{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QTWHSW66C5KOJFXCU3USMKG3NN","short_pith_number":"pith:QTWHSW66","schema_version":"1.0","canonical_sha256":"84ec795bde1754e496e2a6e92628db6b49d1c48f32cdb3fa607d6fcf470c16b1","source":{"kind":"arxiv","id":"1905.05393","version":1},"attestation_state":"computed","paper":{"title":"Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Daniel Ho, Eric Liang, Ion Stoica, Pieter Abbeel, Xi Chen","submitted_at":"2019-05-14T05:01:43Z","abstract_excerpt":"A key challenge in leveraging data augmentation for neural network training is choosing an effective augmentation policy from a large search space of candidate operations. Properly chosen augmentation policies can lead to significant generalization improvements; however, state-of-the-art approaches such as AutoAugment are computationally infeasible to run for the ordinary user. In this paper, we introduce a new data augmentation algorithm, Population Based Augmentation (PBA), which generates nonstationary augmentation policy schedules instead of a fixed augmentation policy. We show that PBA ca"},"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":"1905.05393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-14T05:01:43Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"48d76357e9a37aafed18a010654d437429c23ffa3a02d6a48b96b19710cac36a","abstract_canon_sha256":"d25c9cc797e1a2adfa83e8b09990787a30e7d8dbb6db4f73411ace59bd715448"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:16.631217Z","signature_b64":"L3b/eZUFqDGJgqsna2o/cu3ToDAbbUfPm6JikqrjehkaWS0xqhNw3kM5EdcTIMuXhsbtQ/XE6DB0WqKfIvNOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84ec795bde1754e496e2a6e92628db6b49d1c48f32cdb3fa607d6fcf470c16b1","last_reissued_at":"2026-05-17T23:46:16.630641Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:16.630641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Daniel Ho, Eric Liang, Ion Stoica, Pieter Abbeel, Xi Chen","submitted_at":"2019-05-14T05:01:43Z","abstract_excerpt":"A key challenge in leveraging data augmentation for neural network training is choosing an effective augmentation policy from a large search space of candidate operations. Properly chosen augmentation policies can lead to significant generalization improvements; however, state-of-the-art approaches such as AutoAugment are computationally infeasible to run for the ordinary user. In this paper, we introduce a new data augmentation algorithm, Population Based Augmentation (PBA), which generates nonstationary augmentation policy schedules instead of a fixed augmentation policy. We show that PBA ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05393","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":""},"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":"1905.05393","created_at":"2026-05-17T23:46:16.630724+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.05393v1","created_at":"2026-05-17T23:46:16.630724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05393","created_at":"2026-05-17T23:46:16.630724+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTWHSW66C5KO","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTWHSW66C5KOJFXC","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTWHSW66","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11172","citing_title":"Learning Data Augmentation Strategies for Object Detection","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTWHSW66C5KOJFXCU3USMKG3NN","json":"https://pith.science/pith/QTWHSW66C5KOJFXCU3USMKG3NN.json","graph_json":"https://pith.science/api/pith-number/QTWHSW66C5KOJFXCU3USMKG3NN/graph.json","events_json":"https://pith.science/api/pith-number/QTWHSW66C5KOJFXCU3USMKG3NN/events.json","paper":"https://pith.science/paper/QTWHSW66"},"agent_actions":{"view_html":"https://pith.science/pith/QTWHSW66C5KOJFXCU3USMKG3NN","download_json":"https://pith.science/pith/QTWHSW66C5KOJFXCU3USMKG3NN.json","view_paper":"https://pith.science/paper/QTWHSW66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.05393&json=true","fetch_graph":"https://pith.science/api/pith-number/QTWHSW66C5KOJFXCU3USMKG3NN/graph.json","fetch_events":"https://pith.science/api/pith-number/QTWHSW66C5KOJFXCU3USMKG3NN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTWHSW66C5KOJFXCU3USMKG3NN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTWHSW66C5KOJFXCU3USMKG3NN/action/storage_attestation","attest_author":"https://pith.science/pith/QTWHSW66C5KOJFXCU3USMKG3NN/action/author_attestation","sign_citation":"https://pith.science/pith/QTWHSW66C5KOJFXCU3USMKG3NN/action/citation_signature","submit_replication":"https://pith.science/pith/QTWHSW66C5KOJFXCU3USMKG3NN/action/replication_record"}},"created_at":"2026-05-17T23:46:16.630724+00:00","updated_at":"2026-05-17T23:46:16.630724+00:00"}