{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JO2FEZP3NIKJXCRUT7AFECXQR5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a31f688533afe591bf9956efb6795668dc33f853d2a2634f11be6e46bb80c229","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-05T15:14:18Z","title_canon_sha256":"6964fc4c03beaa8c88b44919ef3590ff118724d446c6aab1f84b105ffe9e8498"},"schema_version":"1.0","source":{"id":"1908.01686","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01686","created_at":"2026-07-05T03:51:53Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01686v3","created_at":"2026-07-05T03:51:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01686","created_at":"2026-07-05T03:51:53Z"},{"alias_kind":"pith_short_12","alias_value":"JO2FEZP3NIKJ","created_at":"2026-07-05T03:51:53Z"},{"alias_kind":"pith_short_16","alias_value":"JO2FEZP3NIKJXCRU","created_at":"2026-07-05T03:51:53Z"},{"alias_kind":"pith_short_8","alias_value":"JO2FEZP3","created_at":"2026-07-05T03:51:53Z"}],"graph_snapshots":[{"event_id":"sha256:314a24bdcd0a35096978af0b83dd73a1539745efcabb63bf918bd61efb3fea1b","target":"graph","created_at":"2026-07-05T03:51:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.01686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep generative modeling using flows has gained popularity owing to the tractable exact log-likelihood estimation with efficient training and synthesis process. However, flow models suffer from the challenge of having high dimensional latent space, the same in dimension as the input space. An effective solution to the above challenge as proposed by Dinh et al. (2016) is a multi-scale architecture, which is based on iterative early factorization of a part of the total dimensions at regular intervals. Prior works on generative flow models involving a multi-scale architecture perform the dimensio","authors_text":"Costas J. Spanos, Hari Prasanna Das, Pieter Abbeel","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01686","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a94f1a39dd08aaa298ff5fab99b501567874bc07ed407e4cd520a0aa5f09d296","target":"record","created_at":"2026-07-05T03:51:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a31f688533afe591bf9956efb6795668dc33f853d2a2634f11be6e46bb80c229","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-05T15:14:18Z","title_canon_sha256":"6964fc4c03beaa8c88b44919ef3590ff118724d446c6aab1f84b105ffe9e8498"},"schema_version":"1.0","source":{"id":"1908.01686","kind":"arxiv","version":3}},"canonical_sha256":"4bb45265fb6a149b8a349fc0520af08f79d0ed333bfce3c3e2bd5fe1dcd17d29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bb45265fb6a149b8a349fc0520af08f79d0ed333bfce3c3e2bd5fe1dcd17d29","first_computed_at":"2026-07-05T03:51:53.104097Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:51:53.104097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YCjPNuZWwYMj2+Kl2aCIQyI3cfkcT0nFqPXbAfF2In+nfu7Q6jXJe6pYV2YrSZzd9LIWymx9XpMZ8Wp0tZ56Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:51:53.104537Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.01686","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a94f1a39dd08aaa298ff5fab99b501567874bc07ed407e4cd520a0aa5f09d296","sha256:314a24bdcd0a35096978af0b83dd73a1539745efcabb63bf918bd61efb3fea1b"],"state_sha256":"cb1db26c64bbe5c521854867d37554db1b0c58787fbda107e09516d774559450"}