{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N3CYIV4VSRJITUDQUXZYSEB4AY","short_pith_number":"pith:N3CYIV4V","schema_version":"1.0","canonical_sha256":"6ec5845795945289d070a5f389103c062a04147625ec8fdf0cb570d6819ef535","source":{"kind":"arxiv","id":"2412.01078","version":2},"attestation_state":"computed","paper":{"title":"Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Bajian Xiang, Qiang Niu, Shuaijiang Zhao, Tingwei Guo, Tongtang Wan, Wei Zou, Xiangang Li","submitted_at":"2024-12-02T03:31:46Z","abstract_excerpt":"The GPT-4o represents a significant milestone in enabling real-time interaction with large language models (LLMs) through speech, its remarkable low latency and high fluency not only capture attention but also stimulate research interest in the field. This real-time speech interaction is particularly valuable in scenarios requiring rapid feedback and immediate responses, dramatically enhancing user experience. However, there is a notable lack of research focused on real-time large speech language models, particularly for Chinese. In this work, we present KE-Omni, a seamless large speech langua"},"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":"2412.01078","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T03:31:46Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"7eefa539274104341f46e287d187b6b7e5bc5297bc3053d188718c80876f8421","abstract_canon_sha256":"63ecfb3b72c02a75069a6611781f5a99e8085ccf8583899d95644dd8f54f2035"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:38.496601Z","signature_b64":"X3DqtgkMonSo9A1rdBBAjdIgucE9rXoq5+X18f8lEJMFk4C6aOKqxgMlL5jQ0wz1n5wKAAwWhGxWKLr6+ep3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ec5845795945289d070a5f389103c062a04147625ec8fdf0cb570d6819ef535","last_reissued_at":"2026-07-05T09:43:38.496149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:38.496149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Bajian Xiang, Qiang Niu, Shuaijiang Zhao, Tingwei Guo, Tongtang Wan, Wei Zou, Xiangang Li","submitted_at":"2024-12-02T03:31:46Z","abstract_excerpt":"The GPT-4o represents a significant milestone in enabling real-time interaction with large language models (LLMs) through speech, its remarkable low latency and high fluency not only capture attention but also stimulate research interest in the field. This real-time speech interaction is particularly valuable in scenarios requiring rapid feedback and immediate responses, dramatically enhancing user experience. However, there is a notable lack of research focused on real-time large speech language models, particularly for Chinese. In this work, we present KE-Omni, a seamless large speech langua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01078","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/2412.01078/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":"2412.01078","created_at":"2026-07-05T09:43:38.496203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01078v2","created_at":"2026-07-05T09:43:38.496203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01078","created_at":"2026-07-05T09:43:38.496203+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3CYIV4VSRJI","created_at":"2026-07-05T09:43:38.496203+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3CYIV4VSRJITUDQ","created_at":"2026-07-05T09:43:38.496203+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3CYIV4V","created_at":"2026-07-05T09:43:38.496203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16578","citing_title":"Voice \"Cloning\" is Style Transfer","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16578","citing_title":"Voice \"Cloning\" is Style Transfer","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2601.04638","citing_title":"SpeechMedAssist: Efficiently and Effectively Adapting Speech Language Models for Medical Consultation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N3CYIV4VSRJITUDQUXZYSEB4AY","json":"https://pith.science/pith/N3CYIV4VSRJITUDQUXZYSEB4AY.json","graph_json":"https://pith.science/api/pith-number/N3CYIV4VSRJITUDQUXZYSEB4AY/graph.json","events_json":"https://pith.science/api/pith-number/N3CYIV4VSRJITUDQUXZYSEB4AY/events.json","paper":"https://pith.science/paper/N3CYIV4V"},"agent_actions":{"view_html":"https://pith.science/pith/N3CYIV4VSRJITUDQUXZYSEB4AY","download_json":"https://pith.science/pith/N3CYIV4VSRJITUDQUXZYSEB4AY.json","view_paper":"https://pith.science/paper/N3CYIV4V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01078&json=true","fetch_graph":"https://pith.science/api/pith-number/N3CYIV4VSRJITUDQUXZYSEB4AY/graph.json","fetch_events":"https://pith.science/api/pith-number/N3CYIV4VSRJITUDQUXZYSEB4AY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3CYIV4VSRJITUDQUXZYSEB4AY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3CYIV4VSRJITUDQUXZYSEB4AY/action/storage_attestation","attest_author":"https://pith.science/pith/N3CYIV4VSRJITUDQUXZYSEB4AY/action/author_attestation","sign_citation":"https://pith.science/pith/N3CYIV4VSRJITUDQUXZYSEB4AY/action/citation_signature","submit_replication":"https://pith.science/pith/N3CYIV4VSRJITUDQUXZYSEB4AY/action/replication_record"}},"created_at":"2026-07-05T09:43:38.496203+00:00","updated_at":"2026-07-05T09:43:38.496203+00:00"}