{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KZBPYHA2OLLVJAJVQB2FLFX3IA","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":"a60dfb1ccac364c17e4517d7db13c058574ee65d2735220de49fd84e8c2f1f9e","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-27T01:56:45Z","title_canon_sha256":"d0df9d32e5cb2de4f21a6c6342b413556c1b21414195f821a9922471a908a22a"},"schema_version":"1.0","source":{"id":"2605.27840","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27840","created_at":"2026-05-28T01:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27840v1","created_at":"2026-05-28T01:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27840","created_at":"2026-05-28T01:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"KZBPYHA2OLLV","created_at":"2026-05-28T01:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"KZBPYHA2OLLVJAJV","created_at":"2026-05-28T01:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"KZBPYHA2","created_at":"2026-05-28T01:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:e82b83d3a363ac154e947c556c740396d4ce4264dd558345b534c4dffa1679fc","target":"graph","created_at":"2026-05-28T01:04:50Z","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/2605.27840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio tokenizers are fundamental to unifying audio understanding and generation. Understanding requires high-level semantics, while generation demands semantic and acoustic details. Existing unified tokenizers jointly encode both in high-dimensional continuous latents, which increases the modeling burden of Diffusion Transformers (DiTs) for generation. We propose LoSATok, a low-dimensional audio tokenizer for cross-domain audio understanding and generation. Motivated by the observation that 1280-dimensional semantic encoder features are compressible, we introduce a Semantic Bottleneck that com","authors_text":"Guoyang Zeng, Jing Peng, Xiang Li, Yixuan Zhou, Zhisheng Zhang, Zhiyong Wu","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-27T01:56:45Z","title":"LoSATok: Low-dimensional Semantic-Acoustic Tokenizer for Cross-Domain Audio Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27840","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":"sha256:1bf7766db03a9b5598c37a808b3717edcfa305c8fab4fd4a2b7afa7b87aecd3c","target":"record","created_at":"2026-05-28T01:04:50Z","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":"a60dfb1ccac364c17e4517d7db13c058574ee65d2735220de49fd84e8c2f1f9e","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-27T01:56:45Z","title_canon_sha256":"d0df9d32e5cb2de4f21a6c6342b413556c1b21414195f821a9922471a908a22a"},"schema_version":"1.0","source":{"id":"2605.27840","kind":"arxiv","version":1}},"canonical_sha256":"5642fc1c1a72d754813580745596fb400d09b46053f0334af18d557e97954a24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5642fc1c1a72d754813580745596fb400d09b46053f0334af18d557e97954a24","first_computed_at":"2026-05-28T01:04:50.112564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:50.112564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dgFcWQFIoM3XTvSv9qGCE07BM7z8ISqTwo7FRPf6T+HE9taUGSuAisGGeDKc2NVVY/ghuI6p8jkGQHmy9jTwAA==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:50.112928Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27840","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bf7766db03a9b5598c37a808b3717edcfa305c8fab4fd4a2b7afa7b87aecd3c","sha256:e82b83d3a363ac154e947c556c740396d4ce4264dd558345b534c4dffa1679fc"],"state_sha256":"40cffbda899a2e74d1fd4ee554acae3c47ed0602e56ba03f40bf7af696b507a5"}