{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:TYTQRVFYRTTXHZ5VH5H3QHECT5","short_pith_number":"pith:TYTQRVFY","schema_version":"1.0","canonical_sha256":"9e2708d4b88ce773e7b53f4fb81c829f41a6155ba895140929ac5b35a18a5ec8","source":{"kind":"arxiv","id":"1412.6257","version":1},"attestation_state":"computed","paper":{"title":"Gradual training of deep denoising auto encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Alexander Kalmanovich, Gal Chechik","submitted_at":"2014-12-19T09:30:33Z","abstract_excerpt":"Stacked denoising auto encoders (DAEs) are well known to learn useful deep representations, which can be used to improve supervised training by initializing a deep network. We investigate a training scheme of a deep DAE, where DAE layers are gradually added and keep adapting as additional layers are added. We show that in the regime of mid-sized datasets, this gradual training provides a small but consistent improvement over stacked training in both reconstruction quality and classification error over stacked training on MNIST and CIFAR datasets."},"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":"1412.6257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-19T09:30:33Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"4eb495a1bcbbe336b34645bbd4a2bb49b1f34c926260f7222831be6b3bfb85f8","abstract_canon_sha256":"cad9a365b27af2610c5cc6fbf94125d156cf035fd3227b6831f53dae7bd15dc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:30:53.988473Z","signature_b64":"IIrQRsozMq5fUPHgtG1lLlQKSKXXrsAu0XWEsOQ43qjolB6xdLnTX6h9mfQVcfbZ9PfUBf0m2AFLcHUK0H9+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e2708d4b88ce773e7b53f4fb81c829f41a6155ba895140929ac5b35a18a5ec8","last_reissued_at":"2026-05-18T02:30:53.987803Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:30:53.987803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradual training of deep denoising auto encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Alexander Kalmanovich, Gal Chechik","submitted_at":"2014-12-19T09:30:33Z","abstract_excerpt":"Stacked denoising auto encoders (DAEs) are well known to learn useful deep representations, which can be used to improve supervised training by initializing a deep network. We investigate a training scheme of a deep DAE, where DAE layers are gradually added and keep adapting as additional layers are added. We show that in the regime of mid-sized datasets, this gradual training provides a small but consistent improvement over stacked training in both reconstruction quality and classification error over stacked training on MNIST and CIFAR datasets."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6257","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":"1412.6257","created_at":"2026-05-18T02:30:53.987898+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.6257v1","created_at":"2026-05-18T02:30:53.987898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6257","created_at":"2026-05-18T02:30:53.987898+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYTQRVFYRTTX","created_at":"2026-05-18T12:28:52.271510+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYTQRVFYRTTXHZ5V","created_at":"2026-05-18T12:28:52.271510+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYTQRVFY","created_at":"2026-05-18T12:28:52.271510+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/TYTQRVFYRTTXHZ5VH5H3QHECT5","json":"https://pith.science/pith/TYTQRVFYRTTXHZ5VH5H3QHECT5.json","graph_json":"https://pith.science/api/pith-number/TYTQRVFYRTTXHZ5VH5H3QHECT5/graph.json","events_json":"https://pith.science/api/pith-number/TYTQRVFYRTTXHZ5VH5H3QHECT5/events.json","paper":"https://pith.science/paper/TYTQRVFY"},"agent_actions":{"view_html":"https://pith.science/pith/TYTQRVFYRTTXHZ5VH5H3QHECT5","download_json":"https://pith.science/pith/TYTQRVFYRTTXHZ5VH5H3QHECT5.json","view_paper":"https://pith.science/paper/TYTQRVFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.6257&json=true","fetch_graph":"https://pith.science/api/pith-number/TYTQRVFYRTTXHZ5VH5H3QHECT5/graph.json","fetch_events":"https://pith.science/api/pith-number/TYTQRVFYRTTXHZ5VH5H3QHECT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYTQRVFYRTTXHZ5VH5H3QHECT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYTQRVFYRTTXHZ5VH5H3QHECT5/action/storage_attestation","attest_author":"https://pith.science/pith/TYTQRVFYRTTXHZ5VH5H3QHECT5/action/author_attestation","sign_citation":"https://pith.science/pith/TYTQRVFYRTTXHZ5VH5H3QHECT5/action/citation_signature","submit_replication":"https://pith.science/pith/TYTQRVFYRTTXHZ5VH5H3QHECT5/action/replication_record"}},"created_at":"2026-05-18T02:30:53.987898+00:00","updated_at":"2026-05-18T02:30:53.987898+00:00"}