{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VJPQSGKQ7EFFWMFA4XHRWZNLJ2","short_pith_number":"pith:VJPQSGKQ","schema_version":"1.0","canonical_sha256":"aa5f091950f90a5b30a0e5cf1b65ab4ebc32667ded96d6bc876c0ffd9408ab42","source":{"kind":"arxiv","id":"2506.23325","version":2},"attestation_state":"computed","paper":{"title":"XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dong Zhang, Luozhijie Jin, Qinyuan Cheng, Ruifan Deng, Shimin Li, Xin Zhang, Xipeng Qiu, Yitian Gong, Zhaoye Fei","submitted_at":"2025-06-29T16:51:50Z","abstract_excerpt":"Speech codecs serve as bridges between speech signals and large language models. An ideal codec for speech language models should not only preserve acoustic information but also capture rich semantic information. However, existing speech codecs struggle to balance high-quality audio reconstruction with ease of modeling by language models. In this study, we analyze the limitations of previous codecs in balancing semantic richness and acoustic fidelity. We propose XY-Tokenizer, a novel codec that mitigates the conflict between semantic and acoustic capabilities through multi-stage, multi-task le"},"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":"2506.23325","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-29T16:51:50Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"d058b9b6525220254eab961d0ae8d6621ed6423655a1dfb9151f2cee7a43b37a","abstract_canon_sha256":"5052c0ac09df969094f617ff8be996dbc3080ed402536c003e76d62b71fa8c09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:10.198854Z","signature_b64":"wdjgiOqmNskydlgG4Fh/NeNxXXC6OqlebQc7URiEIe41Da8bOl3sxoFpfmMLwJoE93WZb+q2rd4LwzJaxOzmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa5f091950f90a5b30a0e5cf1b65ab4ebc32667ded96d6bc876c0ffd9408ab42","last_reissued_at":"2026-07-05T11:34:10.198402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:10.198402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dong Zhang, Luozhijie Jin, Qinyuan Cheng, Ruifan Deng, Shimin Li, Xin Zhang, Xipeng Qiu, Yitian Gong, Zhaoye Fei","submitted_at":"2025-06-29T16:51:50Z","abstract_excerpt":"Speech codecs serve as bridges between speech signals and large language models. An ideal codec for speech language models should not only preserve acoustic information but also capture rich semantic information. However, existing speech codecs struggle to balance high-quality audio reconstruction with ease of modeling by language models. In this study, we analyze the limitations of previous codecs in balancing semantic richness and acoustic fidelity. We propose XY-Tokenizer, a novel codec that mitigates the conflict between semantic and acoustic capabilities through multi-stage, multi-task le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23325","kind":"arxiv","version":2},"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/2506.23325/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":"2506.23325","created_at":"2026-07-05T11:34:10.198463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23325v2","created_at":"2026-07-05T11:34:10.198463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23325","created_at":"2026-07-05T11:34:10.198463+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJPQSGKQ7EFF","created_at":"2026-07-05T11:34:10.198463+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJPQSGKQ7EFFWMFA","created_at":"2026-07-05T11:34:10.198463+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJPQSGKQ","created_at":"2026-07-05T11:34:10.198463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07080","citing_title":"dots.tts Technical Report","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15621","citing_title":"Qwen3-TTS Technical Report","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08608","citing_title":"Reducing Linguistic Hallucination in LM-Based Speech Enhancement via Noise-Invariant Acoustic-Semantic Distillation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12145","citing_title":"Why Your Tokenizer Fails in Information Fusion: A Timing-Aware Pre-Quantization Fusion for Video-Enhanced Audio Tokenization","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06765","citing_title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJPQSGKQ7EFFWMFA4XHRWZNLJ2","json":"https://pith.science/pith/VJPQSGKQ7EFFWMFA4XHRWZNLJ2.json","graph_json":"https://pith.science/api/pith-number/VJPQSGKQ7EFFWMFA4XHRWZNLJ2/graph.json","events_json":"https://pith.science/api/pith-number/VJPQSGKQ7EFFWMFA4XHRWZNLJ2/events.json","paper":"https://pith.science/paper/VJPQSGKQ"},"agent_actions":{"view_html":"https://pith.science/pith/VJPQSGKQ7EFFWMFA4XHRWZNLJ2","download_json":"https://pith.science/pith/VJPQSGKQ7EFFWMFA4XHRWZNLJ2.json","view_paper":"https://pith.science/paper/VJPQSGKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23325&json=true","fetch_graph":"https://pith.science/api/pith-number/VJPQSGKQ7EFFWMFA4XHRWZNLJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/VJPQSGKQ7EFFWMFA4XHRWZNLJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJPQSGKQ7EFFWMFA4XHRWZNLJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJPQSGKQ7EFFWMFA4XHRWZNLJ2/action/storage_attestation","attest_author":"https://pith.science/pith/VJPQSGKQ7EFFWMFA4XHRWZNLJ2/action/author_attestation","sign_citation":"https://pith.science/pith/VJPQSGKQ7EFFWMFA4XHRWZNLJ2/action/citation_signature","submit_replication":"https://pith.science/pith/VJPQSGKQ7EFFWMFA4XHRWZNLJ2/action/replication_record"}},"created_at":"2026-07-05T11:34:10.198463+00:00","updated_at":"2026-07-05T11:34:10.198463+00:00"}