{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:TRAUS2RE5LRK4WK7PFVBVFD5OT","short_pith_number":"pith:TRAUS2RE","schema_version":"1.0","canonical_sha256":"9c41496a24eae2ae595f796a1a947d74d5005c741f5837cb223637d3cdd91b9d","source":{"kind":"arxiv","id":"1305.6663","version":4},"attestation_state":"computed","paper":{"title":"Generalized Denoising Auto-Encoders as Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guillaume Alain, Li Yao, Pascal Vincent, Yoshua Bengio","submitted_at":"2013-05-29T00:25:54Z","abstract_excerpt":"Recent work has shown how denoising and contractive autoencoders implicitly capture the structure of the data-generating density, in the case where the corruption noise is Gaussian, the reconstruction error is the squared error, and the data is continuous-valued. This has led to various proposals for sampling from this implicitly learned density function, using Langevin and Metropolis-Hastings MCMC. However, it remained unclear how to connect the training procedure of regularized auto-encoders to the implicit estimation of the underlying data-generating distribution when the data are discrete,"},"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":"1305.6663","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-05-29T00:25:54Z","cross_cats_sorted":[],"title_canon_sha256":"a729f5aceea7b4ca6d8aa79f5c5ff6ceb049a3d40adc609eae2867ab2813ae34","abstract_canon_sha256":"20de8bb28e1d2c8872f980f0ef02a768b3909926fc1007c9b8adf59c2960ffbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:07:34.187479Z","signature_b64":"jClPRw/LhyGXJ262VpA/ccF2vK1hARTREhEvYU2PE/fS2eZsWDAexhpNe1c/H1+Srnge6zVSGUu9GfZNaUEUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c41496a24eae2ae595f796a1a947d74d5005c741f5837cb223637d3cdd91b9d","last_reissued_at":"2026-05-18T03:07:34.186994Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:07:34.186994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized Denoising Auto-Encoders as Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guillaume Alain, Li Yao, Pascal Vincent, Yoshua Bengio","submitted_at":"2013-05-29T00:25:54Z","abstract_excerpt":"Recent work has shown how denoising and contractive autoencoders implicitly capture the structure of the data-generating density, in the case where the corruption noise is Gaussian, the reconstruction error is the squared error, and the data is continuous-valued. This has led to various proposals for sampling from this implicitly learned density function, using Langevin and Metropolis-Hastings MCMC. However, it remained unclear how to connect the training procedure of regularized auto-encoders to the implicit estimation of the underlying data-generating distribution when the data are discrete,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.6663","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":"1305.6663","created_at":"2026-05-18T03:07:34.187068+00:00"},{"alias_kind":"arxiv_version","alias_value":"1305.6663v4","created_at":"2026-05-18T03:07:34.187068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.6663","created_at":"2026-05-18T03:07:34.187068+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRAUS2RE5LRK","created_at":"2026-05-18T12:28:02.375192+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRAUS2RE5LRK4WK7","created_at":"2026-05-18T12:28:02.375192+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRAUS2RE","created_at":"2026-05-18T12:28:02.375192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.11019","citing_title":"Signal Decomposition Reveals Structure in Insider Threat Detection under Sparse Temporal Data","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TRAUS2RE5LRK4WK7PFVBVFD5OT","json":"https://pith.science/pith/TRAUS2RE5LRK4WK7PFVBVFD5OT.json","graph_json":"https://pith.science/api/pith-number/TRAUS2RE5LRK4WK7PFVBVFD5OT/graph.json","events_json":"https://pith.science/api/pith-number/TRAUS2RE5LRK4WK7PFVBVFD5OT/events.json","paper":"https://pith.science/paper/TRAUS2RE"},"agent_actions":{"view_html":"https://pith.science/pith/TRAUS2RE5LRK4WK7PFVBVFD5OT","download_json":"https://pith.science/pith/TRAUS2RE5LRK4WK7PFVBVFD5OT.json","view_paper":"https://pith.science/paper/TRAUS2RE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1305.6663&json=true","fetch_graph":"https://pith.science/api/pith-number/TRAUS2RE5LRK4WK7PFVBVFD5OT/graph.json","fetch_events":"https://pith.science/api/pith-number/TRAUS2RE5LRK4WK7PFVBVFD5OT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRAUS2RE5LRK4WK7PFVBVFD5OT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRAUS2RE5LRK4WK7PFVBVFD5OT/action/storage_attestation","attest_author":"https://pith.science/pith/TRAUS2RE5LRK4WK7PFVBVFD5OT/action/author_attestation","sign_citation":"https://pith.science/pith/TRAUS2RE5LRK4WK7PFVBVFD5OT/action/citation_signature","submit_replication":"https://pith.science/pith/TRAUS2RE5LRK4WK7PFVBVFD5OT/action/replication_record"}},"created_at":"2026-05-18T03:07:34.187068+00:00","updated_at":"2026-05-18T03:07:34.187068+00:00"}