{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SK7PHI2XFJEHLEWZVHEQBJFPUJ","short_pith_number":"pith:SK7PHI2X","schema_version":"1.0","canonical_sha256":"92bef3a3572a487592d9a9c900a4afa2712be563e4b7f9cca02194442a6749e6","source":{"kind":"arxiv","id":"2411.05939","version":1},"attestation_state":"computed","paper":{"title":"GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Kyungim Baek, Moseli Mots'oehli","submitted_at":"2024-11-08T19:59:40Z","abstract_excerpt":"Active learning aims to train accurate classifiers while minimizing labeling costs by strategically selecting informative samples for annotation. This study focuses on image classification tasks, comparing AL methods on CIFAR10, CIFAR100, Food101, and the Chest X-ray datasets under varying label noise rates. We investigate the impact of model architecture by comparing Convolutional Neural Networks (CNNs) and Vision Transformer (ViT)-based models. Additionally, we propose a novel deep active learning algorithm, GCI-ViTAL, designed to be robust to label noise. GCI-ViTAL utilizes prediction entro"},"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":"2411.05939","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T19:59:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ca0e17d1790a214d71820610b206dc1a62b54458dba662ed1838e2b1598073ff","abstract_canon_sha256":"375d5aa2ec15fe695fead53deed66a0e85c501010173ad238cee70cd3c142c24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:13.699104Z","signature_b64":"4vnGYtQu7snljt+MfQf3Ky71qhqMPoj1QL4eCoJVmzyPXZ17P64TT8ULSmkXvsiCM568Os0xU2s+TqL3T2vsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92bef3a3572a487592d9a9c900a4afa2712be563e4b7f9cca02194442a6749e6","last_reissued_at":"2026-07-05T09:33:13.698618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:13.698618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Kyungim Baek, Moseli Mots'oehli","submitted_at":"2024-11-08T19:59:40Z","abstract_excerpt":"Active learning aims to train accurate classifiers while minimizing labeling costs by strategically selecting informative samples for annotation. This study focuses on image classification tasks, comparing AL methods on CIFAR10, CIFAR100, Food101, and the Chest X-ray datasets under varying label noise rates. We investigate the impact of model architecture by comparing Convolutional Neural Networks (CNNs) and Vision Transformer (ViT)-based models. Additionally, we propose a novel deep active learning algorithm, GCI-ViTAL, designed to be robust to label noise. GCI-ViTAL utilizes prediction entro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05939","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/2411.05939/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":"2411.05939","created_at":"2026-07-05T09:33:13.698676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05939v1","created_at":"2026-07-05T09:33:13.698676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05939","created_at":"2026-07-05T09:33:13.698676+00:00"},{"alias_kind":"pith_short_12","alias_value":"SK7PHI2XFJEH","created_at":"2026-07-05T09:33:13.698676+00:00"},{"alias_kind":"pith_short_16","alias_value":"SK7PHI2XFJEHLEWZ","created_at":"2026-07-05T09:33:13.698676+00:00"},{"alias_kind":"pith_short_8","alias_value":"SK7PHI2X","created_at":"2026-07-05T09:33:13.698676+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.04375","citing_title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SK7PHI2XFJEHLEWZVHEQBJFPUJ","json":"https://pith.science/pith/SK7PHI2XFJEHLEWZVHEQBJFPUJ.json","graph_json":"https://pith.science/api/pith-number/SK7PHI2XFJEHLEWZVHEQBJFPUJ/graph.json","events_json":"https://pith.science/api/pith-number/SK7PHI2XFJEHLEWZVHEQBJFPUJ/events.json","paper":"https://pith.science/paper/SK7PHI2X"},"agent_actions":{"view_html":"https://pith.science/pith/SK7PHI2XFJEHLEWZVHEQBJFPUJ","download_json":"https://pith.science/pith/SK7PHI2XFJEHLEWZVHEQBJFPUJ.json","view_paper":"https://pith.science/paper/SK7PHI2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05939&json=true","fetch_graph":"https://pith.science/api/pith-number/SK7PHI2XFJEHLEWZVHEQBJFPUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/SK7PHI2XFJEHLEWZVHEQBJFPUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SK7PHI2XFJEHLEWZVHEQBJFPUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SK7PHI2XFJEHLEWZVHEQBJFPUJ/action/storage_attestation","attest_author":"https://pith.science/pith/SK7PHI2XFJEHLEWZVHEQBJFPUJ/action/author_attestation","sign_citation":"https://pith.science/pith/SK7PHI2XFJEHLEWZVHEQBJFPUJ/action/citation_signature","submit_replication":"https://pith.science/pith/SK7PHI2XFJEHLEWZVHEQBJFPUJ/action/replication_record"}},"created_at":"2026-07-05T09:33:13.698676+00:00","updated_at":"2026-07-05T09:33:13.698676+00:00"}