{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BF2OCZUHURTA5WLRO23MV3ZSCW","short_pith_number":"pith:BF2OCZUH","schema_version":"1.0","canonical_sha256":"0974e16687a4660ed97176b6caef321586f84d5ba0053b07f13ac532ea59735a","source":{"kind":"arxiv","id":"1711.04340","version":3},"attestation_state":"computed","paper":{"title":"Data Augmentation Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Amos Storkey, Antreas Antoniou, Harrison Edwards","submitted_at":"2017-11-12T19:17:57Z","abstract_excerpt":"Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviates this by using existing data more effectively. However standard data augmentation produces only limited plausible alternative data. Given there is potential to generate a much broader set of augmentations, we design and train a generative model to do data augmentation. The model, based on image conditional Generative Adversarial Networks, takes data from a source domain and learns to take any data item and generalis"},"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":"1711.04340","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-12T19:17:57Z","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"title_canon_sha256":"05554f38b6dc552c41292a472ca7bf562cc8c365a4a614c50ce490abeadc7dfc","abstract_canon_sha256":"a6f69723e376ec1f1424a47a880930ca6564705f0fa0231226152fdc551d5d30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:24.115647Z","signature_b64":"F0SSenRbXnTVz/IDCAO+VrSmS7Zj6edEKwyqKe8a+dkHoIl87wLNaTx6pd1ukIlokn/CsyiJhQcdlcKmtaq+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0974e16687a4660ed97176b6caef321586f84d5ba0053b07f13ac532ea59735a","last_reissued_at":"2026-05-18T00:20:24.115128Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:24.115128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Augmentation Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Amos Storkey, Antreas Antoniou, Harrison Edwards","submitted_at":"2017-11-12T19:17:57Z","abstract_excerpt":"Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviates this by using existing data more effectively. However standard data augmentation produces only limited plausible alternative data. Given there is potential to generate a much broader set of augmentations, we design and train a generative model to do data augmentation. The model, based on image conditional Generative Adversarial Networks, takes data from a source domain and learns to take any data item and generalis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04340","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":""},"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":"1711.04340","created_at":"2026-05-18T00:20:24.115202+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.04340v3","created_at":"2026-05-18T00:20:24.115202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04340","created_at":"2026-05-18T00:20:24.115202+00:00"},{"alias_kind":"pith_short_12","alias_value":"BF2OCZUHURTA","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BF2OCZUHURTA5WLR","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BF2OCZUH","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1906.11052","citing_title":"Further advantages of data augmentation on convolutional neural networks","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11172","citing_title":"Learning Data Augmentation Strategies for Object Detection","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"1907.03644","citing_title":"Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2403.10559","citing_title":"Generative Models and Connected and Automated Vehicles: A Survey in Exploring the Intersection of Transportation and AI","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BF2OCZUHURTA5WLRO23MV3ZSCW","json":"https://pith.science/pith/BF2OCZUHURTA5WLRO23MV3ZSCW.json","graph_json":"https://pith.science/api/pith-number/BF2OCZUHURTA5WLRO23MV3ZSCW/graph.json","events_json":"https://pith.science/api/pith-number/BF2OCZUHURTA5WLRO23MV3ZSCW/events.json","paper":"https://pith.science/paper/BF2OCZUH"},"agent_actions":{"view_html":"https://pith.science/pith/BF2OCZUHURTA5WLRO23MV3ZSCW","download_json":"https://pith.science/pith/BF2OCZUHURTA5WLRO23MV3ZSCW.json","view_paper":"https://pith.science/paper/BF2OCZUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.04340&json=true","fetch_graph":"https://pith.science/api/pith-number/BF2OCZUHURTA5WLRO23MV3ZSCW/graph.json","fetch_events":"https://pith.science/api/pith-number/BF2OCZUHURTA5WLRO23MV3ZSCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BF2OCZUHURTA5WLRO23MV3ZSCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BF2OCZUHURTA5WLRO23MV3ZSCW/action/storage_attestation","attest_author":"https://pith.science/pith/BF2OCZUHURTA5WLRO23MV3ZSCW/action/author_attestation","sign_citation":"https://pith.science/pith/BF2OCZUHURTA5WLRO23MV3ZSCW/action/citation_signature","submit_replication":"https://pith.science/pith/BF2OCZUHURTA5WLRO23MV3ZSCW/action/replication_record"}},"created_at":"2026-05-18T00:20:24.115202+00:00","updated_at":"2026-05-18T00:20:24.115202+00:00"}