{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QSK6PT62WCDWVGLES7LVNDHBDB","short_pith_number":"pith:QSK6PT62","schema_version":"1.0","canonical_sha256":"8495e7cfdab0876a996497d7568ce11859ca429167aa74720526da2052e8c282","source":{"kind":"arxiv","id":"2308.11990","version":1},"attestation_state":"computed","paper":{"title":"RankMixup: Ranking-Based Mixup Training for Network Calibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bumsub Ham, Hyekang Park, Jongyoun Noh, Junghyup Lee","submitted_at":"2023-08-23T08:25:30Z","abstract_excerpt":"Network calibration aims to accurately estimate the level of confidences, which is particularly important for employing deep neural networks in real-world systems. Recent approaches leverage mixup to calibrate the network's predictions during training. However, they do not consider the problem that mixtures of labels in mixup may not accurately represent the actual distribution of augmented samples. In this paper, we present RankMixup, a novel mixup-based framework alleviating the problem of the mixture of labels for network calibration. To this end, we propose to use an ordinal ranking relati"},"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":"2308.11990","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T08:25:30Z","cross_cats_sorted":[],"title_canon_sha256":"ee1d5f9bb7d4359b76a5975558dc0b32bb51463cf32bc280f6f8e029e43986d1","abstract_canon_sha256":"3c4fcc7e1a7c08c601bcc18b460f5833f2c9141c8ece7350573b608de747448f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:57.813713Z","signature_b64":"SGJwPW6C/xJUiFVlP2vJ4bd7EiuXx1FlqI2zKBYfU1Q9gY5F8HfUMB5b9zAsNWt5/H5Wv/ghyHh1t4zsiq7BBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8495e7cfdab0876a996497d7568ce11859ca429167aa74720526da2052e8c282","last_reissued_at":"2026-07-05T06:43:57.813280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:57.813280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RankMixup: Ranking-Based Mixup Training for Network Calibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bumsub Ham, Hyekang Park, Jongyoun Noh, Junghyup Lee","submitted_at":"2023-08-23T08:25:30Z","abstract_excerpt":"Network calibration aims to accurately estimate the level of confidences, which is particularly important for employing deep neural networks in real-world systems. Recent approaches leverage mixup to calibrate the network's predictions during training. However, they do not consider the problem that mixtures of labels in mixup may not accurately represent the actual distribution of augmented samples. In this paper, we present RankMixup, a novel mixup-based framework alleviating the problem of the mixture of labels for network calibration. To this end, we propose to use an ordinal ranking relati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11990","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/2308.11990/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":"2308.11990","created_at":"2026-07-05T06:43:57.813341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.11990v1","created_at":"2026-07-05T06:43:57.813341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11990","created_at":"2026-07-05T06:43:57.813341+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSK6PT62WCDW","created_at":"2026-07-05T06:43:57.813341+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSK6PT62WCDWVGLE","created_at":"2026-07-05T06:43:57.813341+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSK6PT62","created_at":"2026-07-05T06:43:57.813341+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/QSK6PT62WCDWVGLES7LVNDHBDB","json":"https://pith.science/pith/QSK6PT62WCDWVGLES7LVNDHBDB.json","graph_json":"https://pith.science/api/pith-number/QSK6PT62WCDWVGLES7LVNDHBDB/graph.json","events_json":"https://pith.science/api/pith-number/QSK6PT62WCDWVGLES7LVNDHBDB/events.json","paper":"https://pith.science/paper/QSK6PT62"},"agent_actions":{"view_html":"https://pith.science/pith/QSK6PT62WCDWVGLES7LVNDHBDB","download_json":"https://pith.science/pith/QSK6PT62WCDWVGLES7LVNDHBDB.json","view_paper":"https://pith.science/paper/QSK6PT62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.11990&json=true","fetch_graph":"https://pith.science/api/pith-number/QSK6PT62WCDWVGLES7LVNDHBDB/graph.json","fetch_events":"https://pith.science/api/pith-number/QSK6PT62WCDWVGLES7LVNDHBDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSK6PT62WCDWVGLES7LVNDHBDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSK6PT62WCDWVGLES7LVNDHBDB/action/storage_attestation","attest_author":"https://pith.science/pith/QSK6PT62WCDWVGLES7LVNDHBDB/action/author_attestation","sign_citation":"https://pith.science/pith/QSK6PT62WCDWVGLES7LVNDHBDB/action/citation_signature","submit_replication":"https://pith.science/pith/QSK6PT62WCDWVGLES7LVNDHBDB/action/replication_record"}},"created_at":"2026-07-05T06:43:57.813341+00:00","updated_at":"2026-07-05T06:43:57.813341+00:00"}