{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BTDA6ZYVWJJ66IRPYRJ3GDBH3Z","short_pith_number":"pith:BTDA6ZYV","schema_version":"1.0","canonical_sha256":"0cc60f6715b253ef222fc453b30c27de6510d015975742091fb3ab61268674c5","source":{"kind":"arxiv","id":"2304.10310","version":1},"attestation_state":"computed","paper":{"title":"LA3: Efficient Label-Aware AutoAugment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Di Niu, Mingjun Zhao, Shan Lu, Xiaoli Wang, Zixuan Wang","submitted_at":"2023-04-20T13:42:18Z","abstract_excerpt":"Automated augmentation is an emerging and effective technique to search for data augmentation policies to improve generalizability of deep neural network training. Most existing work focuses on constructing a unified policy applicable to all data samples in a given dataset, without considering sample or class variations. In this paper, we propose a novel two-stage data augmentation algorithm, named Label-Aware AutoAugment (LA3), which takes advantage of the label information, and learns augmentation policies separately for samples of different labels. LA3 consists of two learning stages, where"},"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":"2304.10310","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-20T13:42:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f1ff6e24eceaa658c771c0068c3e4e973fbac15435873d18ed6607ac47f2db54","abstract_canon_sha256":"fa086c69296db57376376a8fa0f635aa138435658d0eeca458e5ba728601204f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:56.701674Z","signature_b64":"RLjB1983QPvuqFvFPfmvlTgdDuCuCgX72cY/I+5vykjkBv/ysAWDWnjluDih/UsM3y5WZ4hnaAruwXSD826cDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cc60f6715b253ef222fc453b30c27de6510d015975742091fb3ab61268674c5","last_reissued_at":"2026-07-05T06:02:56.701250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:56.701250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LA3: Efficient Label-Aware AutoAugment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Di Niu, Mingjun Zhao, Shan Lu, Xiaoli Wang, Zixuan Wang","submitted_at":"2023-04-20T13:42:18Z","abstract_excerpt":"Automated augmentation is an emerging and effective technique to search for data augmentation policies to improve generalizability of deep neural network training. Most existing work focuses on constructing a unified policy applicable to all data samples in a given dataset, without considering sample or class variations. In this paper, we propose a novel two-stage data augmentation algorithm, named Label-Aware AutoAugment (LA3), which takes advantage of the label information, and learns augmentation policies separately for samples of different labels. LA3 consists of two learning stages, where"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10310","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/2304.10310/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":"2304.10310","created_at":"2026-07-05T06:02:56.701307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.10310v1","created_at":"2026-07-05T06:02:56.701307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10310","created_at":"2026-07-05T06:02:56.701307+00:00"},{"alias_kind":"pith_short_12","alias_value":"BTDA6ZYVWJJ6","created_at":"2026-07-05T06:02:56.701307+00:00"},{"alias_kind":"pith_short_16","alias_value":"BTDA6ZYVWJJ66IRP","created_at":"2026-07-05T06:02:56.701307+00:00"},{"alias_kind":"pith_short_8","alias_value":"BTDA6ZYV","created_at":"2026-07-05T06:02:56.701307+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/BTDA6ZYVWJJ66IRPYRJ3GDBH3Z","json":"https://pith.science/pith/BTDA6ZYVWJJ66IRPYRJ3GDBH3Z.json","graph_json":"https://pith.science/api/pith-number/BTDA6ZYVWJJ66IRPYRJ3GDBH3Z/graph.json","events_json":"https://pith.science/api/pith-number/BTDA6ZYVWJJ66IRPYRJ3GDBH3Z/events.json","paper":"https://pith.science/paper/BTDA6ZYV"},"agent_actions":{"view_html":"https://pith.science/pith/BTDA6ZYVWJJ66IRPYRJ3GDBH3Z","download_json":"https://pith.science/pith/BTDA6ZYVWJJ66IRPYRJ3GDBH3Z.json","view_paper":"https://pith.science/paper/BTDA6ZYV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.10310&json=true","fetch_graph":"https://pith.science/api/pith-number/BTDA6ZYVWJJ66IRPYRJ3GDBH3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/BTDA6ZYVWJJ66IRPYRJ3GDBH3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BTDA6ZYVWJJ66IRPYRJ3GDBH3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BTDA6ZYVWJJ66IRPYRJ3GDBH3Z/action/storage_attestation","attest_author":"https://pith.science/pith/BTDA6ZYVWJJ66IRPYRJ3GDBH3Z/action/author_attestation","sign_citation":"https://pith.science/pith/BTDA6ZYVWJJ66IRPYRJ3GDBH3Z/action/citation_signature","submit_replication":"https://pith.science/pith/BTDA6ZYVWJJ66IRPYRJ3GDBH3Z/action/replication_record"}},"created_at":"2026-07-05T06:02:56.701307+00:00","updated_at":"2026-07-05T06:02:56.701307+00:00"}