{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R5ZPPT66DBII4MKYSKC75R7G3W","short_pith_number":"pith:R5ZPPT66","schema_version":"1.0","canonical_sha256":"8f72f7cfde18508e31589285fec7e6dd9b5f441554d5cf31ec2e822e3deb72ae","source":{"kind":"arxiv","id":"2607.08208","version":1},"attestation_state":"computed","paper":{"title":"Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Wu, RongQi Han, Wei Liang, Wei Xu, Zhen Wang","submitted_at":"2026-07-09T08:07:34Z","abstract_excerpt":"This paper describes our self-designed system for Task 1 of the MLC-SLM 2026 Challenge for multilingual two-speaker conversational speech. The system combines a modular speaker diarization front end with a challenge-adapted Qwen3-ASR-1.7B recognizer. The diarization front end performs voice activity detection, subsegment generation, CAMPPlus speaker embedding extraction, two-speaker spectral clustering, and RTTM-based audio segmentation. The resulting speaker-attributed segments are grouped by language or region and decoded by the adapted ASR model. For ASR adaptation, we first perform supervi"},"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":"2607.08208","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T08:07:34Z","cross_cats_sorted":[],"title_canon_sha256":"4d555d679700e314cd6b31ff9c9968aa97beb653a94aab76fe98604c6bea4de3","abstract_canon_sha256":"e19b02ba63d324953f25c4ac8fb99ecf156ce9173ab92a3fdb9a092aa35a36bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:29.759527Z","signature_b64":"ak9FsEbnJOlNxaeFm6Q5VOtOKhDGn7YOYS4ep9XKXWB9YelMYw8E3T4oCX238FD8M/8uoQcKTLmIdAHEAwXFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f72f7cfde18508e31589285fec7e6dd9b5f441554d5cf31ec2e822e3deb72ae","last_reissued_at":"2026-07-10T01:19:29.759097Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:29.759097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Wu, RongQi Han, Wei Liang, Wei Xu, Zhen Wang","submitted_at":"2026-07-09T08:07:34Z","abstract_excerpt":"This paper describes our self-designed system for Task 1 of the MLC-SLM 2026 Challenge for multilingual two-speaker conversational speech. The system combines a modular speaker diarization front end with a challenge-adapted Qwen3-ASR-1.7B recognizer. The diarization front end performs voice activity detection, subsegment generation, CAMPPlus speaker embedding extraction, two-speaker spectral clustering, and RTTM-based audio segmentation. The resulting speaker-attributed segments are grouped by language or region and decoded by the adapted ASR model. For ASR adaptation, we first perform supervi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08208","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/2607.08208/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":"2607.08208","created_at":"2026-07-10T01:19:29.759145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08208v1","created_at":"2026-07-10T01:19:29.759145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08208","created_at":"2026-07-10T01:19:29.759145+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5ZPPT66DBII","created_at":"2026-07-10T01:19:29.759145+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5ZPPT66DBII4MKY","created_at":"2026-07-10T01:19:29.759145+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5ZPPT66","created_at":"2026-07-10T01:19:29.759145+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08208","citing_title":"Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R5ZPPT66DBII4MKYSKC75R7G3W","json":"https://pith.science/pith/R5ZPPT66DBII4MKYSKC75R7G3W.json","graph_json":"https://pith.science/api/pith-number/R5ZPPT66DBII4MKYSKC75R7G3W/graph.json","events_json":"https://pith.science/api/pith-number/R5ZPPT66DBII4MKYSKC75R7G3W/events.json","paper":"https://pith.science/paper/R5ZPPT66"},"agent_actions":{"view_html":"https://pith.science/pith/R5ZPPT66DBII4MKYSKC75R7G3W","download_json":"https://pith.science/pith/R5ZPPT66DBII4MKYSKC75R7G3W.json","view_paper":"https://pith.science/paper/R5ZPPT66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08208&json=true","fetch_graph":"https://pith.science/api/pith-number/R5ZPPT66DBII4MKYSKC75R7G3W/graph.json","fetch_events":"https://pith.science/api/pith-number/R5ZPPT66DBII4MKYSKC75R7G3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5ZPPT66DBII4MKYSKC75R7G3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5ZPPT66DBII4MKYSKC75R7G3W/action/storage_attestation","attest_author":"https://pith.science/pith/R5ZPPT66DBII4MKYSKC75R7G3W/action/author_attestation","sign_citation":"https://pith.science/pith/R5ZPPT66DBII4MKYSKC75R7G3W/action/citation_signature","submit_replication":"https://pith.science/pith/R5ZPPT66DBII4MKYSKC75R7G3W/action/replication_record"}},"created_at":"2026-07-10T01:19:29.759145+00:00","updated_at":"2026-07-10T01:19:29.759145+00:00"}