{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SUMVL234DN5LKU45D6A6T5KJ55","short_pith_number":"pith:SUMVL234","schema_version":"1.0","canonical_sha256":"951955eb7c1b7ab5539d1f81e9f549ef66cc9c66b7390b06105217822d8eddea","source":{"kind":"arxiv","id":"1706.00531","version":1},"attestation_state":"computed","paper":{"title":"PixelGAN Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alireza Makhzani, Brendan Frey","submitted_at":"2017-06-02T00:53:14Z","abstract_excerpt":"In this paper, we describe the \"PixelGAN autoencoder\", a generative autoencoder in which the generative path is a convolutional autoregressive neural network on pixels (PixelCNN) that is conditioned on a latent code, and the recognition path uses a generative adversarial network (GAN) to impose a prior distribution on the latent code. We show that different priors result in different decompositions of information between the latent code and the autoregressive decoder. For example, by imposing a Gaussian distribution as the prior, we can achieve a global vs. local decomposition, or by imposing "},"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":"1706.00531","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-02T00:53:14Z","cross_cats_sorted":[],"title_canon_sha256":"530690ecfd3319a7e120a0484fdaf563af34a9355a75900339e0517c8a33ff5a","abstract_canon_sha256":"f141771d9191a4fea3a8637f0358e1f25ecb305295038e11ea917f2790d1ee5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:12.762758Z","signature_b64":"vFWPHyEhWblOvDR98+e4cXgcAzlJnvgA+0+7S2jMx4xXYgAxTWhx3Tj56Dz6lNfEq1fjBIl+fz9KDF09OA44BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"951955eb7c1b7ab5539d1f81e9f549ef66cc9c66b7390b06105217822d8eddea","last_reissued_at":"2026-05-18T00:43:12.762082Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:12.762082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PixelGAN Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alireza Makhzani, Brendan Frey","submitted_at":"2017-06-02T00:53:14Z","abstract_excerpt":"In this paper, we describe the \"PixelGAN autoencoder\", a generative autoencoder in which the generative path is a convolutional autoregressive neural network on pixels (PixelCNN) that is conditioned on a latent code, and the recognition path uses a generative adversarial network (GAN) to impose a prior distribution on the latent code. We show that different priors result in different decompositions of information between the latent code and the autoregressive decoder. For example, by imposing a Gaussian distribution as the prior, we can achieve a global vs. local decomposition, or by imposing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00531","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":"1706.00531","created_at":"2026-05-18T00:43:12.762192+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.00531v1","created_at":"2026-05-18T00:43:12.762192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00531","created_at":"2026-05-18T00:43:12.762192+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUMVL234DN5L","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUMVL234DN5LKU45","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUMVL234","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1710.10196","citing_title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SUMVL234DN5LKU45D6A6T5KJ55","json":"https://pith.science/pith/SUMVL234DN5LKU45D6A6T5KJ55.json","graph_json":"https://pith.science/api/pith-number/SUMVL234DN5LKU45D6A6T5KJ55/graph.json","events_json":"https://pith.science/api/pith-number/SUMVL234DN5LKU45D6A6T5KJ55/events.json","paper":"https://pith.science/paper/SUMVL234"},"agent_actions":{"view_html":"https://pith.science/pith/SUMVL234DN5LKU45D6A6T5KJ55","download_json":"https://pith.science/pith/SUMVL234DN5LKU45D6A6T5KJ55.json","view_paper":"https://pith.science/paper/SUMVL234","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.00531&json=true","fetch_graph":"https://pith.science/api/pith-number/SUMVL234DN5LKU45D6A6T5KJ55/graph.json","fetch_events":"https://pith.science/api/pith-number/SUMVL234DN5LKU45D6A6T5KJ55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUMVL234DN5LKU45D6A6T5KJ55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUMVL234DN5LKU45D6A6T5KJ55/action/storage_attestation","attest_author":"https://pith.science/pith/SUMVL234DN5LKU45D6A6T5KJ55/action/author_attestation","sign_citation":"https://pith.science/pith/SUMVL234DN5LKU45D6A6T5KJ55/action/citation_signature","submit_replication":"https://pith.science/pith/SUMVL234DN5LKU45D6A6T5KJ55/action/replication_record"}},"created_at":"2026-05-18T00:43:12.762192+00:00","updated_at":"2026-05-18T00:43:12.762192+00:00"}