{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z23FHT2HC5ZN5JXFWT3NH7YK33","short_pith_number":"pith:Z23FHT2H","schema_version":"1.0","canonical_sha256":"ceb653cf471772dea6e5b4f6d3ff0adef2cb746e41449579dc8bf642cd646ea8","source":{"kind":"arxiv","id":"2607.06540","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Fanbo Meng, Haizhou Li, Haolan Chen, Minjun Zhao, Min Zhang, Qixun Teng, Shenyuan Jiang, Xuanyu Zhang, Yancheng He, Yunxin Li, Yu Xu, Zhenyu Liu","submitted_at":"2026-07-07T17:43:36Z","abstract_excerpt":"Developing seamless, high-performance, native intelligent full-duplex Spoken Language Models (SLMs) remains a critical challenge and long-standing goal for the speech and NLP community. Despite notable progress, recent endeavors are fundamentally constrained by severe modality interference, which causes substantial knowledge degradation and compromises semantic integrity -- ultimately making full-duplex SLMs feel unnatural and unintelligent. In this paper, through an exhaustive fine-grained analysis of model optimization dynamics, we uncover the root cause of such performance degradation, reve"},"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":"2607.06540","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-07T17:43:36Z","cross_cats_sorted":[],"title_canon_sha256":"f6dde983bffd0e5232045bb660d38d1edeb2434bf36fec43f7ec5ed2a1cb9087","abstract_canon_sha256":"5982b56444461ad7273f4419589151ccf080861689d95e908e2f720e8060a214"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:19:29.339042Z","signature_b64":"+oT2Fpre5Nca374qijWwebVUa4PbMdsmfjPpcNaXBo4xzGX0T9av9U8wjgu/Wg93eOUDxmmoxoBX6OZchUOzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceb653cf471772dea6e5b4f6d3ff0adef2cb746e41449579dc8bf642cd646ea8","last_reissued_at":"2026-07-08T01:19:29.338604Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:19:29.338604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Fanbo Meng, Haizhou Li, Haolan Chen, Minjun Zhao, Min Zhang, Qixun Teng, Shenyuan Jiang, Xuanyu Zhang, Yancheng He, Yunxin Li, Yu Xu, Zhenyu Liu","submitted_at":"2026-07-07T17:43:36Z","abstract_excerpt":"Developing seamless, high-performance, native intelligent full-duplex Spoken Language Models (SLMs) remains a critical challenge and long-standing goal for the speech and NLP community. Despite notable progress, recent endeavors are fundamentally constrained by severe modality interference, which causes substantial knowledge degradation and compromises semantic integrity -- ultimately making full-duplex SLMs feel unnatural and unintelligent. In this paper, through an exhaustive fine-grained analysis of model optimization dynamics, we uncover the root cause of such performance degradation, reve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06540","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/2607.06540/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":"2607.06540","created_at":"2026-07-08T01:19:29.338664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06540v1","created_at":"2026-07-08T01:19:29.338664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06540","created_at":"2026-07-08T01:19:29.338664+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z23FHT2HC5ZN","created_at":"2026-07-08T01:19:29.338664+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z23FHT2HC5ZN5JXF","created_at":"2026-07-08T01:19:29.338664+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z23FHT2H","created_at":"2026-07-08T01:19:29.338664+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/Z23FHT2HC5ZN5JXFWT3NH7YK33","json":"https://pith.science/pith/Z23FHT2HC5ZN5JXFWT3NH7YK33.json","graph_json":"https://pith.science/api/pith-number/Z23FHT2HC5ZN5JXFWT3NH7YK33/graph.json","events_json":"https://pith.science/api/pith-number/Z23FHT2HC5ZN5JXFWT3NH7YK33/events.json","paper":"https://pith.science/paper/Z23FHT2H"},"agent_actions":{"view_html":"https://pith.science/pith/Z23FHT2HC5ZN5JXFWT3NH7YK33","download_json":"https://pith.science/pith/Z23FHT2HC5ZN5JXFWT3NH7YK33.json","view_paper":"https://pith.science/paper/Z23FHT2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06540&json=true","fetch_graph":"https://pith.science/api/pith-number/Z23FHT2HC5ZN5JXFWT3NH7YK33/graph.json","fetch_events":"https://pith.science/api/pith-number/Z23FHT2HC5ZN5JXFWT3NH7YK33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z23FHT2HC5ZN5JXFWT3NH7YK33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z23FHT2HC5ZN5JXFWT3NH7YK33/action/storage_attestation","attest_author":"https://pith.science/pith/Z23FHT2HC5ZN5JXFWT3NH7YK33/action/author_attestation","sign_citation":"https://pith.science/pith/Z23FHT2HC5ZN5JXFWT3NH7YK33/action/citation_signature","submit_replication":"https://pith.science/pith/Z23FHT2HC5ZN5JXFWT3NH7YK33/action/replication_record"}},"created_at":"2026-07-08T01:19:29.338664+00:00","updated_at":"2026-07-08T01:19:29.338664+00:00"}