{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OATXF4MLQCUNC3UPUAHEMMLS7R","short_pith_number":"pith:OATXF4ML","schema_version":"1.0","canonical_sha256":"702772f18b80a8d16e8fa00e463172fc77cdfbf9b8c63dd6c7a69c967aece3a9","source":{"kind":"arxiv","id":"1908.09948","version":1},"attestation_state":"computed","paper":{"title":"PixelVAE++: Improved PixelVAE with Discrete Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Evgeny Andriyash, Hossein Sadeghi, Lorenzo Buffoni, Mohammad H. Amin, Walter Vinci","submitted_at":"2019-08-26T22:40:55Z","abstract_excerpt":"Constructing powerful generative models for natural images is a challenging task. PixelCNN models capture details and local information in images very well but have limited receptive field. Variational autoencoders with a factorial decoder can capture global information easily, but they often fail to reconstruct details faithfully. PixelVAE combines the best features of the two models and constructs a generative model that is able to learn local and global structures. Here we introduce PixelVAE++, a VAE with three types of latent variables and a PixelCNN++ for the decoder. We introduce a novel"},"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":"1908.09948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-26T22:40:55Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"babac36e2a987461f5342983350b0c0da0c2fc7b7b1df5a2663baf084457d19c","abstract_canon_sha256":"51c5d3ed869265706bc8980b985f3b294eefcdab4fad56e515056eae1cff2d21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:52.185867Z","signature_b64":"uZ3ysyHy2i2rekF8c+sGXUMpl6fUyvC9miFLx/WapMc06/Z6XCPmFGYalfxFhm277IukqR1Fkn/l0jy+8WNwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"702772f18b80a8d16e8fa00e463172fc77cdfbf9b8c63dd6c7a69c967aece3a9","last_reissued_at":"2026-07-04T23:59:52.185442Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:52.185442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PixelVAE++: Improved PixelVAE with Discrete Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Evgeny Andriyash, Hossein Sadeghi, Lorenzo Buffoni, Mohammad H. Amin, Walter Vinci","submitted_at":"2019-08-26T22:40:55Z","abstract_excerpt":"Constructing powerful generative models for natural images is a challenging task. PixelCNN models capture details and local information in images very well but have limited receptive field. Variational autoencoders with a factorial decoder can capture global information easily, but they often fail to reconstruct details faithfully. PixelVAE combines the best features of the two models and constructs a generative model that is able to learn local and global structures. Here we introduce PixelVAE++, a VAE with three types of latent variables and a PixelCNN++ for the decoder. We introduce a novel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09948","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.09948/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1908.09948","created_at":"2026-07-04T23:59:52.185494+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.09948v1","created_at":"2026-07-04T23:59:52.185494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09948","created_at":"2026-07-04T23:59:52.185494+00:00"},{"alias_kind":"pith_short_12","alias_value":"OATXF4MLQCUN","created_at":"2026-07-04T23:59:52.185494+00:00"},{"alias_kind":"pith_short_16","alias_value":"OATXF4MLQCUNC3UP","created_at":"2026-07-04T23:59:52.185494+00:00"},{"alias_kind":"pith_short_8","alias_value":"OATXF4ML","created_at":"2026-07-04T23:59:52.185494+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/OATXF4MLQCUNC3UPUAHEMMLS7R","json":"https://pith.science/pith/OATXF4MLQCUNC3UPUAHEMMLS7R.json","graph_json":"https://pith.science/api/pith-number/OATXF4MLQCUNC3UPUAHEMMLS7R/graph.json","events_json":"https://pith.science/api/pith-number/OATXF4MLQCUNC3UPUAHEMMLS7R/events.json","paper":"https://pith.science/paper/OATXF4ML"},"agent_actions":{"view_html":"https://pith.science/pith/OATXF4MLQCUNC3UPUAHEMMLS7R","download_json":"https://pith.science/pith/OATXF4MLQCUNC3UPUAHEMMLS7R.json","view_paper":"https://pith.science/paper/OATXF4ML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.09948&json=true","fetch_graph":"https://pith.science/api/pith-number/OATXF4MLQCUNC3UPUAHEMMLS7R/graph.json","fetch_events":"https://pith.science/api/pith-number/OATXF4MLQCUNC3UPUAHEMMLS7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OATXF4MLQCUNC3UPUAHEMMLS7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OATXF4MLQCUNC3UPUAHEMMLS7R/action/storage_attestation","attest_author":"https://pith.science/pith/OATXF4MLQCUNC3UPUAHEMMLS7R/action/author_attestation","sign_citation":"https://pith.science/pith/OATXF4MLQCUNC3UPUAHEMMLS7R/action/citation_signature","submit_replication":"https://pith.science/pith/OATXF4MLQCUNC3UPUAHEMMLS7R/action/replication_record"}},"created_at":"2026-07-04T23:59:52.185494+00:00","updated_at":"2026-07-04T23:59:52.185494+00:00"}