{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S76DLTVV6D6R57GZEZJF36CMQP","short_pith_number":"pith:S76DLTVV","schema_version":"1.0","canonical_sha256":"97fc35ceb5f0fd1efcd926525df84c83e6e7690766363f8787c69fd6519ca083","source":{"kind":"arxiv","id":"2506.17611","version":1},"attestation_state":"computed","paper":{"title":"OpusLM: A Family of Open Unified Speech Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Huck Yang, Jiatong Shi, Jinchuan Tian, Keita Goto, Shikhar Bharadwaj, Shinji Watanabe, Siddhant Arora, Takashi Maekaku, William Chen, Xiang Yue, Yifan Peng, Yusuke Shinohara","submitted_at":"2025-06-21T06:30:59Z","abstract_excerpt":"This paper presents Open Unified Speech Language Models (OpusLMs), a family of open foundational speech language models (SpeechLMs) up to 7B. Initialized from decoder-only text language models, the OpusLMs are continuously pre-trained on 213K hours of speech-text pairs and 292B text-only tokens. We demonstrate our OpusLMs achieve comparable (or even superior) performance with existing SpeechLMs in speech recognition, speech synthesis, and text-only capabilities. Technically, this paper articulates our SpeechLM designs on tokenization, multi-stream language models, and multi-stage training stra"},"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":"2506.17611","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-21T06:30:59Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"377fcb79ca7644d6c38046fc4ff3353ed7b027da4648f613128551279fd52f6b","abstract_canon_sha256":"f805cefd1675f5a6c866a16e504e3ce893419ddcc7341de07525e70724395e78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:32.760823Z","signature_b64":"iMdu69WnklmU34w7ZRUwVFVW2WSUJbo7i6Pw+/SXzmZzc2dbJbDVArhiNec/9lMT1maEeJ8webw2lp2jqjzwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97fc35ceb5f0fd1efcd926525df84c83e6e7690766363f8787c69fd6519ca083","last_reissued_at":"2026-07-05T11:26:32.760302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:32.760302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpusLM: A Family of Open Unified Speech Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Huck Yang, Jiatong Shi, Jinchuan Tian, Keita Goto, Shikhar Bharadwaj, Shinji Watanabe, Siddhant Arora, Takashi Maekaku, William Chen, Xiang Yue, Yifan Peng, Yusuke Shinohara","submitted_at":"2025-06-21T06:30:59Z","abstract_excerpt":"This paper presents Open Unified Speech Language Models (OpusLMs), a family of open foundational speech language models (SpeechLMs) up to 7B. Initialized from decoder-only text language models, the OpusLMs are continuously pre-trained on 213K hours of speech-text pairs and 292B text-only tokens. We demonstrate our OpusLMs achieve comparable (or even superior) performance with existing SpeechLMs in speech recognition, speech synthesis, and text-only capabilities. Technically, this paper articulates our SpeechLM designs on tokenization, multi-stream language models, and multi-stage training stra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17611","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/2506.17611/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":"2506.17611","created_at":"2026-07-05T11:26:32.760372+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17611v1","created_at":"2026-07-05T11:26:32.760372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17611","created_at":"2026-07-05T11:26:32.760372+00:00"},{"alias_kind":"pith_short_12","alias_value":"S76DLTVV6D6R","created_at":"2026-07-05T11:26:32.760372+00:00"},{"alias_kind":"pith_short_16","alias_value":"S76DLTVV6D6R57GZ","created_at":"2026-07-05T11:26:32.760372+00:00"},{"alias_kind":"pith_short_8","alias_value":"S76DLTVV","created_at":"2026-07-05T11:26:32.760372+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22811","citing_title":"Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02119","citing_title":"An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S76DLTVV6D6R57GZEZJF36CMQP","json":"https://pith.science/pith/S76DLTVV6D6R57GZEZJF36CMQP.json","graph_json":"https://pith.science/api/pith-number/S76DLTVV6D6R57GZEZJF36CMQP/graph.json","events_json":"https://pith.science/api/pith-number/S76DLTVV6D6R57GZEZJF36CMQP/events.json","paper":"https://pith.science/paper/S76DLTVV"},"agent_actions":{"view_html":"https://pith.science/pith/S76DLTVV6D6R57GZEZJF36CMQP","download_json":"https://pith.science/pith/S76DLTVV6D6R57GZEZJF36CMQP.json","view_paper":"https://pith.science/paper/S76DLTVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17611&json=true","fetch_graph":"https://pith.science/api/pith-number/S76DLTVV6D6R57GZEZJF36CMQP/graph.json","fetch_events":"https://pith.science/api/pith-number/S76DLTVV6D6R57GZEZJF36CMQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S76DLTVV6D6R57GZEZJF36CMQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S76DLTVV6D6R57GZEZJF36CMQP/action/storage_attestation","attest_author":"https://pith.science/pith/S76DLTVV6D6R57GZEZJF36CMQP/action/author_attestation","sign_citation":"https://pith.science/pith/S76DLTVV6D6R57GZEZJF36CMQP/action/citation_signature","submit_replication":"https://pith.science/pith/S76DLTVV6D6R57GZEZJF36CMQP/action/replication_record"}},"created_at":"2026-07-05T11:26:32.760372+00:00","updated_at":"2026-07-05T11:26:32.760372+00:00"}