{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:SIRNTYNOVI6UQ6CTXTWOLEMMOL","short_pith_number":"pith:SIRNTYNO","schema_version":"1.0","canonical_sha256":"9222d9e1aeaa3d487853bcece5918c72d183711518d5dabfb8eecd49c2c3e10c","source":{"kind":"arxiv","id":"1412.6583","version":4},"attestation_state":"computed","paper":{"title":"Discovering Hidden Factors of Variation in Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Arjun K. Bansal, Brian Cheung, Bruno A. Olshausen, Jesse A. Livezey","submitted_at":"2014-12-20T02:52:03Z","abstract_excerpt":"Deep learning has enjoyed a great deal of success because of its ability to learn useful features for tasks such as classification. But there has been less exploration in learning the factors of variation apart from the classification signal. By augmenting autoencoders with simple regularization terms during training, we demonstrate that standard deep architectures can discover and explicitly represent factors of variation beyond those relevant for categorization. We introduce a cross-covariance penalty (XCov) as a method to disentangle factors like handwriting style for digits and subject ide"},"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":"1412.6583","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-20T02:52:03Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"15c59122ab70e6fe27cb7457433c17a576998ac5a5caf194e7eb9fd6900e3af4","abstract_canon_sha256":"80ceeebb60967255f96dcb8d05a59ee554ff5772216fbadbfddb9d80ba9af7f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:46:13.741628Z","signature_b64":"+MxFRlWCMvgz+ERbCoU7+CzFQO6sXwj0ylhA9pMayyHOXMIm6WAhKSlkvBRUn4qcfyOcPsEyVhUnI80ZZyEgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9222d9e1aeaa3d487853bcece5918c72d183711518d5dabfb8eecd49c2c3e10c","last_reissued_at":"2026-05-18T01:46:13.740890Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:46:13.740890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discovering Hidden Factors of Variation in Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Arjun K. Bansal, Brian Cheung, Bruno A. Olshausen, Jesse A. Livezey","submitted_at":"2014-12-20T02:52:03Z","abstract_excerpt":"Deep learning has enjoyed a great deal of success because of its ability to learn useful features for tasks such as classification. But there has been less exploration in learning the factors of variation apart from the classification signal. By augmenting autoencoders with simple regularization terms during training, we demonstrate that standard deep architectures can discover and explicitly represent factors of variation beyond those relevant for categorization. We introduce a cross-covariance penalty (XCov) as a method to disentangle factors like handwriting style for digits and subject ide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6583","kind":"arxiv","version":4},"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":"1412.6583","created_at":"2026-05-18T01:46:13.741002+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.6583v4","created_at":"2026-05-18T01:46:13.741002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6583","created_at":"2026-05-18T01:46:13.741002+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIRNTYNOVI6U","created_at":"2026-05-18T12:28:49.207871+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIRNTYNOVI6UQ6CT","created_at":"2026-05-18T12:28:49.207871+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIRNTYNO","created_at":"2026-05-18T12:28:49.207871+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/SIRNTYNOVI6UQ6CTXTWOLEMMOL","json":"https://pith.science/pith/SIRNTYNOVI6UQ6CTXTWOLEMMOL.json","graph_json":"https://pith.science/api/pith-number/SIRNTYNOVI6UQ6CTXTWOLEMMOL/graph.json","events_json":"https://pith.science/api/pith-number/SIRNTYNOVI6UQ6CTXTWOLEMMOL/events.json","paper":"https://pith.science/paper/SIRNTYNO"},"agent_actions":{"view_html":"https://pith.science/pith/SIRNTYNOVI6UQ6CTXTWOLEMMOL","download_json":"https://pith.science/pith/SIRNTYNOVI6UQ6CTXTWOLEMMOL.json","view_paper":"https://pith.science/paper/SIRNTYNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.6583&json=true","fetch_graph":"https://pith.science/api/pith-number/SIRNTYNOVI6UQ6CTXTWOLEMMOL/graph.json","fetch_events":"https://pith.science/api/pith-number/SIRNTYNOVI6UQ6CTXTWOLEMMOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIRNTYNOVI6UQ6CTXTWOLEMMOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIRNTYNOVI6UQ6CTXTWOLEMMOL/action/storage_attestation","attest_author":"https://pith.science/pith/SIRNTYNOVI6UQ6CTXTWOLEMMOL/action/author_attestation","sign_citation":"https://pith.science/pith/SIRNTYNOVI6UQ6CTXTWOLEMMOL/action/citation_signature","submit_replication":"https://pith.science/pith/SIRNTYNOVI6UQ6CTXTWOLEMMOL/action/replication_record"}},"created_at":"2026-05-18T01:46:13.741002+00:00","updated_at":"2026-05-18T01:46:13.741002+00:00"}