{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XAQ7EFX7QDJUDUMXNQMTLYSMZB","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":"f526b5bfb97699cf3a69be5c802436a816491fb7b23e465ce3797080278bfde2","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T16:25:07Z","title_canon_sha256":"a905690ea1cc12cea5083e9b8f7557d76145fd3808c533ac05b98748107ebfb1"},"schema_version":"1.0","source":{"id":"2606.06357","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06357","created_at":"2026-06-05T01:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06357v1","created_at":"2026-06-05T01:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06357","created_at":"2026-06-05T01:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"XAQ7EFX7QDJU","created_at":"2026-06-05T01:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"XAQ7EFX7QDJUDUMX","created_at":"2026-06-05T01:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"XAQ7EFX7","created_at":"2026-06-05T01:15:42Z"}],"graph_snapshots":[{"event_id":"sha256:f958801e9eda5e1ce9ef182e6dc5dd38c58ad3ace09d58b2b083d4709010335c","target":"graph","created_at":"2026-06-05T01:15:42Z","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/2606.06357/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continuous audio autoencoders reconstruct waveforms well but often produce latents with weak structure for understanding, while self-supervised audio encoders capture semantics but are not directly decodable. This mismatch complicates a single audio tokenizer that must support both understanding and generation. We adapt continuous autoencoder latents to this setting with two components: a noise-regularized autoencoder bottleneck and a latent-side representation encoder. The bottleneck uses channel normalization and stochastic perturbation instead of KL-based variational training, yielding scal","authors_text":"Dinghao Zhou, Di Wu, Pengyu Cheng, Shengfan Shen, Sixiang Lv, Xingchen Song","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T16:25:07Z","title":"F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06357","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":"sha256:884296c2e0ed20cf8a83d659e72fe68a23ddeea9c7d646d80e472e137651f1a2","target":"record","created_at":"2026-06-05T01:15:42Z","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":"f526b5bfb97699cf3a69be5c802436a816491fb7b23e465ce3797080278bfde2","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T16:25:07Z","title_canon_sha256":"a905690ea1cc12cea5083e9b8f7557d76145fd3808c533ac05b98748107ebfb1"},"schema_version":"1.0","source":{"id":"2606.06357","kind":"arxiv","version":1}},"canonical_sha256":"b821f216ff80d341d1976c1935e24cc848e5363c428bc7e0bdf145814dd37820","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b821f216ff80d341d1976c1935e24cc848e5363c428bc7e0bdf145814dd37820","first_computed_at":"2026-06-05T01:15:42.669116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:42.669116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hDcszrBoHt3uV+rGlAK8XBOM2UTSyJzOdg/N15lwoOtSQRw9/jO4Kq4Uj1lPmO7FASR4WyGQLSXZ0btdBA6kCw==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:42.669529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06357","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:884296c2e0ed20cf8a83d659e72fe68a23ddeea9c7d646d80e472e137651f1a2","sha256:f958801e9eda5e1ce9ef182e6dc5dd38c58ad3ace09d58b2b083d4709010335c"],"state_sha256":"9d103c9fd0e7c9906bb63704c043c90f11235c2bad3baa2913c4c901678fc4fe"}