{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:676DMMQMU5C4EI3QTWPON32V53","short_pith_number":"pith:676DMMQM","schema_version":"1.0","canonical_sha256":"f7fc36320ca745c223709d9ee6ef55eeec45dad67d509f8c61b4dc2f2ef90c48","source":{"kind":"arxiv","id":"1611.04273","version":2},"attestation_state":"computed","paper":{"title":"On the Quantitative Analysis of Decoder-Based Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Roger Grosse, Ruslan Salakhutdinov, Yuhuai Wu, Yuri Burda","submitted_at":"2016-11-14T07:36:22Z","abstract_excerpt":"The past several years have seen remarkable progress in generative models which produce convincing samples of images and other modalities. A shared component of many powerful generative models is a decoder network, a parametric deep neural net that defines a generative distribution. Examples include variational autoencoders, generative adversarial networks, and generative moment matching networks. Unfortunately, it can be difficult to quantify the performance of these models because of the intractability of log-likelihood estimation, and inspecting samples can be misleading. We propose to use "},"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":"1611.04273","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-14T07:36:22Z","cross_cats_sorted":[],"title_canon_sha256":"6bf1c9aa1a0e3b5d12922f2ee194eb15ecc3d59be824c8e485c96e6d6680531f","abstract_canon_sha256":"785278bf53f3661a87efe068fb663a198ff492e22d1ab16da844f7cd12d9eca7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:51.481598Z","signature_b64":"2UXSSxNYNf5OSbpDkZz1pHjqZ+qQPHXSvNK6bepB2YcWoiTwh7FzXTCkz6jjbpd38k8QQOB4sLOWNdVXZuhMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7fc36320ca745c223709d9ee6ef55eeec45dad67d509f8c61b4dc2f2ef90c48","last_reissued_at":"2026-05-18T00:42:51.480893Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:51.480893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Quantitative Analysis of Decoder-Based Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Roger Grosse, Ruslan Salakhutdinov, Yuhuai Wu, Yuri Burda","submitted_at":"2016-11-14T07:36:22Z","abstract_excerpt":"The past several years have seen remarkable progress in generative models which produce convincing samples of images and other modalities. A shared component of many powerful generative models is a decoder network, a parametric deep neural net that defines a generative distribution. Examples include variational autoencoders, generative adversarial networks, and generative moment matching networks. Unfortunately, it can be difficult to quantify the performance of these models because of the intractability of log-likelihood estimation, and inspecting samples can be misleading. We propose to use "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04273","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":"1611.04273","created_at":"2026-05-18T00:42:51.481020+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.04273v2","created_at":"2026-05-18T00:42:51.481020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04273","created_at":"2026-05-18T00:42:51.481020+00:00"},{"alias_kind":"pith_short_12","alias_value":"676DMMQMU5C4","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_16","alias_value":"676DMMQMU5C4EI3Q","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_8","alias_value":"676DMMQM","created_at":"2026-05-18T12:30:01.593930+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/676DMMQMU5C4EI3QTWPON32V53","json":"https://pith.science/pith/676DMMQMU5C4EI3QTWPON32V53.json","graph_json":"https://pith.science/api/pith-number/676DMMQMU5C4EI3QTWPON32V53/graph.json","events_json":"https://pith.science/api/pith-number/676DMMQMU5C4EI3QTWPON32V53/events.json","paper":"https://pith.science/paper/676DMMQM"},"agent_actions":{"view_html":"https://pith.science/pith/676DMMQMU5C4EI3QTWPON32V53","download_json":"https://pith.science/pith/676DMMQMU5C4EI3QTWPON32V53.json","view_paper":"https://pith.science/paper/676DMMQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.04273&json=true","fetch_graph":"https://pith.science/api/pith-number/676DMMQMU5C4EI3QTWPON32V53/graph.json","fetch_events":"https://pith.science/api/pith-number/676DMMQMU5C4EI3QTWPON32V53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/676DMMQMU5C4EI3QTWPON32V53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/676DMMQMU5C4EI3QTWPON32V53/action/storage_attestation","attest_author":"https://pith.science/pith/676DMMQMU5C4EI3QTWPON32V53/action/author_attestation","sign_citation":"https://pith.science/pith/676DMMQMU5C4EI3QTWPON32V53/action/citation_signature","submit_replication":"https://pith.science/pith/676DMMQMU5C4EI3QTWPON32V53/action/replication_record"}},"created_at":"2026-05-18T00:42:51.481020+00:00","updated_at":"2026-05-18T00:42:51.481020+00:00"}