{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JHBN3UEOKPGRXTP5UQTCIH6QDR","short_pith_number":"pith:JHBN3UEO","schema_version":"1.0","canonical_sha256":"49c2ddd08e53cd1bcdfda426241fd01c469a5fe0cd2da39288ce77b3b720329f","source":{"kind":"arxiv","id":"2608.08667","version":1},"attestation_state":"computed","paper":{"title":"A Unifying Perspective on Audio Generative Modeling: Latent Representations and Modeling Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Dongchao Yang","submitted_at":"2026-08-09T12:21:54Z","abstract_excerpt":"Every audio generative system makes two coupled decisions: what representation to generate, and how to model its distribution. This paper organizes audio generative modeling around this coupling. For representation design, we compare discrete, continuous, and hybrid latents through four objectives: representation burden, distortion, empirical modelability, and streaming compatibility. For distribution modeling, rather than treating a latent's difficulty as an intrinsic scalar, we use two diagnostic dimensions: dependency horizon, how far useful context extends, and conditional ambiguity, how m"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.08667","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-08-09T12:21:54Z","cross_cats_sorted":[],"title_canon_sha256":"172eba7039ec45415f07805007bba44ac9c8451fb97d6e2172d807dce2598e9d","abstract_canon_sha256":"9efaf09aa9e7caaff15ece17ab39534d7863aa6ae2f2f17dc5070d5289dbe56a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:23:24.470174Z","signature_b64":"0BdPyk8XuykG2yREM1JMLERKzUXLS/KeHG5Wnl97YO+OHWZt4rtEXr88f2FPpgip4BTi6Jly5zoYsEvBv5pdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49c2ddd08e53cd1bcdfda426241fd01c469a5fe0cd2da39288ce77b3b720329f","last_reissued_at":"2026-08-11T01:23:24.467704Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:23:24.467704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unifying Perspective on Audio Generative Modeling: Latent Representations and Modeling Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Dongchao Yang","submitted_at":"2026-08-09T12:21:54Z","abstract_excerpt":"Every audio generative system makes two coupled decisions: what representation to generate, and how to model its distribution. This paper organizes audio generative modeling around this coupling. For representation design, we compare discrete, continuous, and hybrid latents through four objectives: representation burden, distortion, empirical modelability, and streaming compatibility. For distribution modeling, rather than treating a latent's difficulty as an intrinsic scalar, we use two diagnostic dimensions: dependency horizon, how far useful context extends, and conditional ambiguity, how m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08667","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.08667/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.08667","created_at":"2026-08-11T01:23:24.468532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08667v1","created_at":"2026-08-11T01:23:24.468532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08667","created_at":"2026-08-11T01:23:24.468532+00:00"},{"alias_kind":"pith_short_12","alias_value":"JHBN3UEOKPGR","created_at":"2026-08-11T01:23:24.468532+00:00"},{"alias_kind":"pith_short_16","alias_value":"JHBN3UEOKPGRXTP5","created_at":"2026-08-11T01:23:24.468532+00:00"},{"alias_kind":"pith_short_8","alias_value":"JHBN3UEO","created_at":"2026-08-11T01:23:24.468532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JHBN3UEOKPGRXTP5UQTCIH6QDR","json":"https://pith.science/pith/JHBN3UEOKPGRXTP5UQTCIH6QDR.json","graph_json":"https://pith.science/api/pith-number/JHBN3UEOKPGRXTP5UQTCIH6QDR/graph.json","events_json":"https://pith.science/api/pith-number/JHBN3UEOKPGRXTP5UQTCIH6QDR/events.json","paper":"https://pith.science/paper/JHBN3UEO"},"agent_actions":{"view_html":"https://pith.science/pith/JHBN3UEOKPGRXTP5UQTCIH6QDR","download_json":"https://pith.science/pith/JHBN3UEOKPGRXTP5UQTCIH6QDR.json","view_paper":"https://pith.science/paper/JHBN3UEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08667&json=true","fetch_graph":"https://pith.science/api/pith-number/JHBN3UEOKPGRXTP5UQTCIH6QDR/graph.json","fetch_events":"https://pith.science/api/pith-number/JHBN3UEOKPGRXTP5UQTCIH6QDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JHBN3UEOKPGRXTP5UQTCIH6QDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JHBN3UEOKPGRXTP5UQTCIH6QDR/action/storage_attestation","attest_author":"https://pith.science/pith/JHBN3UEOKPGRXTP5UQTCIH6QDR/action/author_attestation","sign_citation":"https://pith.science/pith/JHBN3UEOKPGRXTP5UQTCIH6QDR/action/citation_signature","submit_replication":"https://pith.science/pith/JHBN3UEOKPGRXTP5UQTCIH6QDR/action/replication_record"}},"created_at":"2026-08-11T01:23:24.468532+00:00","updated_at":"2026-08-11T01:23:24.468532+00:00"}