{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:C6D4JA6SZQ2VC2BSNXGCD7ZTA7","short_pith_number":"pith:C6D4JA6S","schema_version":"1.0","canonical_sha256":"1787c483d2cc355168326dcc21ff3307e769512b5e5a8c8bb1ceeea909ffdf00","source":{"kind":"arxiv","id":"2006.04769","version":1},"attestation_state":"computed","paper":{"title":"The Penalty Imposed by Ablated Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Najmi, Frederick Liu, Mukund Sundararajan","submitted_at":"2020-06-08T17:38:21Z","abstract_excerpt":"There is a set of data augmentation techniques that ablate parts of the input at random. These include input dropout, cutout, and random erasing. We term these techniques ablated data augmentation. Though these techniques seems similar in spirit and have shown success in improving model performance in a variety of domains, we do not yet have a mathematical understanding of the differences between these techniques like we do for other regularization techniques like L1 or L2. First, we study a formal model of mean ablated data augmentation and inverted dropout for linear regression. We prove tha"},"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":"2006.04769","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T17:38:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6687a438a054a4c3da4637de57134edd1dfa3ef4b968392b128141dfafedeeaa","abstract_canon_sha256":"2e795b30f976935f4c3e7c594fcc22cc5dc2dee7da571d2e12fb61a5de44b659"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:48.599458Z","signature_b64":"OhrruKWzs/U/WsyiF8qKi04bq0yNcMYic183mR3KtMKDAULzwy52D8O8qyVG24uZ6RMKWPd5w0t+tT8Ah2DuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1787c483d2cc355168326dcc21ff3307e769512b5e5a8c8bb1ceeea909ffdf00","last_reissued_at":"2026-07-05T01:08:48.599023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:48.599023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Penalty Imposed by Ablated Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Najmi, Frederick Liu, Mukund Sundararajan","submitted_at":"2020-06-08T17:38:21Z","abstract_excerpt":"There is a set of data augmentation techniques that ablate parts of the input at random. These include input dropout, cutout, and random erasing. We term these techniques ablated data augmentation. Though these techniques seems similar in spirit and have shown success in improving model performance in a variety of domains, we do not yet have a mathematical understanding of the differences between these techniques like we do for other regularization techniques like L1 or L2. First, we study a formal model of mean ablated data augmentation and inverted dropout for linear regression. We prove tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04769","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.04769/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":"2006.04769","created_at":"2026-07-05T01:08:48.599081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04769v1","created_at":"2026-07-05T01:08:48.599081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04769","created_at":"2026-07-05T01:08:48.599081+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6D4JA6SZQ2V","created_at":"2026-07-05T01:08:48.599081+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6D4JA6SZQ2VC2BS","created_at":"2026-07-05T01:08:48.599081+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6D4JA6S","created_at":"2026-07-05T01:08:48.599081+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/C6D4JA6SZQ2VC2BSNXGCD7ZTA7","json":"https://pith.science/pith/C6D4JA6SZQ2VC2BSNXGCD7ZTA7.json","graph_json":"https://pith.science/api/pith-number/C6D4JA6SZQ2VC2BSNXGCD7ZTA7/graph.json","events_json":"https://pith.science/api/pith-number/C6D4JA6SZQ2VC2BSNXGCD7ZTA7/events.json","paper":"https://pith.science/paper/C6D4JA6S"},"agent_actions":{"view_html":"https://pith.science/pith/C6D4JA6SZQ2VC2BSNXGCD7ZTA7","download_json":"https://pith.science/pith/C6D4JA6SZQ2VC2BSNXGCD7ZTA7.json","view_paper":"https://pith.science/paper/C6D4JA6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04769&json=true","fetch_graph":"https://pith.science/api/pith-number/C6D4JA6SZQ2VC2BSNXGCD7ZTA7/graph.json","fetch_events":"https://pith.science/api/pith-number/C6D4JA6SZQ2VC2BSNXGCD7ZTA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6D4JA6SZQ2VC2BSNXGCD7ZTA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6D4JA6SZQ2VC2BSNXGCD7ZTA7/action/storage_attestation","attest_author":"https://pith.science/pith/C6D4JA6SZQ2VC2BSNXGCD7ZTA7/action/author_attestation","sign_citation":"https://pith.science/pith/C6D4JA6SZQ2VC2BSNXGCD7ZTA7/action/citation_signature","submit_replication":"https://pith.science/pith/C6D4JA6SZQ2VC2BSNXGCD7ZTA7/action/replication_record"}},"created_at":"2026-07-05T01:08:48.599081+00:00","updated_at":"2026-07-05T01:08:48.599081+00:00"}