{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XAQ7EFX7QDJUDUMXNQMTLYSMZB","short_pith_number":"pith:XAQ7EFX7","schema_version":"1.0","canonical_sha256":"b821f216ff80d341d1976c1935e24cc848e5363c428bc7e0bdf145814dd37820","source":{"kind":"arxiv","id":"2606.06357","version":1},"attestation_state":"computed","paper":{"title":"F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dinghao Zhou, Di Wu, Pengyu Cheng, Shengfan Shen, Sixiang Lv, Xingchen Song","submitted_at":"2026-06-04T16:25:07Z","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"},"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":"2606.06357","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T16:25:07Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"a905690ea1cc12cea5083e9b8f7557d76145fd3808c533ac05b98748107ebfb1","abstract_canon_sha256":"f526b5bfb97699cf3a69be5c802436a816491fb7b23e465ce3797080278bfde2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:42.669529Z","signature_b64":"hDcszrBoHt3uV+rGlAK8XBOM2UTSyJzOdg/N15lwoOtSQRw9/jO4Kq4Uj1lPmO7FASR4WyGQLSXZ0btdBA6kCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b821f216ff80d341d1976c1935e24cc848e5363c428bc7e0bdf145814dd37820","last_reissued_at":"2026-06-05T01:15:42.669116Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:42.669116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dinghao Zhou, Di Wu, Pengyu Cheng, Shengfan Shen, Sixiang Lv, Xingchen Song","submitted_at":"2026-06-04T16:25:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06357","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/2606.06357/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":"2606.06357","created_at":"2026-06-05T01:15:42.669176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06357v1","created_at":"2026-06-05T01:15:42.669176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06357","created_at":"2026-06-05T01:15:42.669176+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAQ7EFX7QDJU","created_at":"2026-06-05T01:15:42.669176+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAQ7EFX7QDJUDUMX","created_at":"2026-06-05T01:15:42.669176+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAQ7EFX7","created_at":"2026-06-05T01:15:42.669176+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/XAQ7EFX7QDJUDUMXNQMTLYSMZB","json":"https://pith.science/pith/XAQ7EFX7QDJUDUMXNQMTLYSMZB.json","graph_json":"https://pith.science/api/pith-number/XAQ7EFX7QDJUDUMXNQMTLYSMZB/graph.json","events_json":"https://pith.science/api/pith-number/XAQ7EFX7QDJUDUMXNQMTLYSMZB/events.json","paper":"https://pith.science/paper/XAQ7EFX7"},"agent_actions":{"view_html":"https://pith.science/pith/XAQ7EFX7QDJUDUMXNQMTLYSMZB","download_json":"https://pith.science/pith/XAQ7EFX7QDJUDUMXNQMTLYSMZB.json","view_paper":"https://pith.science/paper/XAQ7EFX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06357&json=true","fetch_graph":"https://pith.science/api/pith-number/XAQ7EFX7QDJUDUMXNQMTLYSMZB/graph.json","fetch_events":"https://pith.science/api/pith-number/XAQ7EFX7QDJUDUMXNQMTLYSMZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAQ7EFX7QDJUDUMXNQMTLYSMZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAQ7EFX7QDJUDUMXNQMTLYSMZB/action/storage_attestation","attest_author":"https://pith.science/pith/XAQ7EFX7QDJUDUMXNQMTLYSMZB/action/author_attestation","sign_citation":"https://pith.science/pith/XAQ7EFX7QDJUDUMXNQMTLYSMZB/action/citation_signature","submit_replication":"https://pith.science/pith/XAQ7EFX7QDJUDUMXNQMTLYSMZB/action/replication_record"}},"created_at":"2026-06-05T01:15:42.669176+00:00","updated_at":"2026-06-05T01:15:42.669176+00:00"}