{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:H3K5PXMF2AXGNY7LV4YONSYNOK","short_pith_number":"pith:H3K5PXMF","schema_version":"1.0","canonical_sha256":"3ed5d7dd85d02e66e3ebaf30e6cb0d72a9261f23a63ce412cd6c77f0b47dcbb2","source":{"kind":"arxiv","id":"1905.12914","version":3},"attestation_state":"computed","paper":{"title":"Meta Dropout: Learning to Perturb Features for Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eunho Yang, Hae Beom Lee, Sung Ju Hwang, Taewook Nam","submitted_at":"2019-05-30T08:44:16Z","abstract_excerpt":"A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we know how to optimally perturb training examples to account for test examples, we may achieve better generalization performance. However, obtaining such perturbation is not possible in standard machine learning frameworks as the distribution of the test data is unknown. To tackle this challenge, we propose a novel regularization method, meta-dropout, which learns to perturb the latent features of training examples for generalization in a meta-learning framework. Specifically, we meta-lea"},"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":"1905.12914","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T08:44:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"af155a5ce071b0a6ebd806902031dc5e8a2aac6a2596298af7c9e18780123696","abstract_canon_sha256":"8c57df59527ed455cefc9d032bb94bdbd82eb8a8db29646e227638e1d4de62d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:13.446556Z","signature_b64":"kjwS6EC2DAkqUULsYRCXg9cjgsC+Zm7ioWwukHnxPjm0J2cYwntz+PiNpuMNpPN0hPovjZtLWmojZ2Ob6GtJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ed5d7dd85d02e66e3ebaf30e6cb0d72a9261f23a63ce412cd6c77f0b47dcbb2","last_reissued_at":"2026-07-05T03:56:13.446162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:13.446162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta Dropout: Learning to Perturb Features for Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eunho Yang, Hae Beom Lee, Sung Ju Hwang, Taewook Nam","submitted_at":"2019-05-30T08:44:16Z","abstract_excerpt":"A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we know how to optimally perturb training examples to account for test examples, we may achieve better generalization performance. However, obtaining such perturbation is not possible in standard machine learning frameworks as the distribution of the test data is unknown. To tackle this challenge, we propose a novel regularization method, meta-dropout, which learns to perturb the latent features of training examples for generalization in a meta-learning framework. Specifically, we meta-lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12914","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.12914/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":"1905.12914","created_at":"2026-07-05T03:56:13.446215+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12914v3","created_at":"2026-07-05T03:56:13.446215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12914","created_at":"2026-07-05T03:56:13.446215+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3K5PXMF2AXG","created_at":"2026-07-05T03:56:13.446215+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3K5PXMF2AXGNY7L","created_at":"2026-07-05T03:56:13.446215+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3K5PXMF","created_at":"2026-07-05T03:56:13.446215+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/H3K5PXMF2AXGNY7LV4YONSYNOK","json":"https://pith.science/pith/H3K5PXMF2AXGNY7LV4YONSYNOK.json","graph_json":"https://pith.science/api/pith-number/H3K5PXMF2AXGNY7LV4YONSYNOK/graph.json","events_json":"https://pith.science/api/pith-number/H3K5PXMF2AXGNY7LV4YONSYNOK/events.json","paper":"https://pith.science/paper/H3K5PXMF"},"agent_actions":{"view_html":"https://pith.science/pith/H3K5PXMF2AXGNY7LV4YONSYNOK","download_json":"https://pith.science/pith/H3K5PXMF2AXGNY7LV4YONSYNOK.json","view_paper":"https://pith.science/paper/H3K5PXMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12914&json=true","fetch_graph":"https://pith.science/api/pith-number/H3K5PXMF2AXGNY7LV4YONSYNOK/graph.json","fetch_events":"https://pith.science/api/pith-number/H3K5PXMF2AXGNY7LV4YONSYNOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3K5PXMF2AXGNY7LV4YONSYNOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3K5PXMF2AXGNY7LV4YONSYNOK/action/storage_attestation","attest_author":"https://pith.science/pith/H3K5PXMF2AXGNY7LV4YONSYNOK/action/author_attestation","sign_citation":"https://pith.science/pith/H3K5PXMF2AXGNY7LV4YONSYNOK/action/citation_signature","submit_replication":"https://pith.science/pith/H3K5PXMF2AXGNY7LV4YONSYNOK/action/replication_record"}},"created_at":"2026-07-05T03:56:13.446215+00:00","updated_at":"2026-07-05T03:56:13.446215+00:00"}