{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:FRWKTUGDKHC7EKIODB4DPZFH5G","short_pith_number":"pith:FRWKTUGD","schema_version":"1.0","canonical_sha256":"2c6ca9d0c351c5f2290e187837e4a7e9ba32e91400d55197a0c604bf80f39788","source":{"kind":"arxiv","id":"1406.3269","version":3},"attestation_state":"computed","paper":{"title":"Scheduled denoising autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Sutton, Krzysztof J. Geras","submitted_at":"2014-06-12T15:40:18Z","abstract_excerpt":"We present a representation learning method that learns features at multiple different levels of scale. Working within the unsupervised framework of denoising autoencoders, we observe that when the input is heavily corrupted during training, the network tends to learn coarse-grained features, whereas when the input is only slightly corrupted, the network tends to learn fine-grained features. This motivates the scheduled denoising autoencoder, which starts with a high level of noise that lowers as training progresses. We find that the resulting representation yields a significant boost on a lat"},"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":"1406.3269","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-12T15:40:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1d6b877f820ae85aa9d6b8fbe41945cd57452b02ef290f1d1334f3339d0b8b66","abstract_canon_sha256":"0c009f61f42d05c17ccf682262267e678dabbe4f6086d574145c05357a4defd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:06.015220Z","signature_b64":"Mb2M9vwNP5Nirg9ftxfe8C4Rfidxwc/KjNSPFKR377U3XgzEW44C+yw9Dd+kB8q0G9duRDLKMPl175UsHppgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c6ca9d0c351c5f2290e187837e4a7e9ba32e91400d55197a0c604bf80f39788","last_reissued_at":"2026-05-18T02:19:06.014812Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:06.014812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scheduled denoising autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Sutton, Krzysztof J. Geras","submitted_at":"2014-06-12T15:40:18Z","abstract_excerpt":"We present a representation learning method that learns features at multiple different levels of scale. Working within the unsupervised framework of denoising autoencoders, we observe that when the input is heavily corrupted during training, the network tends to learn coarse-grained features, whereas when the input is only slightly corrupted, the network tends to learn fine-grained features. This motivates the scheduled denoising autoencoder, which starts with a high level of noise that lowers as training progresses. We find that the resulting representation yields a significant boost on a lat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.3269","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":""},"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":"1406.3269","created_at":"2026-05-18T02:19:06.014875+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.3269v3","created_at":"2026-05-18T02:19:06.014875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.3269","created_at":"2026-05-18T02:19:06.014875+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRWKTUGDKHC7","created_at":"2026-05-18T12:28:28.263976+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRWKTUGDKHC7EKIO","created_at":"2026-05-18T12:28:28.263976+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRWKTUGD","created_at":"2026-05-18T12:28:28.263976+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.05600","citing_title":"Generative Modeling by Estimating Gradients of the Data Distribution","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FRWKTUGDKHC7EKIODB4DPZFH5G","json":"https://pith.science/pith/FRWKTUGDKHC7EKIODB4DPZFH5G.json","graph_json":"https://pith.science/api/pith-number/FRWKTUGDKHC7EKIODB4DPZFH5G/graph.json","events_json":"https://pith.science/api/pith-number/FRWKTUGDKHC7EKIODB4DPZFH5G/events.json","paper":"https://pith.science/paper/FRWKTUGD"},"agent_actions":{"view_html":"https://pith.science/pith/FRWKTUGDKHC7EKIODB4DPZFH5G","download_json":"https://pith.science/pith/FRWKTUGDKHC7EKIODB4DPZFH5G.json","view_paper":"https://pith.science/paper/FRWKTUGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.3269&json=true","fetch_graph":"https://pith.science/api/pith-number/FRWKTUGDKHC7EKIODB4DPZFH5G/graph.json","fetch_events":"https://pith.science/api/pith-number/FRWKTUGDKHC7EKIODB4DPZFH5G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRWKTUGDKHC7EKIODB4DPZFH5G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRWKTUGDKHC7EKIODB4DPZFH5G/action/storage_attestation","attest_author":"https://pith.science/pith/FRWKTUGDKHC7EKIODB4DPZFH5G/action/author_attestation","sign_citation":"https://pith.science/pith/FRWKTUGDKHC7EKIODB4DPZFH5G/action/citation_signature","submit_replication":"https://pith.science/pith/FRWKTUGDKHC7EKIODB4DPZFH5G/action/replication_record"}},"created_at":"2026-05-18T02:19:06.014875+00:00","updated_at":"2026-05-18T02:19:06.014875+00:00"}