{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NGQUCCFKB2BSETOL2NTGCDW6FJ","short_pith_number":"pith:NGQUCCFK","schema_version":"1.0","canonical_sha256":"69a14108aa0e83224dcbd366610ede2a4e4838187aab93f31472227b523bb839","source":{"kind":"arxiv","id":"1802.05355","version":1},"attestation_state":"computed","paper":{"title":"The Role of Information Complexity and Randomization in Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Leonardo Rey Vega, Mat\\'ias Vera, Pablo Piantanida","submitted_at":"2018-02-14T23:31:11Z","abstract_excerpt":"A grand challenge in representation learning is to learn the different explanatory factors of variation behind the high dimen- sional data. Encoder models are often determined to optimize performance on training data when the real objective is to generalize well to unseen data. Although there is enough numerical evidence suggesting that noise injection (during training) at the representation level might improve the generalization ability of encoders, an information-theoretic understanding of this principle remains elusive. This paper presents a sample-dependent bound on the generalization gap "},"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":"1802.05355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-14T23:31:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8f5dfb73180c709e6d0cfe34dc29ec66a98b7bce6b0915c84a87600c6061fa0e","abstract_canon_sha256":"049113c1683cd5f471646a8e33d351d67efd72062ef20d701c23c0efbc793e4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:15.884166Z","signature_b64":"Aef++IQoBe3LjM3YgNri+SW12hzfqFc/KvK07uZxTYf3N7CFETJCy24BFQWV4NtjaNagcS1nrrW4PbpSXLEaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69a14108aa0e83224dcbd366610ede2a4e4838187aab93f31472227b523bb839","last_reissued_at":"2026-05-18T00:23:15.883489Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:15.883489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Role of Information Complexity and Randomization in Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Leonardo Rey Vega, Mat\\'ias Vera, Pablo Piantanida","submitted_at":"2018-02-14T23:31:11Z","abstract_excerpt":"A grand challenge in representation learning is to learn the different explanatory factors of variation behind the high dimen- sional data. Encoder models are often determined to optimize performance on training data when the real objective is to generalize well to unseen data. Although there is enough numerical evidence suggesting that noise injection (during training) at the representation level might improve the generalization ability of encoders, an information-theoretic understanding of this principle remains elusive. This paper presents a sample-dependent bound on the generalization gap "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05355","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":""},"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":"1802.05355","created_at":"2026-05-18T00:23:15.883606+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.05355v1","created_at":"2026-05-18T00:23:15.883606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05355","created_at":"2026-05-18T00:23:15.883606+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGQUCCFKB2BS","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGQUCCFKB2BSETOL","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGQUCCFK","created_at":"2026-05-18T12:32:40.477152+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/NGQUCCFKB2BSETOL2NTGCDW6FJ","json":"https://pith.science/pith/NGQUCCFKB2BSETOL2NTGCDW6FJ.json","graph_json":"https://pith.science/api/pith-number/NGQUCCFKB2BSETOL2NTGCDW6FJ/graph.json","events_json":"https://pith.science/api/pith-number/NGQUCCFKB2BSETOL2NTGCDW6FJ/events.json","paper":"https://pith.science/paper/NGQUCCFK"},"agent_actions":{"view_html":"https://pith.science/pith/NGQUCCFKB2BSETOL2NTGCDW6FJ","download_json":"https://pith.science/pith/NGQUCCFKB2BSETOL2NTGCDW6FJ.json","view_paper":"https://pith.science/paper/NGQUCCFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.05355&json=true","fetch_graph":"https://pith.science/api/pith-number/NGQUCCFKB2BSETOL2NTGCDW6FJ/graph.json","fetch_events":"https://pith.science/api/pith-number/NGQUCCFKB2BSETOL2NTGCDW6FJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGQUCCFKB2BSETOL2NTGCDW6FJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGQUCCFKB2BSETOL2NTGCDW6FJ/action/storage_attestation","attest_author":"https://pith.science/pith/NGQUCCFKB2BSETOL2NTGCDW6FJ/action/author_attestation","sign_citation":"https://pith.science/pith/NGQUCCFKB2BSETOL2NTGCDW6FJ/action/citation_signature","submit_replication":"https://pith.science/pith/NGQUCCFKB2BSETOL2NTGCDW6FJ/action/replication_record"}},"created_at":"2026-05-18T00:23:15.883606+00:00","updated_at":"2026-05-18T00:23:15.883606+00:00"}