{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VGTRBJPDOUQ4EUJXXWCVDXEQZS","short_pith_number":"pith:VGTRBJPD","schema_version":"1.0","canonical_sha256":"a9a710a5e37521c25137bd8551dc90ccac237c262463ebf2a0185223abb970df","source":{"kind":"arxiv","id":"2506.13300","version":3},"attestation_state":"computed","paper":{"title":"Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bo Li, Chengben Xu, Wufeng Zhang","submitted_at":"2025-06-16T09:42:05Z","abstract_excerpt":"This paper presents Seewo's systems for both tracks of the Multilingual Conversational Speech Language Model Challenge (MLC-SLM), addressing automatic speech recognition (ASR) and speaker diarization with ASR (SD-ASR). We introduce a multi-stage training pipeline that explicitly enhances reasoning and self-correction in speech language models for ASR. Our approach combines curriculum learning for progressive capability acquisition, Chain-of-Thought data augmentation to foster intermediate reflection, and Reinforcement Learning with Verifiable Rewards (RLVR) to further refine self-correction th"},"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":"2506.13300","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T09:42:05Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"cf46a340aa1ca7566f33f4c9214062d9b4254279efcd3b70dad408f7568d582f","abstract_canon_sha256":"ed52f60ce3a3800531a6122cc7ca0eb911810847c6ed18cff0a8f0e46105df39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:30.483768Z","signature_b64":"LcmRDMifJ9Qbcx35jU9HHUTmaRytgWxI/kzE3y/NDMPwOr2JpUolNcvThfL8Pqp/6VmQA03CgbgTjmvgBQ9pAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9a710a5e37521c25137bd8551dc90ccac237c262463ebf2a0185223abb970df","last_reissued_at":"2026-07-05T11:23:30.483240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:30.483240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bo Li, Chengben Xu, Wufeng Zhang","submitted_at":"2025-06-16T09:42:05Z","abstract_excerpt":"This paper presents Seewo's systems for both tracks of the Multilingual Conversational Speech Language Model Challenge (MLC-SLM), addressing automatic speech recognition (ASR) and speaker diarization with ASR (SD-ASR). We introduce a multi-stage training pipeline that explicitly enhances reasoning and self-correction in speech language models for ASR. Our approach combines curriculum learning for progressive capability acquisition, Chain-of-Thought data augmentation to foster intermediate reflection, and Reinforcement Learning with Verifiable Rewards (RLVR) to further refine self-correction th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13300","kind":"arxiv","version":3},"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/2506.13300/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":"2506.13300","created_at":"2026-07-05T11:23:30.483295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13300v3","created_at":"2026-07-05T11:23:30.483295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13300","created_at":"2026-07-05T11:23:30.483295+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGTRBJPDOUQ4","created_at":"2026-07-05T11:23:30.483295+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGTRBJPDOUQ4EUJX","created_at":"2026-07-05T11:23:30.483295+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGTRBJPD","created_at":"2026-07-05T11:23:30.483295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13300","citing_title":"Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGTRBJPDOUQ4EUJXXWCVDXEQZS","json":"https://pith.science/pith/VGTRBJPDOUQ4EUJXXWCVDXEQZS.json","graph_json":"https://pith.science/api/pith-number/VGTRBJPDOUQ4EUJXXWCVDXEQZS/graph.json","events_json":"https://pith.science/api/pith-number/VGTRBJPDOUQ4EUJXXWCVDXEQZS/events.json","paper":"https://pith.science/paper/VGTRBJPD"},"agent_actions":{"view_html":"https://pith.science/pith/VGTRBJPDOUQ4EUJXXWCVDXEQZS","download_json":"https://pith.science/pith/VGTRBJPDOUQ4EUJXXWCVDXEQZS.json","view_paper":"https://pith.science/paper/VGTRBJPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13300&json=true","fetch_graph":"https://pith.science/api/pith-number/VGTRBJPDOUQ4EUJXXWCVDXEQZS/graph.json","fetch_events":"https://pith.science/api/pith-number/VGTRBJPDOUQ4EUJXXWCVDXEQZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGTRBJPDOUQ4EUJXXWCVDXEQZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGTRBJPDOUQ4EUJXXWCVDXEQZS/action/storage_attestation","attest_author":"https://pith.science/pith/VGTRBJPDOUQ4EUJXXWCVDXEQZS/action/author_attestation","sign_citation":"https://pith.science/pith/VGTRBJPDOUQ4EUJXXWCVDXEQZS/action/citation_signature","submit_replication":"https://pith.science/pith/VGTRBJPDOUQ4EUJXXWCVDXEQZS/action/replication_record"}},"created_at":"2026-07-05T11:23:30.483295+00:00","updated_at":"2026-07-05T11:23:30.483295+00:00"}