{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7GEYI4STYH4QG3KZIOBPGUIENQ","short_pith_number":"pith:7GEYI4ST","schema_version":"1.0","canonical_sha256":"f989847253c1f9036d594382f351046c26ae20d951b9fa37823ef9c086ba3a4a","source":{"kind":"arxiv","id":"2006.07989","version":2},"attestation_state":"computed","paper":{"title":"GradAug: A New Regularization Method for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Sijie Zhu, Taojiannan Yang","submitted_at":"2020-06-14T19:30:34Z","abstract_excerpt":"We propose a new regularization method to alleviate over-fitting in deep neural networks. The key idea is utilizing randomly transformed training samples to regularize a set of sub-networks, which are originated by sampling the width of the original network, in the training process. As such, the proposed method introduces self-guided disturbances to the raw gradients of the network and therefore is termed as Gradient Augmentation (GradAug). We demonstrate that GradAug can help the network learn well-generalized and more diverse representations. Moreover, it is easy to implement and can be appl"},"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":"2006.07989","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-14T19:30:34Z","cross_cats_sorted":[],"title_canon_sha256":"c2f12a5e0cac352da3148d17394dedb40f3c50f4b7de2b30c7cb7734380fced7","abstract_canon_sha256":"516078cc9c8af987305a90eb5b8980405fdbe7533a8589bb5af45180eb33a670"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:14.322892Z","signature_b64":"g3A6KzJtSAppxK3M8HwGZVU4ZrhJ3LefDkbJMRW1ZvH1BbttuzZn8iujdgAqwLMWFYNYO+tksm76iK7zBlHZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f989847253c1f9036d594382f351046c26ae20d951b9fa37823ef9c086ba3a4a","last_reissued_at":"2026-07-05T01:42:14.322400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:14.322400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GradAug: A New Regularization Method for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Sijie Zhu, Taojiannan Yang","submitted_at":"2020-06-14T19:30:34Z","abstract_excerpt":"We propose a new regularization method to alleviate over-fitting in deep neural networks. The key idea is utilizing randomly transformed training samples to regularize a set of sub-networks, which are originated by sampling the width of the original network, in the training process. As such, the proposed method introduces self-guided disturbances to the raw gradients of the network and therefore is termed as Gradient Augmentation (GradAug). We demonstrate that GradAug can help the network learn well-generalized and more diverse representations. Moreover, it is easy to implement and can be appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07989","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/2006.07989/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":"2006.07989","created_at":"2026-07-05T01:42:14.322464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07989v2","created_at":"2026-07-05T01:42:14.322464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07989","created_at":"2026-07-05T01:42:14.322464+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GEYI4STYH4Q","created_at":"2026-07-05T01:42:14.322464+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GEYI4STYH4QG3KZ","created_at":"2026-07-05T01:42:14.322464+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GEYI4ST","created_at":"2026-07-05T01:42:14.322464+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/7GEYI4STYH4QG3KZIOBPGUIENQ","json":"https://pith.science/pith/7GEYI4STYH4QG3KZIOBPGUIENQ.json","graph_json":"https://pith.science/api/pith-number/7GEYI4STYH4QG3KZIOBPGUIENQ/graph.json","events_json":"https://pith.science/api/pith-number/7GEYI4STYH4QG3KZIOBPGUIENQ/events.json","paper":"https://pith.science/paper/7GEYI4ST"},"agent_actions":{"view_html":"https://pith.science/pith/7GEYI4STYH4QG3KZIOBPGUIENQ","download_json":"https://pith.science/pith/7GEYI4STYH4QG3KZIOBPGUIENQ.json","view_paper":"https://pith.science/paper/7GEYI4ST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07989&json=true","fetch_graph":"https://pith.science/api/pith-number/7GEYI4STYH4QG3KZIOBPGUIENQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7GEYI4STYH4QG3KZIOBPGUIENQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GEYI4STYH4QG3KZIOBPGUIENQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GEYI4STYH4QG3KZIOBPGUIENQ/action/storage_attestation","attest_author":"https://pith.science/pith/7GEYI4STYH4QG3KZIOBPGUIENQ/action/author_attestation","sign_citation":"https://pith.science/pith/7GEYI4STYH4QG3KZIOBPGUIENQ/action/citation_signature","submit_replication":"https://pith.science/pith/7GEYI4STYH4QG3KZIOBPGUIENQ/action/replication_record"}},"created_at":"2026-07-05T01:42:14.322464+00:00","updated_at":"2026-07-05T01:42:14.322464+00:00"}