.science/api/pith-number/BAKPWKLXR3ON5IBXEDU2FRWXJL/events.json","paper":"https://pith.science/paper/BAKPWKLX"},"agent_actions":{"view_html":"https://pith.science/pith/BAKPWKLXR3ON5IBXEDU2FRWXJL","download_json":"https://pith.science/pith/BAKPWKLXR3ON5IBXEDU2FRWXJL.json","view_paper":"https://pith.science/paper/BAKPWKLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11533&json=true","fetch_graph":"https://pith.science/api/pith-number/BAKPWKLXR3ON5IBXEDU2FRWXJL/graph.json","fetch_events":"https://pith.science/api/pith-number/BAKPWKLXR3ON5IBXEDU2FRWXJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAKPWKLXR3ON5IBXEDU2FRWXJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAKPWKLXR3ON5IBXEDU2FRWXJL/action/storage_attestation","attest_author":"https://pith.science/pith/BAKPWKLXR3ON5IBXEDU2FRWXJL/action/author_attestation","sign_citation":"https://pith.science/pith/BAKPWKLXR3ON5IBXEDU2FRWXJL/action/citation_signature","submit_replication":"https://pith.science/pith/BAKPWKLXR3ON5IBXEDU2FRWXJL/action/replication_record"}},"created_at":"2026-07-05T09:56:51.539704+00:00","updated_at":"2026-07-05T09:56:51.539704+00:00"}