{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7FIGEFLA44K26BJ3DYG3QK7X5Y","short_pith_number":"pith:7FIGEFLA","schema_version":"1.0","canonical_sha256":"f950621560e715af053b1e0db82bf7ee1488ad06d1291ccf8c8d4ef74bc77620","source":{"kind":"arxiv","id":"2003.03780","version":3},"attestation_state":"computed","paper":{"title":"DADA: Differentiable Automatic Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Guosheng Hu, Neil M. Robertson, Timothy Hospedales, Yonggang Li, Yongtao Wang, Yongxin Yang","submitted_at":"2020-03-08T13:23:14Z","abstract_excerpt":"Data augmentation (DA) techniques aim to increase data variability, and thus train deep networks with better generalisation. The pioneering AutoAugment automated the search for optimal DA policies with reinforcement learning. However, AutoAugment is extremely computationally expensive, limiting its wide applicability. Followup works such as Population Based Augmentation (PBA) and Fast AutoAugment improved efficiency, but their optimization speed remains a bottleneck. In this paper, we propose Differentiable Automatic Data Augmentation (DADA) which dramatically reduces the cost. DADA relaxes th"},"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":"2003.03780","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-08T13:23:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f3ec1cd41d4407741f4d91b61a4f7f1bd9599e32c5dbc2070b02efee7601d02f","abstract_canon_sha256":"6d862b2e2ba56c64e7e89f9c8eaa69bd243876b391757109c2016d1cecd5d676"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:24.138328Z","signature_b64":"WNjM1Q5HnI0pvG3fV3/IQZ8ST/GObAqUa9EqA6a8ErkKFcKoil/3ebFOGhHdX5aYjf62eR9XWqUIsBIB2FAcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f950621560e715af053b1e0db82bf7ee1488ad06d1291ccf8c8d4ef74bc77620","last_reissued_at":"2026-07-05T01:23:24.137720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:24.137720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DADA: Differentiable Automatic Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Guosheng Hu, Neil M. Robertson, Timothy Hospedales, Yonggang Li, Yongtao Wang, Yongxin Yang","submitted_at":"2020-03-08T13:23:14Z","abstract_excerpt":"Data augmentation (DA) techniques aim to increase data variability, and thus train deep networks with better generalisation. The pioneering AutoAugment automated the search for optimal DA policies with reinforcement learning. However, AutoAugment is extremely computationally expensive, limiting its wide applicability. Followup works such as Population Based Augmentation (PBA) and Fast AutoAugment improved efficiency, but their optimization speed remains a bottleneck. In this paper, we propose Differentiable Automatic Data Augmentation (DADA) which dramatically reduces the cost. DADA relaxes th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03780","kind":"arxiv","version":3},"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/2003.03780/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":"2003.03780","created_at":"2026-07-05T01:23:24.137854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.03780v3","created_at":"2026-07-05T01:23:24.137854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03780","created_at":"2026-07-05T01:23:24.137854+00:00"},{"alias_kind":"pith_short_12","alias_value":"7FIGEFLA44K2","created_at":"2026-07-05T01:23:24.137854+00:00"},{"alias_kind":"pith_short_16","alias_value":"7FIGEFLA44K26BJ3","created_at":"2026-07-05T01:23:24.137854+00:00"},{"alias_kind":"pith_short_8","alias_value":"7FIGEFLA","created_at":"2026-07-05T01:23:24.137854+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/7FIGEFLA44K26BJ3DYG3QK7X5Y","json":"https://pith.science/pith/7FIGEFLA44K26BJ3DYG3QK7X5Y.json","graph_json":"https://pith.science/api/pith-number/7FIGEFLA44K26BJ3DYG3QK7X5Y/graph.json","events_json":"https://pith.science/api/pith-number/7FIGEFLA44K26BJ3DYG3QK7X5Y/events.json","paper":"https://pith.science/paper/7FIGEFLA"},"agent_actions":{"view_html":"https://pith.science/pith/7FIGEFLA44K26BJ3DYG3QK7X5Y","download_json":"https://pith.science/pith/7FIGEFLA44K26BJ3DYG3QK7X5Y.json","view_paper":"https://pith.science/paper/7FIGEFLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.03780&json=true","fetch_graph":"https://pith.science/api/pith-number/7FIGEFLA44K26BJ3DYG3QK7X5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/7FIGEFLA44K26BJ3DYG3QK7X5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7FIGEFLA44K26BJ3DYG3QK7X5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7FIGEFLA44K26BJ3DYG3QK7X5Y/action/storage_attestation","attest_author":"https://pith.science/pith/7FIGEFLA44K26BJ3DYG3QK7X5Y/action/author_attestation","sign_citation":"https://pith.science/pith/7FIGEFLA44K26BJ3DYG3QK7X5Y/action/citation_signature","submit_replication":"https://pith.science/pith/7FIGEFLA44K26BJ3DYG3QK7X5Y/action/replication_record"}},"created_at":"2026-07-05T01:23:24.137854+00:00","updated_at":"2026-07-05T01:23:24.137854+00:00"}