{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HZAE4PJPLU76EYA6RTCGK5B3FR","short_pith_number":"pith:HZAE4PJP","schema_version":"1.0","canonical_sha256":"3e404e3d2f5d3fe2601e8cc465743b2c5721b7a7701d87d0981a851ffc88a0a0","source":{"kind":"arxiv","id":"1909.13719","version":2},"attestation_state":"computed","paper":{"title":"RandAugment: Practical automated data augmentation with a reduced search space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Barret Zoph, Ekin D. Cubuk, Jonathon Shlens, Quoc V. Le","submitted_at":"2019-09-30T14:05:14Z","abstract_excerpt":"Recent work has shown that data augmentation has the potential to significantly improve the generalization of deep learning models. Recently, automated augmentation strategies have led to state-of-the-art results in image classification and object detection. While these strategies were optimized for improving validation accuracy, they also led to state-of-the-art results in semi-supervised learning and improved robustness to common corruptions of images. An obstacle to a large-scale adoption of these methods is a separate search phase which increases the training complexity and may substantial"},"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":"1909.13719","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-30T14:05:14Z","cross_cats_sorted":[],"title_canon_sha256":"3a0b686cdf83d01680e244806547980ca886b2ef9b00503693b9d2a51ae11e77","abstract_canon_sha256":"0fd7beb1f5fca7f890732da4739f9bd86a45e7494950b1702d7ec5f8638ed208"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:10.666038Z","signature_b64":"43tu0+Fd87a+z6Ti+1dwIx6amU9jRzPsIJc7vdZo7F6YjcggbkGZc6laaCxPW0u4BL8D4q2KU5mWaVThphiWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e404e3d2f5d3fe2601e8cc465743b2c5721b7a7701d87d0981a851ffc88a0a0","last_reissued_at":"2026-07-05T00:19:10.665526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:10.665526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RandAugment: Practical automated data augmentation with a reduced search space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Barret Zoph, Ekin D. Cubuk, Jonathon Shlens, Quoc V. Le","submitted_at":"2019-09-30T14:05:14Z","abstract_excerpt":"Recent work has shown that data augmentation has the potential to significantly improve the generalization of deep learning models. Recently, automated augmentation strategies have led to state-of-the-art results in image classification and object detection. While these strategies were optimized for improving validation accuracy, they also led to state-of-the-art results in semi-supervised learning and improved robustness to common corruptions of images. An obstacle to a large-scale adoption of these methods is a separate search phase which increases the training complexity and may substantial"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.13719","kind":"arxiv","version":2},"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/1909.13719/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":"1909.13719","created_at":"2026-07-05T00:19:10.665583+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.13719v2","created_at":"2026-07-05T00:19:10.665583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.13719","created_at":"2026-07-05T00:19:10.665583+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZAE4PJPLU76","created_at":"2026-07-05T00:19:10.665583+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZAE4PJPLU76EYA6","created_at":"2026-07-05T00:19:10.665583+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZAE4PJP","created_at":"2026-07-05T00:19:10.665583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11870","citing_title":"Information theoretic underpinning of self-supervised learning by clustering","ref_index":171,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZAE4PJPLU76EYA6RTCGK5B3FR","json":"https://pith.science/pith/HZAE4PJPLU76EYA6RTCGK5B3FR.json","graph_json":"https://pith.science/api/pith-number/HZAE4PJPLU76EYA6RTCGK5B3FR/graph.json","events_json":"https://pith.science/api/pith-number/HZAE4PJPLU76EYA6RTCGK5B3FR/events.json","paper":"https://pith.science/paper/HZAE4PJP"},"agent_actions":{"view_html":"https://pith.science/pith/HZAE4PJPLU76EYA6RTCGK5B3FR","download_json":"https://pith.science/pith/HZAE4PJPLU76EYA6RTCGK5B3FR.json","view_paper":"https://pith.science/paper/HZAE4PJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.13719&json=true","fetch_graph":"https://pith.science/api/pith-number/HZAE4PJPLU76EYA6RTCGK5B3FR/graph.json","fetch_events":"https://pith.science/api/pith-number/HZAE4PJPLU76EYA6RTCGK5B3FR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZAE4PJPLU76EYA6RTCGK5B3FR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZAE4PJPLU76EYA6RTCGK5B3FR/action/storage_attestation","attest_author":"https://pith.science/pith/HZAE4PJPLU76EYA6RTCGK5B3FR/action/author_attestation","sign_citation":"https://pith.science/pith/HZAE4PJPLU76EYA6RTCGK5B3FR/action/citation_signature","submit_replication":"https://pith.science/pith/HZAE4PJPLU76EYA6RTCGK5B3FR/action/replication_record"}},"created_at":"2026-07-05T00:19:10.665583+00:00","updated_at":"2026-07-05T00:19:10.665583+00:00"}