{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:GUN5OPVE3BRBD2PQDSJMAZ6FBG","short_pith_number":"pith:GUN5OPVE","schema_version":"1.0","canonical_sha256":"351bd73ea4d86211e9f01c92c067c5098a8ffc661857034648336990bf382d28","source":{"kind":"arxiv","id":"1609.08976","version":1},"attestation_state":"computed","paper":{"title":"Variational Autoencoder for Deep Learning of Images, Labels and Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew Stevens, Chunyuan Li, Lawrence Carin, Ricardo Henao, Xin Yuan, Yunchen Pu, Zhe Gan","submitted_at":"2016-09-28T15:56:15Z","abstract_excerpt":"A novel variational autoencoder is developed to model images, as well as associated labels or captions. The Deep Generative Deconvolutional Network (DGDN) is used as a decoder of the latent image features, and a deep Convolutional Neural Network (CNN) is used as an image encoder; the CNN is used to approximate a distribution for the latent DGDN features/code. The latent code is also linked to generative models for labels (Bayesian support vector machine) or captions (recurrent neural network). When predicting a label/caption for a new image at test, averaging is performed across the distributi"},"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":"1609.08976","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-09-28T15:56:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5aeecf2d663351cd94eb96edb70f7f99464ce4423ab0784c3247ef63ae75fae0","abstract_canon_sha256":"f5c203517f4a33b5583436e8ef8c0da42655d193d135774882e4d6be65ca8db7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:41.469014Z","signature_b64":"4rTZZqDvBYAyGe+6E9MZ312zg8nWQ+rZjenc1bIrHNQvRUL1CQT3OgOrhKDMukHjpI9jZl5DpYcwBv28mFhDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"351bd73ea4d86211e9f01c92c067c5098a8ffc661857034648336990bf382d28","last_reissued_at":"2026-05-18T01:03:41.468637Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:41.468637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Autoencoder for Deep Learning of Images, Labels and Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew Stevens, Chunyuan Li, Lawrence Carin, Ricardo Henao, Xin Yuan, Yunchen Pu, Zhe Gan","submitted_at":"2016-09-28T15:56:15Z","abstract_excerpt":"A novel variational autoencoder is developed to model images, as well as associated labels or captions. The Deep Generative Deconvolutional Network (DGDN) is used as a decoder of the latent image features, and a deep Convolutional Neural Network (CNN) is used as an image encoder; the CNN is used to approximate a distribution for the latent DGDN features/code. The latent code is also linked to generative models for labels (Bayesian support vector machine) or captions (recurrent neural network). When predicting a label/caption for a new image at test, averaging is performed across the distributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.08976","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":"1609.08976","created_at":"2026-05-18T01:03:41.468703+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.08976v1","created_at":"2026-05-18T01:03:41.468703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.08976","created_at":"2026-05-18T01:03:41.468703+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUN5OPVE3BRB","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUN5OPVE3BRBD2PQ","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUN5OPVE","created_at":"2026-05-18T12:30:19.053100+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/GUN5OPVE3BRBD2PQDSJMAZ6FBG","json":"https://pith.science/pith/GUN5OPVE3BRBD2PQDSJMAZ6FBG.json","graph_json":"https://pith.science/api/pith-number/GUN5OPVE3BRBD2PQDSJMAZ6FBG/graph.json","events_json":"https://pith.science/api/pith-number/GUN5OPVE3BRBD2PQDSJMAZ6FBG/events.json","paper":"https://pith.science/paper/GUN5OPVE"},"agent_actions":{"view_html":"https://pith.science/pith/GUN5OPVE3BRBD2PQDSJMAZ6FBG","download_json":"https://pith.science/pith/GUN5OPVE3BRBD2PQDSJMAZ6FBG.json","view_paper":"https://pith.science/paper/GUN5OPVE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.08976&json=true","fetch_graph":"https://pith.science/api/pith-number/GUN5OPVE3BRBD2PQDSJMAZ6FBG/graph.json","fetch_events":"https://pith.science/api/pith-number/GUN5OPVE3BRBD2PQDSJMAZ6FBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUN5OPVE3BRBD2PQDSJMAZ6FBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUN5OPVE3BRBD2PQDSJMAZ6FBG/action/storage_attestation","attest_author":"https://pith.science/pith/GUN5OPVE3BRBD2PQDSJMAZ6FBG/action/author_attestation","sign_citation":"https://pith.science/pith/GUN5OPVE3BRBD2PQDSJMAZ6FBG/action/citation_signature","submit_replication":"https://pith.science/pith/GUN5OPVE3BRBD2PQDSJMAZ6FBG/action/replication_record"}},"created_at":"2026-05-18T01:03:41.468703+00:00","updated_at":"2026-05-18T01:03:41.468703+00:00"}