{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FQUECXHSENS4OJSFOIJ3YN2QUW","short_pith_number":"pith:FQUECXHS","schema_version":"1.0","canonical_sha256":"2c28415cf22365c726457213bc3750a5af8f0a41b856c0d265f701695ea30874","source":{"kind":"arxiv","id":"2501.01130","version":1},"attestation_state":"computed","paper":{"title":"An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against Label Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hengyu Liu, Jingyi Cui, Yi-Ge Zhang, Yisen Wang","submitted_at":"2025-01-02T08:12:23Z","abstract_excerpt":"Learning from noisy labels is a critical challenge in machine learning, with vast implications for numerous real-world scenarios. While supervised contrastive learning has recently emerged as a powerful tool for navigating label noise, many existing solutions remain heuristic, often devoid of a systematic theoretical foundation for crafting robust supervised contrastive losses. To address the gap, in this paper, we propose a unified theoretical framework for robust losses under the pairwise contrastive paradigm. In particular, we for the first time derive a general robust condition for arbitra"},"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":"2501.01130","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-02T08:12:23Z","cross_cats_sorted":[],"title_canon_sha256":"1d39fcbd43bc9d7940d697740393f29914bc8b060d067e4f582f1ea7d7ba1168","abstract_canon_sha256":"864127e3c0af776badfb1804413f40492f05aba5068804fa578cdf5d5da68d67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:15.265619Z","signature_b64":"tB0+5HRu43CGjAw76/43v/oQVJmF0L7Xm5WKuhnW88bWn/tbysdxnb2ZdL2Y4Sv2TrTEwAng+29HCYXpjL0YBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c28415cf22365c726457213bc3750a5af8f0a41b856c0d265f701695ea30874","last_reissued_at":"2026-07-05T09:56:15.265128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:15.265128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against Label Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hengyu Liu, Jingyi Cui, Yi-Ge Zhang, Yisen Wang","submitted_at":"2025-01-02T08:12:23Z","abstract_excerpt":"Learning from noisy labels is a critical challenge in machine learning, with vast implications for numerous real-world scenarios. While supervised contrastive learning has recently emerged as a powerful tool for navigating label noise, many existing solutions remain heuristic, often devoid of a systematic theoretical foundation for crafting robust supervised contrastive losses. To address the gap, in this paper, we propose a unified theoretical framework for robust losses under the pairwise contrastive paradigm. In particular, we for the first time derive a general robust condition for arbitra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01130","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/2501.01130/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":"2501.01130","created_at":"2026-07-05T09:56:15.265187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01130v1","created_at":"2026-07-05T09:56:15.265187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01130","created_at":"2026-07-05T09:56:15.265187+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQUECXHSENS4","created_at":"2026-07-05T09:56:15.265187+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQUECXHSENS4OJSF","created_at":"2026-07-05T09:56:15.265187+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQUECXHS","created_at":"2026-07-05T09:56:15.265187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07596","citing_title":"A Refined Generalization Analysis for Extreme Multi-class Supervised Contrastive Representation Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07596","citing_title":"A Refined Generalization Analysis for Extreme Multi-class Supervised Contrastive Representation Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07596","citing_title":"A Refined Generalization Analysis for Extreme Multi-class Supervised Contrastive Representation Learning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQUECXHSENS4OJSFOIJ3YN2QUW","json":"https://pith.science/pith/FQUECXHSENS4OJSFOIJ3YN2QUW.json","graph_json":"https://pith.science/api/pith-number/FQUECXHSENS4OJSFOIJ3YN2QUW/graph.json","events_json":"https://pith.science/api/pith-number/FQUECXHSENS4OJSFOIJ3YN2QUW/events.json","paper":"https://pith.science/paper/FQUECXHS"},"agent_actions":{"view_html":"https://pith.science/pith/FQUECXHSENS4OJSFOIJ3YN2QUW","download_json":"https://pith.science/pith/FQUECXHSENS4OJSFOIJ3YN2QUW.json","view_paper":"https://pith.science/paper/FQUECXHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01130&json=true","fetch_graph":"https://pith.science/api/pith-number/FQUECXHSENS4OJSFOIJ3YN2QUW/graph.json","fetch_events":"https://pith.science/api/pith-number/FQUECXHSENS4OJSFOIJ3YN2QUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQUECXHSENS4OJSFOIJ3YN2QUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQUECXHSENS4OJSFOIJ3YN2QUW/action/storage_attestation","attest_author":"https://pith.science/pith/FQUECXHSENS4OJSFOIJ3YN2QUW/action/author_attestation","sign_citation":"https://pith.science/pith/FQUECXHSENS4OJSFOIJ3YN2QUW/action/citation_signature","submit_replication":"https://pith.science/pith/FQUECXHSENS4OJSFOIJ3YN2QUW/action/replication_record"}},"created_at":"2026-07-05T09:56:15.265187+00:00","updated_at":"2026-07-05T09:56:15.265187+00:00"}