{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TX6SNWHMKGCDG5SLNVQEQ2MFO4","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":"3d2f1cbc32fbb2bbd50caf9b5a1771674e979668174b528e6cb447f8fedee3ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-14T08:28:48Z","title_canon_sha256":"15327de3d2cc09bb82e3f6e1202aaa2b7662717ed22db045bf1a11ac790cc86f"},"schema_version":"1.0","source":{"id":"2607.12496","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.12496","created_at":"2026-07-15T01:21:38Z"},{"alias_kind":"arxiv_version","alias_value":"2607.12496v1","created_at":"2026-07-15T01:21:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12496","created_at":"2026-07-15T01:21:38Z"},{"alias_kind":"pith_short_12","alias_value":"TX6SNWHMKGCD","created_at":"2026-07-15T01:21:38Z"},{"alias_kind":"pith_short_16","alias_value":"TX6SNWHMKGCDG5SL","created_at":"2026-07-15T01:21:38Z"},{"alias_kind":"pith_short_8","alias_value":"TX6SNWHM","created_at":"2026-07-15T01:21:38Z"}],"graph_snapshots":[{"event_id":"sha256:157a1ed5f7058ed195a98f18119f2332155cfaf142be9c9b76b3b643bc072fb8","target":"graph","created_at":"2026-07-15T01:21:38Z","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/2607.12496/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot dialog TTS benefits from flow-matching, but minute-scale generation on dense mel-spectrograms causes severe memory bottlenecks, often forcing unnatural chunked synthesis. We propose ZipL-Dialog, which shifts conditional flow-matching into a 4x time-compressed (25 Hz) latent space. To preserve acoustic fidelity under compression, we employ a deterministic mel autoencoder with auxiliary mel-domain supervision and optimize the ZipFormer's hierarchical downsampling schedule. Experiments show that ZipL-Dialog reduces maximum peak GPU memory by 11.22x and accelerates inference by 2.23x ove","authors_text":"Jihwan Kim, Nam Soo Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-14T08:28:48Z","title":"ZipL-Dialog: Memory-Efficient Long-Form Spoken Dialog Synthesis via Latent Flow Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12496","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:b4e90fe575560d14454fe546a60fbadde3fc04257bbd05c6a88402ea8f56ef4d","target":"record","created_at":"2026-07-15T01:21:38Z","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":"3d2f1cbc32fbb2bbd50caf9b5a1771674e979668174b528e6cb447f8fedee3ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-14T08:28:48Z","title_canon_sha256":"15327de3d2cc09bb82e3f6e1202aaa2b7662717ed22db045bf1a11ac790cc86f"},"schema_version":"1.0","source":{"id":"2607.12496","kind":"arxiv","version":1}},"canonical_sha256":"9dfd26d8ec518433764b6d604869857703d4bff552720422ed15a99719750fec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dfd26d8ec518433764b6d604869857703d4bff552720422ed15a99719750fec","first_computed_at":"2026-07-15T01:21:38.094087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-15T01:21:38.094087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dUT5nwUGxLPOyLbI+hdjQfqr9Erd/6uuQErx+wFt9Sd7P8Rgsq6CnqRhixrBbi+1P7mxDDwdd+z2A+ZHeyMOBQ==","signature_status":"signed_v1","signed_at":"2026-07-15T01:21:38.095028Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.12496","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4e90fe575560d14454fe546a60fbadde3fc04257bbd05c6a88402ea8f56ef4d","sha256:157a1ed5f7058ed195a98f18119f2332155cfaf142be9c9b76b3b643bc072fb8"],"state_sha256":"d4a470d6d5c8cbe26f2cf74863104d032118194a0bcaecbe0f052eba2b75d781"}