{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:Q6KHECRBOOTSLEAELVMRYGQNBL","short_pith_number":"pith:Q6KHECRB","schema_version":"1.0","canonical_sha256":"8794720a2173a72590045d591c1a0d0acdba448b9e6c9b2e0013b2cdcc5b2baa","source":{"kind":"arxiv","id":"1611.09119","version":2},"attestation_state":"computed","paper":{"title":"Learning Deep Representations Using Convolutional Auto-encoders with Symmetric Skip Connections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Jianfeng Dong, Xiao-Jiao Mao, Yu-Bin Yang","submitted_at":"2016-11-28T13:56:20Z","abstract_excerpt":"Unsupervised pre-training was a critical technique for training deep neural networks years ago. With sufficient labeled data and modern training techniques, it is possible to train very deep neural networks from scratch in a purely supervised manner nowadays. However, unlabeled data is easier to obtain and usually of very large scale. How to make use of them better to help supervised learning is still a well-valued topic. In this paper, we investigate convolutional denoising auto-encoders to show that unsupervised pre-training can still improve the performance of high-level image related tasks"},"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":"1611.09119","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-28T13:56:20Z","cross_cats_sorted":[],"title_canon_sha256":"42b486cd56719b27b2153455f244aeb2826c45654a56dbeee119dbabb15fd7d2","abstract_canon_sha256":"024445aceaa8c5e50bc00d410b3c095e953f4c39ff9a765ca161380308dbde9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:49.235854Z","signature_b64":"HddBlaQqjD9wMDDUt8nckXEJX5XdYo8dsNjku+eZHgANbykNREm5KhhXDDFv/F+H1Io2xD0iQnolaH8MuvHNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8794720a2173a72590045d591c1a0d0acdba448b9e6c9b2e0013b2cdcc5b2baa","last_reissued_at":"2026-05-18T00:47:49.235125Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:49.235125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Deep Representations Using Convolutional Auto-encoders with Symmetric Skip Connections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Jianfeng Dong, Xiao-Jiao Mao, Yu-Bin Yang","submitted_at":"2016-11-28T13:56:20Z","abstract_excerpt":"Unsupervised pre-training was a critical technique for training deep neural networks years ago. With sufficient labeled data and modern training techniques, it is possible to train very deep neural networks from scratch in a purely supervised manner nowadays. However, unlabeled data is easier to obtain and usually of very large scale. How to make use of them better to help supervised learning is still a well-valued topic. In this paper, we investigate convolutional denoising auto-encoders to show that unsupervised pre-training can still improve the performance of high-level image related tasks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.09119","kind":"arxiv","version":2},"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":"1611.09119","created_at":"2026-05-18T00:47:49.235226+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.09119v2","created_at":"2026-05-18T00:47:49.235226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.09119","created_at":"2026-05-18T00:47:49.235226+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6KHECRBOOTS","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6KHECRBOOTSLEAE","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6KHECRB","created_at":"2026-05-18T12:30:39.010887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2511.21577","citing_title":"HarmonicAttack: An Adaptive Cross-Domain Audio Watermark Removal","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q6KHECRBOOTSLEAELVMRYGQNBL","json":"https://pith.science/pith/Q6KHECRBOOTSLEAELVMRYGQNBL.json","graph_json":"https://pith.science/api/pith-number/Q6KHECRBOOTSLEAELVMRYGQNBL/graph.json","events_json":"https://pith.science/api/pith-number/Q6KHECRBOOTSLEAELVMRYGQNBL/events.json","paper":"https://pith.science/paper/Q6KHECRB"},"agent_actions":{"view_html":"https://pith.science/pith/Q6KHECRBOOTSLEAELVMRYGQNBL","download_json":"https://pith.science/pith/Q6KHECRBOOTSLEAELVMRYGQNBL.json","view_paper":"https://pith.science/paper/Q6KHECRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.09119&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6KHECRBOOTSLEAELVMRYGQNBL/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6KHECRBOOTSLEAELVMRYGQNBL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6KHECRBOOTSLEAELVMRYGQNBL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6KHECRBOOTSLEAELVMRYGQNBL/action/storage_attestation","attest_author":"https://pith.science/pith/Q6KHECRBOOTSLEAELVMRYGQNBL/action/author_attestation","sign_citation":"https://pith.science/pith/Q6KHECRBOOTSLEAELVMRYGQNBL/action/citation_signature","submit_replication":"https://pith.science/pith/Q6KHECRBOOTSLEAELVMRYGQNBL/action/replication_record"}},"created_at":"2026-05-18T00:47:49.235226+00:00","updated_at":"2026-05-18T00:47:49.235226+00:00"}