{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ME2NW3RE3WTR6MRGEQHJ4P33S5","short_pith_number":"pith:ME2NW3RE","schema_version":"1.0","canonical_sha256":"6134db6e24dda71f3226240e9e3f7b9745d834a58e112a200a3f24af3325b359","source":{"kind":"arxiv","id":"2505.04375","version":1},"attestation_state":"computed","paper":{"title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hope Mogale, Kyungim Baek, Moseli Mots'oehli","submitted_at":"2025-05-07T12:53:13Z","abstract_excerpt":"Fine-tuning pre-trained convolutional neural networks on ImageNet for downstream tasks is well-established. Still, the impact of model size on the performance of vision transformers in similar scenarios, particularly under label noise, remains largely unexplored. Given the utility and versatility of transformer architectures, this study investigates their practicality under low-budget constraints and noisy labels. We explore how classification accuracy and calibration are affected by symmetric label noise in active learning settings, evaluating four vision transformer configurations (Base and "},"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":"2505.04375","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T12:53:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"19e4afafbf55a5ba12da5709ae56c63750e36f53e4f68404a538be7f8cc17a0a","abstract_canon_sha256":"acbc870bdbe419f1d0be61913618e0ce1a7bb70e3ca8e29c05a192b651b5b2e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:50.992561Z","signature_b64":"vwhSI9n+E2TXBL4g51OqUgjirva9Lfw97LE+JajAJjPBVhw3kGS27reRk3uleZhm0Qmwg98rlOoOVd6hz1eGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6134db6e24dda71f3226240e9e3f7b9745d834a58e112a200a3f24af3325b359","last_reissued_at":"2026-07-05T10:59:50.992050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:50.992050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hope Mogale, Kyungim Baek, Moseli Mots'oehli","submitted_at":"2025-05-07T12:53:13Z","abstract_excerpt":"Fine-tuning pre-trained convolutional neural networks on ImageNet for downstream tasks is well-established. Still, the impact of model size on the performance of vision transformers in similar scenarios, particularly under label noise, remains largely unexplored. Given the utility and versatility of transformer architectures, this study investigates their practicality under low-budget constraints and noisy labels. We explore how classification accuracy and calibration are affected by symmetric label noise in active learning settings, evaluating four vision transformer configurations (Base and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04375","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/2505.04375/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":"2505.04375","created_at":"2026-07-05T10:59:50.992115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04375v1","created_at":"2026-07-05T10:59:50.992115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04375","created_at":"2026-07-05T10:59:50.992115+00:00"},{"alias_kind":"pith_short_12","alias_value":"ME2NW3RE3WTR","created_at":"2026-07-05T10:59:50.992115+00:00"},{"alias_kind":"pith_short_16","alias_value":"ME2NW3RE3WTR6MRG","created_at":"2026-07-05T10:59:50.992115+00:00"},{"alias_kind":"pith_short_8","alias_value":"ME2NW3RE","created_at":"2026-07-05T10:59:50.992115+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/ME2NW3RE3WTR6MRGEQHJ4P33S5","json":"https://pith.science/pith/ME2NW3RE3WTR6MRGEQHJ4P33S5.json","graph_json":"https://pith.science/api/pith-number/ME2NW3RE3WTR6MRGEQHJ4P33S5/graph.json","events_json":"https://pith.science/api/pith-number/ME2NW3RE3WTR6MRGEQHJ4P33S5/events.json","paper":"https://pith.science/paper/ME2NW3RE"},"agent_actions":{"view_html":"https://pith.science/pith/ME2NW3RE3WTR6MRGEQHJ4P33S5","download_json":"https://pith.science/pith/ME2NW3RE3WTR6MRGEQHJ4P33S5.json","view_paper":"https://pith.science/paper/ME2NW3RE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04375&json=true","fetch_graph":"https://pith.science/api/pith-number/ME2NW3RE3WTR6MRGEQHJ4P33S5/graph.json","fetch_events":"https://pith.science/api/pith-number/ME2NW3RE3WTR6MRGEQHJ4P33S5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ME2NW3RE3WTR6MRGEQHJ4P33S5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ME2NW3RE3WTR6MRGEQHJ4P33S5/action/storage_attestation","attest_author":"https://pith.science/pith/ME2NW3RE3WTR6MRGEQHJ4P33S5/action/author_attestation","sign_citation":"https://pith.science/pith/ME2NW3RE3WTR6MRGEQHJ4P33S5/action/citation_signature","submit_replication":"https://pith.science/pith/ME2NW3RE3WTR6MRGEQHJ4P33S5/action/replication_record"}},"created_at":"2026-07-05T10:59:50.992115+00:00","updated_at":"2026-07-05T10:59:50.992115+00:00"}