{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3MJKYDYLQYQAT5PI6QDZPAO27B","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":"0baf67bd7ae88aa38d36cf74d3ae721075825598f0e79044f0851034244b0020","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-16T17:01:47Z","title_canon_sha256":"50f49c1db03eccedab8db1cc67f6a7f337845936a6a87d53650ec3856fc029d4"},"schema_version":"1.0","source":{"id":"2605.17085","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17085","created_at":"2026-05-20T00:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17085v1","created_at":"2026-05-20T00:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17085","created_at":"2026-05-20T00:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"3MJKYDYLQYQA","created_at":"2026-05-20T00:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"3MJKYDYLQYQAT5PI","created_at":"2026-05-20T00:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"3MJKYDYL","created_at":"2026-05-20T00:03:39Z"}],"graph_snapshots":[{"event_id":"sha256:bf5801e322b869341a844c3a98bea8c083ad8e95f8222a604aface894a109802","target":"graph","created_at":"2026-05-20T00:03:39Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.805409Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:21:57.741338Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17085/integrity.json","findings":[],"snapshot_sha256":"3def90c7e0a17907b3e874546a49d941b92d488646a2f9ce737ee73a39fa007c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Latent diffusion models have emerged as the dominant paradigm for many generation tasks including audio generation such as text-to-audio, text-to-music and text-to-speech. A key component of latent diffusion is an autoencoder (VAE) that compresses high-dimensional signals into a low frame rate continuous representation that is conducive for downstream prediction. Regularizing these VAEs is challenging, as there is a trade-off between over-regularized (poor output quality) and under-regularized (difficult to predict) latent representations. We propose a framework for studying this trade-off thr","authors_text":"Prem Seetharaman, Rithesh Kumar","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-16T17:01:47Z","title":"Taming Audio VAEs via Target-KL Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17085","kind":"arxiv","version":1},"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":"sha256:8308cd79c81fbec9a83508a0968efc4a48b8078d142c50044e6a209457da2446","target":"record","created_at":"2026-05-20T00:03:39Z","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":"0baf67bd7ae88aa38d36cf74d3ae721075825598f0e79044f0851034244b0020","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-16T17:01:47Z","title_canon_sha256":"50f49c1db03eccedab8db1cc67f6a7f337845936a6a87d53650ec3856fc029d4"},"schema_version":"1.0","source":{"id":"2605.17085","kind":"arxiv","version":1}},"canonical_sha256":"db12ac0f0b862009f5e8f4079781daf8483c6abdb599244e05be629250e2bf7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db12ac0f0b862009f5e8f4079781daf8483c6abdb599244e05be629250e2bf7f","first_computed_at":"2026-05-20T00:03:39.591736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:39.591736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LNPpoJcDw2VpGsP+xlR/C31JqImkPc/4Rvn/OysQMKNf27h0dggZVnL6SBu2SKbyABi6MURBm4oMp+0pqEx/DQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:39.592307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17085","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8308cd79c81fbec9a83508a0968efc4a48b8078d142c50044e6a209457da2446","sha256:bf5801e322b869341a844c3a98bea8c083ad8e95f8222a604aface894a109802"],"state_sha256":"a40c89f40b557bef39421853ad49eefa41ea303e4fe6f9bd0b8999104c12fb8d"}