{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LQGAUFLUJAESM72Q2ZM3L3BJBC","short_pith_number":"pith:LQGAUFLU","schema_version":"1.0","canonical_sha256":"5c0c0a15744809267f50d659b5ec29089c0648022a40239b1a02add3cc0d355b","source":{"kind":"arxiv","id":"1901.11137","version":3},"attestation_state":"computed","paper":{"title":"Emerging Convolutions for Generative Normalizing Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Emiel Hoogeboom, Max Welling, Rianne van den Berg","submitted_at":"2019-01-30T23:02:37Z","abstract_excerpt":"Generative flows are attractive because they admit exact likelihood optimization and efficient image synthesis. Recently, Kingma & Dhariwal (2018) demonstrated with Glow that generative flows are capable of generating high quality images. We generalize the 1 x 1 convolutions proposed in Glow to invertible d x d convolutions, which are more flexible since they operate on both channel and spatial axes. We propose two methods to produce invertible convolutions that have receptive fields identical to standard convolutions: Emerging convolutions are obtained by chaining specific autoregressive conv"},"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":"1901.11137","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T23:02:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bf021367b5d732da95eb31af1053ddd8082c3e27c9865deeceba480e961d3089","abstract_canon_sha256":"5506db853cbe8a931dfdddd9b3f4641d62fd143619beacac127c3c0e99fca599"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:52.186975Z","signature_b64":"raau+0QUSM6VMPeit3MHI+MNd7tIHYsY3u2PVDuOyYkieaS040y9H+e79kBFzopuvrxae0+nh8MVt/uhR8mYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c0c0a15744809267f50d659b5ec29089c0648022a40239b1a02add3cc0d355b","last_reissued_at":"2026-05-17T23:45:52.186498Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:52.186498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emerging Convolutions for Generative Normalizing Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Emiel Hoogeboom, Max Welling, Rianne van den Berg","submitted_at":"2019-01-30T23:02:37Z","abstract_excerpt":"Generative flows are attractive because they admit exact likelihood optimization and efficient image synthesis. Recently, Kingma & Dhariwal (2018) demonstrated with Glow that generative flows are capable of generating high quality images. We generalize the 1 x 1 convolutions proposed in Glow to invertible d x d convolutions, which are more flexible since they operate on both channel and spatial axes. We propose two methods to produce invertible convolutions that have receptive fields identical to standard convolutions: Emerging convolutions are obtained by chaining specific autoregressive conv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11137","kind":"arxiv","version":3},"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":"1901.11137","created_at":"2026-05-17T23:45:52.186561+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.11137v3","created_at":"2026-05-17T23:45:52.186561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11137","created_at":"2026-05-17T23:45:52.186561+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQGAUFLUJAES","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQGAUFLUJAESM72Q","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQGAUFLU","created_at":"2026-05-18T12:33:21.387695+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/LQGAUFLUJAESM72Q2ZM3L3BJBC","json":"https://pith.science/pith/LQGAUFLUJAESM72Q2ZM3L3BJBC.json","graph_json":"https://pith.science/api/pith-number/LQGAUFLUJAESM72Q2ZM3L3BJBC/graph.json","events_json":"https://pith.science/api/pith-number/LQGAUFLUJAESM72Q2ZM3L3BJBC/events.json","paper":"https://pith.science/paper/LQGAUFLU"},"agent_actions":{"view_html":"https://pith.science/pith/LQGAUFLUJAESM72Q2ZM3L3BJBC","download_json":"https://pith.science/pith/LQGAUFLUJAESM72Q2ZM3L3BJBC.json","view_paper":"https://pith.science/paper/LQGAUFLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.11137&json=true","fetch_graph":"https://pith.science/api/pith-number/LQGAUFLUJAESM72Q2ZM3L3BJBC/graph.json","fetch_events":"https://pith.science/api/pith-number/LQGAUFLUJAESM72Q2ZM3L3BJBC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQGAUFLUJAESM72Q2ZM3L3BJBC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQGAUFLUJAESM72Q2ZM3L3BJBC/action/storage_attestation","attest_author":"https://pith.science/pith/LQGAUFLUJAESM72Q2ZM3L3BJBC/action/author_attestation","sign_citation":"https://pith.science/pith/LQGAUFLUJAESM72Q2ZM3L3BJBC/action/citation_signature","submit_replication":"https://pith.science/pith/LQGAUFLUJAESM72Q2ZM3L3BJBC/action/replication_record"}},"created_at":"2026-05-17T23:45:52.186561+00:00","updated_at":"2026-05-17T23:45:52.186561+00:00"}