{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XTRJ3YW55F6RHKTE4TGAIGFSJR","short_pith_number":"pith:XTRJ3YW5","schema_version":"1.0","canonical_sha256":"bce29de2dde97d13aa64e4cc0418b24c644311107c044b85c23fb4f5ab1658ef","source":{"kind":"arxiv","id":"2605.23912","version":1},"attestation_state":"computed","paper":{"title":"Raon-Speech Technical Report","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"cs.CL","authors_text":"Beomsoo Kim, Changho Choi, Dohyun Kim, Dongki Lee, Dongmin Park, Dongwon Kim, Ethan Ewer, Eunchong Kim, Gyeongman Kim, Haechan Kim, Hara Kang, Hyeonghwan Kim, Inkyu Park, Jaewoong Cho, Jihun Yun, Jihwan Moon, Jiyun Kim, Jonghyun Lee, Joonghyun Bae, Junhyuck Kim, Kangwook Lee, Keon Lee, Minkyu Kim, Sehun Lee, Seungjun Chung, Sungwoo Cho","submitted_at":"2026-04-08T23:43:46Z","abstract_excerpt":"We present Raon-Speech, a top-performing 9B-parameter speech language model (SpeechLM) for English and Korean speech understanding, answering, and generation, and Raon-SpeechChat, a high-performing full-duplex extension for natural real-time conversation. Raon-Speech successfully transforms a pre-trained LLM into a SpeechLM that both understands and generates speech while preserving strong text capabilities. It trains on 1.38M hours of highly curated English and Korean speech and text datasets with the following training stages: (1) speech modules alignment, (2) end-to-end SpeechLM pre-trainin"},"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":"2605.23912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-08T23:43:46Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"ad166cbadffd654ba678fb04de04cfae44eb57b453a8f6b2a1566ec95397a4b7","abstract_canon_sha256":"d6564c3986caf98ed55ae61c691ee06bca26cdf0636d33327609f3316d4532c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T00:02:21.589495Z","signature_b64":"jEYpSnNGI8NrGUfD2cIWLewkvLC1x/ORX9YKTB0dTH7OA/emh/b5JVZM7u+AF5Stap158yV53BeWgN9HmOZcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bce29de2dde97d13aa64e4cc0418b24c644311107c044b85c23fb4f5ab1658ef","last_reissued_at":"2026-05-26T00:02:21.588447Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T00:02:21.588447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Raon-Speech Technical Report","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"cs.CL","authors_text":"Beomsoo Kim, Changho Choi, Dohyun Kim, Dongki Lee, Dongmin Park, Dongwon Kim, Ethan Ewer, Eunchong Kim, Gyeongman Kim, Haechan Kim, Hara Kang, Hyeonghwan Kim, Inkyu Park, Jaewoong Cho, Jihun Yun, Jihwan Moon, Jiyun Kim, Jonghyun Lee, Joonghyun Bae, Junhyuck Kim, Kangwook Lee, Keon Lee, Minkyu Kim, Sehun Lee, Seungjun Chung, Sungwoo Cho","submitted_at":"2026-04-08T23:43:46Z","abstract_excerpt":"We present Raon-Speech, a top-performing 9B-parameter speech language model (SpeechLM) for English and Korean speech understanding, answering, and generation, and Raon-SpeechChat, a high-performing full-duplex extension for natural real-time conversation. Raon-Speech successfully transforms a pre-trained LLM into a SpeechLM that both understands and generates speech while preserving strong text capabilities. It trains on 1.38M hours of highly curated English and Korean speech and text datasets with the following training stages: (1) speech modules alignment, (2) end-to-end SpeechLM pre-trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23912","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/2605.23912/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":"2605.23912","created_at":"2026-05-26T00:02:21.588597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23912v1","created_at":"2026-05-26T00:02:21.588597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23912","created_at":"2026-05-26T00:02:21.588597+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTRJ3YW55F6R","created_at":"2026-05-26T00:02:21.588597+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTRJ3YW55F6RHKTE","created_at":"2026-05-26T00:02:21.588597+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTRJ3YW5","created_at":"2026-05-26T00:02:21.588597+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/XTRJ3YW55F6RHKTE4TGAIGFSJR","json":"https://pith.science/pith/XTRJ3YW55F6RHKTE4TGAIGFSJR.json","graph_json":"https://pith.science/api/pith-number/XTRJ3YW55F6RHKTE4TGAIGFSJR/graph.json","events_json":"https://pith.science/api/pith-number/XTRJ3YW55F6RHKTE4TGAIGFSJR/events.json","paper":"https://pith.science/paper/XTRJ3YW5"},"agent_actions":{"view_html":"https://pith.science/pith/XTRJ3YW55F6RHKTE4TGAIGFSJR","download_json":"https://pith.science/pith/XTRJ3YW55F6RHKTE4TGAIGFSJR.json","view_paper":"https://pith.science/paper/XTRJ3YW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23912&json=true","fetch_graph":"https://pith.science/api/pith-number/XTRJ3YW55F6RHKTE4TGAIGFSJR/graph.json","fetch_events":"https://pith.science/api/pith-number/XTRJ3YW55F6RHKTE4TGAIGFSJR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTRJ3YW55F6RHKTE4TGAIGFSJR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTRJ3YW55F6RHKTE4TGAIGFSJR/action/storage_attestation","attest_author":"https://pith.science/pith/XTRJ3YW55F6RHKTE4TGAIGFSJR/action/author_attestation","sign_citation":"https://pith.science/pith/XTRJ3YW55F6RHKTE4TGAIGFSJR/action/citation_signature","submit_replication":"https://pith.science/pith/XTRJ3YW55F6RHKTE4TGAIGFSJR/action/replication_record"}},"created_at":"2026-05-26T00:02:21.588597+00:00","updated_at":"2026-05-26T00:02:21.588597+00:00"}