{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SXLICWPKVYGFFCKJNUV7MGUFLB","short_pith_number":"pith:SXLICWPK","schema_version":"1.0","canonical_sha256":"95d68159eaae0c5289496d2bf61a85584dbfa1e4997f961df611fd54e269efcc","source":{"kind":"arxiv","id":"2607.11738","version":1},"attestation_state":"computed","paper":{"title":"Qwen-Audio-VAE Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chenfei Wu, Dake Guo, Dayiheng Liu, Hangrui Hu, Jiapeng Wang, Jin Xu, Ting He, Wenxiang Guo, Xinfa Zhu, Xiong Wang, Yongqi Wang, Zekai Zhang, Zhifang Guo, Ziyue Jiang","submitted_at":"2026-07-13T16:00:03Z","abstract_excerpt":"We introduce \\textbf{Qwen-Audio-VAE}, a suite of low-bitrate, fast-encoding continuous audio autoencoders designed for scalable general audio generation. The model is built around a simple but important principle: an audio VAE should not only reconstruct diverse audio with high fidelity, but also produce compact latent representations fast enough to support large-scale text-to-audio training. Qwen-Audio-VAE combines a causal encoder-decoder, window Transformer blocks, and multi-discriminator training to achieve a strong balance between reconstruction quality and compression rate. The model is "},"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":"2607.11738","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-13T16:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"962573073f014339bb77d8bc05593e878d7a8528d70580190190af24e3de0ffc","abstract_canon_sha256":"2f5cc212c785aed0be30026f36ce87f12e728fc8bf2057b91004600c26b89b3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T02:22:22.159895Z","signature_b64":"dqlejuYLTkojNDfdyUWx6EwJMuvFQXea8jt+vA1L/4Qx+SOHvd+327xxC+KAoQWqxbHC4LUwspqCWVnhR+ZbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95d68159eaae0c5289496d2bf61a85584dbfa1e4997f961df611fd54e269efcc","last_reissued_at":"2026-07-14T02:22:22.159005Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T02:22:22.159005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Qwen-Audio-VAE Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chenfei Wu, Dake Guo, Dayiheng Liu, Hangrui Hu, Jiapeng Wang, Jin Xu, Ting He, Wenxiang Guo, Xinfa Zhu, Xiong Wang, Yongqi Wang, Zekai Zhang, Zhifang Guo, Ziyue Jiang","submitted_at":"2026-07-13T16:00:03Z","abstract_excerpt":"We introduce \\textbf{Qwen-Audio-VAE}, a suite of low-bitrate, fast-encoding continuous audio autoencoders designed for scalable general audio generation. The model is built around a simple but important principle: an audio VAE should not only reconstruct diverse audio with high fidelity, but also produce compact latent representations fast enough to support large-scale text-to-audio training. Qwen-Audio-VAE combines a causal encoder-decoder, window Transformer blocks, and multi-discriminator training to achieve a strong balance between reconstruction quality and compression rate. The model is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11738","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/2607.11738/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":"2607.11738","created_at":"2026-07-14T02:22:22.159457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11738v1","created_at":"2026-07-14T02:22:22.159457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11738","created_at":"2026-07-14T02:22:22.159457+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXLICWPKVYGF","created_at":"2026-07-14T02:22:22.159457+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXLICWPKVYGFFCKJ","created_at":"2026-07-14T02:22:22.159457+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXLICWPK","created_at":"2026-07-14T02:22:22.159457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05798","citing_title":"KVAE: Family of Tokenizers for Multimodal Generative Models","ref_index":71,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SXLICWPKVYGFFCKJNUV7MGUFLB","json":"https://pith.science/pith/SXLICWPKVYGFFCKJNUV7MGUFLB.json","graph_json":"https://pith.science/api/pith-number/SXLICWPKVYGFFCKJNUV7MGUFLB/graph.json","events_json":"https://pith.science/api/pith-number/SXLICWPKVYGFFCKJNUV7MGUFLB/events.json","paper":"https://pith.science/paper/SXLICWPK"},"agent_actions":{"view_html":"https://pith.science/pith/SXLICWPKVYGFFCKJNUV7MGUFLB","download_json":"https://pith.science/pith/SXLICWPKVYGFFCKJNUV7MGUFLB.json","view_paper":"https://pith.science/paper/SXLICWPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11738&json=true","fetch_graph":"https://pith.science/api/pith-number/SXLICWPKVYGFFCKJNUV7MGUFLB/graph.json","fetch_events":"https://pith.science/api/pith-number/SXLICWPKVYGFFCKJNUV7MGUFLB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXLICWPKVYGFFCKJNUV7MGUFLB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXLICWPKVYGFFCKJNUV7MGUFLB/action/storage_attestation","attest_author":"https://pith.science/pith/SXLICWPKVYGFFCKJNUV7MGUFLB/action/author_attestation","sign_citation":"https://pith.science/pith/SXLICWPKVYGFFCKJNUV7MGUFLB/action/citation_signature","submit_replication":"https://pith.science/pith/SXLICWPKVYGFFCKJNUV7MGUFLB/action/replication_record"}},"created_at":"2026-07-14T02:22:22.159457+00:00","updated_at":"2026-07-14T02:22:22.159457+00:00"}