{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7VRT3DTQAIH2CHSGKV5DLLQFJ4","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":"78ce1077b55065962769f0f4fbdc0225135127c31225972c5538f2a76a6b8a15","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-07T19:02:34Z","title_canon_sha256":"808df289e68577d6085c18260e512c4e66982a6a3503864ed00f5ec118e62191"},"schema_version":"1.0","source":{"id":"2212.03905","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.03905","created_at":"2026-07-05T06:42:03Z"},{"alias_kind":"arxiv_version","alias_value":"2212.03905v2","created_at":"2026-07-05T06:42:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03905","created_at":"2026-07-05T06:42:03Z"},{"alias_kind":"pith_short_12","alias_value":"7VRT3DTQAIH2","created_at":"2026-07-05T06:42:03Z"},{"alias_kind":"pith_short_16","alias_value":"7VRT3DTQAIH2CHSG","created_at":"2026-07-05T06:42:03Z"},{"alias_kind":"pith_short_8","alias_value":"7VRT3DTQ","created_at":"2026-07-05T06:42:03Z"}],"graph_snapshots":[{"event_id":"sha256:7263d613a6999c8901ade632dfa0080d9ca34c7938391612dd0641b96192a223","target":"graph","created_at":"2026-07-05T06:42:03Z","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/2212.03905/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Variational autoencoders (VAEs) are powerful tools for learning latent representations of data used in a wide range of applications. In practice, VAEs usually require multiple training rounds to choose the amount of information the latent variable should retain. This trade-off between the reconstruction error (distortion) and the KL divergence (rate) is typically parameterized by a hyperparameter $\\beta$. In this paper, we introduce Multi-Rate VAE (MR-VAE), a computationally efficient framework for learning optimal parameters corresponding to various $\\beta$ in a single training run. The key i","authors_text":"Eric Wang, Jimmy Ba, Juhan Bae, Michael Ruan, Michael R. Zhang, Roger Grosse, So Hasegawa","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-07T19:02:34Z","title":"Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03905","kind":"arxiv","version":2},"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":"sha256:3aba83373b87569e3416e1028bfbb14e72c053dae3c7c6343c189ae38f5da55e","target":"record","created_at":"2026-07-05T06:42:03Z","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":"78ce1077b55065962769f0f4fbdc0225135127c31225972c5538f2a76a6b8a15","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-07T19:02:34Z","title_canon_sha256":"808df289e68577d6085c18260e512c4e66982a6a3503864ed00f5ec118e62191"},"schema_version":"1.0","source":{"id":"2212.03905","kind":"arxiv","version":2}},"canonical_sha256":"fd633d8e70020fa11e46557a35ae054f0f6cabaee8697726025b841bcbf574b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd633d8e70020fa11e46557a35ae054f0f6cabaee8697726025b841bcbf574b8","first_computed_at":"2026-07-05T06:42:03.166264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:03.166264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4pIK94vvCnJg3wm+/Ua/+6vTpG+iwkpY4+ZM08nOV7hCRk25qYv7iO+iZjwiUQZTzEtr4o3C9kjW5Z0lWPKTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:03.166704Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.03905","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3aba83373b87569e3416e1028bfbb14e72c053dae3c7c6343c189ae38f5da55e","sha256:7263d613a6999c8901ade632dfa0080d9ca34c7938391612dd0641b96192a223"],"state_sha256":"25ef3915b8eb96cc3b8f89fcd9f77893619898e0200da17a885a3f4ec92c64d6"}