{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P6LAEH5NIDG227L66UYPZIZGDL","short_pith_number":"pith:P6LAEH5N","schema_version":"1.0","canonical_sha256":"7f96021fad40cdad7d7ef530fca3261aeba3b2f3d16e14d61822761b5983c4df","source":{"kind":"arxiv","id":"2406.04745","version":1},"attestation_state":"computed","paper":{"title":"Confidence-aware Contrastive Learning for Selective Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chao Qian, Haopu Shang, Shen-Huan Lyu, Xiangyu Wang, Yu-Chang Wu","submitted_at":"2024-06-07T08:43:53Z","abstract_excerpt":"Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks and focus on modifying the architecture of classification layers to enable the model to estimate the confidence of its prediction. This work provides a generalization bound for selective classification, disclosing that optimizing feature layers helps improve the performance of selective classification. Inspired by this theory, we propose to explicitly improve"},"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":"2406.04745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-07T08:43:53Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b63a844f76051be5bbd011f1490e8f667a155d41e8103218d9cf95c076446229","abstract_canon_sha256":"c0ebbfcceb882e4601bfe2ee8ec4bcb4d2083e104e40084072617f1f19bf45cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:48.885711Z","signature_b64":"bOVtEEMMkewaZ31dE2TL4roeAVlCVHizlXo+w1iLeQfGPgY8RWqILL+BIxoL6QSYynE1xfPbr0pcoQI9XXIkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f96021fad40cdad7d7ef530fca3261aeba3b2f3d16e14d61822761b5983c4df","last_reissued_at":"2026-07-05T08:28:48.885256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:48.885256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence-aware Contrastive Learning for Selective Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chao Qian, Haopu Shang, Shen-Huan Lyu, Xiangyu Wang, Yu-Chang Wu","submitted_at":"2024-06-07T08:43:53Z","abstract_excerpt":"Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks and focus on modifying the architecture of classification layers to enable the model to estimate the confidence of its prediction. This work provides a generalization bound for selective classification, disclosing that optimizing feature layers helps improve the performance of selective classification. Inspired by this theory, we propose to explicitly improve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04745","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/2406.04745/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":"2406.04745","created_at":"2026-07-05T08:28:48.885327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04745v1","created_at":"2026-07-05T08:28:48.885327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04745","created_at":"2026-07-05T08:28:48.885327+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6LAEH5NIDG2","created_at":"2026-07-05T08:28:48.885327+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6LAEH5NIDG227L6","created_at":"2026-07-05T08:28:48.885327+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6LAEH5N","created_at":"2026-07-05T08:28:48.885327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07556","citing_title":"Uncertainty-Driven Reliability: Selective Prediction and Trustworthy Deployment in Modern Machine Learning","ref_index":170,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6LAEH5NIDG227L66UYPZIZGDL","json":"https://pith.science/pith/P6LAEH5NIDG227L66UYPZIZGDL.json","graph_json":"https://pith.science/api/pith-number/P6LAEH5NIDG227L66UYPZIZGDL/graph.json","events_json":"https://pith.science/api/pith-number/P6LAEH5NIDG227L66UYPZIZGDL/events.json","paper":"https://pith.science/paper/P6LAEH5N"},"agent_actions":{"view_html":"https://pith.science/pith/P6LAEH5NIDG227L66UYPZIZGDL","download_json":"https://pith.science/pith/P6LAEH5NIDG227L66UYPZIZGDL.json","view_paper":"https://pith.science/paper/P6LAEH5N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04745&json=true","fetch_graph":"https://pith.science/api/pith-number/P6LAEH5NIDG227L66UYPZIZGDL/graph.json","fetch_events":"https://pith.science/api/pith-number/P6LAEH5NIDG227L66UYPZIZGDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6LAEH5NIDG227L66UYPZIZGDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6LAEH5NIDG227L66UYPZIZGDL/action/storage_attestation","attest_author":"https://pith.science/pith/P6LAEH5NIDG227L66UYPZIZGDL/action/author_attestation","sign_citation":"https://pith.science/pith/P6LAEH5NIDG227L66UYPZIZGDL/action/citation_signature","submit_replication":"https://pith.science/pith/P6LAEH5NIDG227L66UYPZIZGDL/action/replication_record"}},"created_at":"2026-07-05T08:28:48.885327+00:00","updated_at":"2026-07-05T08:28:48.885327+00:00"}