{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:H5LAEGTJHOCAIOH3DC5LW4LFWI","short_pith_number":"pith:H5LAEGTJ","schema_version":"1.0","canonical_sha256":"3f56021a693b840438fb18babb7165b2161cdd43e818ac4f0f849cf9689ef9bc","source":{"kind":"arxiv","id":"1905.10485","version":2},"attestation_state":"computed","paper":{"title":"Generative Latent Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Qing Yan, Yali Amit, Zhisheng Xiao","submitted_at":"2019-05-24T23:44:50Z","abstract_excerpt":"In this work, we propose the Generative Latent Flow (GLF), an algorithm for generative modeling of the data distribution. GLF uses an Auto-encoder (AE) to learn latent representations of the data, and a normalizing flow to map the distribution of the latent variables to that of simple i.i.d noise. In contrast to some other Auto-encoder based generative models, which use various regularizers that encourage the encoded latent distribution to match the prior distribution, our model explicitly constructs a mapping between these two distributions, leading to better density matching while avoiding o"},"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":"1905.10485","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-24T23:44:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"555c5d0b5feef29c6ab9a745b54e248cb64f237ec543e3e69fbf64570fd29df9","abstract_canon_sha256":"4a854a02f5dd9aef5bf3e2af25d21a08944fd1f9b6b6f6f602ecf16820e11bd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:06:08.535579Z","signature_b64":"/YVFYP8AB1FFy9XUegqeGTkhM1XaElEO4bCNS0qpOqo466NS7jqnKFm+DcKqnulBTmA5j/j+h4tahdVtL3NqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f56021a693b840438fb18babb7165b2161cdd43e818ac4f0f849cf9689ef9bc","last_reissued_at":"2026-07-05T00:06:08.535040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:06:08.535040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Latent Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Qing Yan, Yali Amit, Zhisheng Xiao","submitted_at":"2019-05-24T23:44:50Z","abstract_excerpt":"In this work, we propose the Generative Latent Flow (GLF), an algorithm for generative modeling of the data distribution. GLF uses an Auto-encoder (AE) to learn latent representations of the data, and a normalizing flow to map the distribution of the latent variables to that of simple i.i.d noise. In contrast to some other Auto-encoder based generative models, which use various regularizers that encourage the encoded latent distribution to match the prior distribution, our model explicitly constructs a mapping between these two distributions, leading to better density matching while avoiding o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10485","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.10485/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":"1905.10485","created_at":"2026-07-05T00:06:08.535114+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10485v2","created_at":"2026-07-05T00:06:08.535114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10485","created_at":"2026-07-05T00:06:08.535114+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5LAEGTJHOCA","created_at":"2026-07-05T00:06:08.535114+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5LAEGTJHOCAIOH3","created_at":"2026-07-05T00:06:08.535114+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5LAEGTJ","created_at":"2026-07-05T00:06:08.535114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2303.01469","citing_title":"Consistency Models","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06701","citing_title":"Bi-Lipschitz Autoencoder With Injectivity Guarantee","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5LAEGTJHOCAIOH3DC5LW4LFWI","json":"https://pith.science/pith/H5LAEGTJHOCAIOH3DC5LW4LFWI.json","graph_json":"https://pith.science/api/pith-number/H5LAEGTJHOCAIOH3DC5LW4LFWI/graph.json","events_json":"https://pith.science/api/pith-number/H5LAEGTJHOCAIOH3DC5LW4LFWI/events.json","paper":"https://pith.science/paper/H5LAEGTJ"},"agent_actions":{"view_html":"https://pith.science/pith/H5LAEGTJHOCAIOH3DC5LW4LFWI","download_json":"https://pith.science/pith/H5LAEGTJHOCAIOH3DC5LW4LFWI.json","view_paper":"https://pith.science/paper/H5LAEGTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10485&json=true","fetch_graph":"https://pith.science/api/pith-number/H5LAEGTJHOCAIOH3DC5LW4LFWI/graph.json","fetch_events":"https://pith.science/api/pith-number/H5LAEGTJHOCAIOH3DC5LW4LFWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5LAEGTJHOCAIOH3DC5LW4LFWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5LAEGTJHOCAIOH3DC5LW4LFWI/action/storage_attestation","attest_author":"https://pith.science/pith/H5LAEGTJHOCAIOH3DC5LW4LFWI/action/author_attestation","sign_citation":"https://pith.science/pith/H5LAEGTJHOCAIOH3DC5LW4LFWI/action/citation_signature","submit_replication":"https://pith.science/pith/H5LAEGTJHOCAIOH3DC5LW4LFWI/action/replication_record"}},"created_at":"2026-07-05T00:06:08.535114+00:00","updated_at":"2026-07-05T00:06:08.535114+00:00"}