{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TVKC73CX37RETDTLBSC66VHU66","short_pith_number":"pith:TVKC73CX","schema_version":"1.0","canonical_sha256":"9d542fec57dfe2498e6b0c85ef54f4f7be561f5f54f38a17afe0a17f2c3b8d9c","source":{"kind":"arxiv","id":"1806.03852","version":5},"attestation_state":"computed","paper":{"title":"Data augmentation instead of explicit regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Hern\\'andez-Garc\\'ia, Peter K\\\"onig","submitted_at":"2018-06-11T08:10:18Z","abstract_excerpt":"Contrary to most machine learning models, modern deep artificial neural networks typically include multiple components that contribute to regularization. Despite the fact that some (explicit) regularization techniques, such as weight decay and dropout, require costly fine-tuning of sensitive hyperparameters, the interplay between them and other elements that provide implicit regularization is not well understood yet. Shedding light upon these interactions is key to efficiently using computational resources and may contribute to solving the puzzle of generalization in deep learning. Here, we fi"},"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":"1806.03852","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-11T08:10:18Z","cross_cats_sorted":[],"title_canon_sha256":"193ee2254e501678daef736573935d30c0cc18eb72acb4c63aa4eeb404445972","abstract_canon_sha256":"0edb1ab039b39757e2f927934c1744ec9f0e66a034e328668486ca720c86419d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:04.053419Z","signature_b64":"EKeCCggpvVKjZNoToz+B2Xmg/2xNLqswv9HBPiCjaJTpREdSct/oUxDUrb1zWj4XvRc0SjCxhKYj1u2nWgSWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d542fec57dfe2498e6b0c85ef54f4f7be561f5f54f38a17afe0a17f2c3b8d9c","last_reissued_at":"2026-07-05T01:51:04.052954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:04.052954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data augmentation instead of explicit regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Hern\\'andez-Garc\\'ia, Peter K\\\"onig","submitted_at":"2018-06-11T08:10:18Z","abstract_excerpt":"Contrary to most machine learning models, modern deep artificial neural networks typically include multiple components that contribute to regularization. Despite the fact that some (explicit) regularization techniques, such as weight decay and dropout, require costly fine-tuning of sensitive hyperparameters, the interplay between them and other elements that provide implicit regularization is not well understood yet. Shedding light upon these interactions is key to efficiently using computational resources and may contribute to solving the puzzle of generalization in deep learning. Here, we fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03852","kind":"arxiv","version":5},"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/1806.03852/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":"1806.03852","created_at":"2026-07-05T01:51:04.053006+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.03852v5","created_at":"2026-07-05T01:51:04.053006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03852","created_at":"2026-07-05T01:51:04.053006+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVKC73CX37RE","created_at":"2026-07-05T01:51:04.053006+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVKC73CX37RETDTL","created_at":"2026-07-05T01:51:04.053006+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVKC73CX","created_at":"2026-07-05T01:51:04.053006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26053","citing_title":"When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04686","citing_title":"How does the optimizer implicitly bias the model merging loss landscape?","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVKC73CX37RETDTLBSC66VHU66","json":"https://pith.science/pith/TVKC73CX37RETDTLBSC66VHU66.json","graph_json":"https://pith.science/api/pith-number/TVKC73CX37RETDTLBSC66VHU66/graph.json","events_json":"https://pith.science/api/pith-number/TVKC73CX37RETDTLBSC66VHU66/events.json","paper":"https://pith.science/paper/TVKC73CX"},"agent_actions":{"view_html":"https://pith.science/pith/TVKC73CX37RETDTLBSC66VHU66","download_json":"https://pith.science/pith/TVKC73CX37RETDTLBSC66VHU66.json","view_paper":"https://pith.science/paper/TVKC73CX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.03852&json=true","fetch_graph":"https://pith.science/api/pith-number/TVKC73CX37RETDTLBSC66VHU66/graph.json","fetch_events":"https://pith.science/api/pith-number/TVKC73CX37RETDTLBSC66VHU66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVKC73CX37RETDTLBSC66VHU66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVKC73CX37RETDTLBSC66VHU66/action/storage_attestation","attest_author":"https://pith.science/pith/TVKC73CX37RETDTLBSC66VHU66/action/author_attestation","sign_citation":"https://pith.science/pith/TVKC73CX37RETDTLBSC66VHU66/action/citation_signature","submit_replication":"https://pith.science/pith/TVKC73CX37RETDTLBSC66VHU66/action/replication_record"}},"created_at":"2026-07-05T01:51:04.053006+00:00","updated_at":"2026-07-05T01:51:04.053006+00:00"}