{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SA7LEACKK3T43SBYVUISY44UQ6","short_pith_number":"pith:SA7LEACK","schema_version":"1.0","canonical_sha256":"903eb2004a56e7cdc838ad112c739487b2b1e4423c77f7ed1f5020ddcae34430","source":{"kind":"arxiv","id":"2506.13414","version":1},"attestation_state":"computed","paper":{"title":"BUT System for the MLC-SLM Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Alexander Polok, Dominik Klement, Jan \\v{C}ernock\\'y, Jiangyu Han, Luk\\'a\\v{s} Burget, Samuele Cornell","submitted_at":"2025-06-16T12:28:35Z","abstract_excerpt":"We present a two-speaker automatic speech recognition (ASR) system that combines DiCoW -- a diarization-conditioned variant of Whisper -- with DiariZen, a diarization pipeline built on top of Pyannote. We first evaluate both systems in out-of-domain (OOD) multilingual scenarios without any fine-tuning. In this scenario, DiariZen consistently outperforms the baseline Pyannote diarization model, demonstrating strong generalization. Despite being fine-tuned on English-only data for target-speaker ASR, DiCoW retains solid multilingual performance, indicating that encoder modifications preserve Whi"},"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":"2506.13414","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-16T12:28:35Z","cross_cats_sorted":[],"title_canon_sha256":"79687a717418910fffe77d558ef443e286184c252f0fab8d01d8ec71be4575cf","abstract_canon_sha256":"50db6509d06aca9106a0f1d2ee0e976e3576270fd0cb08a31033cfeca4e91bf2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:10.046873Z","signature_b64":"cQWgIFfZ1k5IGDLghLjbqNNS/fbh346YWaxpZ5BndK2kd/5wBe7GLU6t8YDPIwyBA5VqDFFizZaqOmslxM5BBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"903eb2004a56e7cdc838ad112c739487b2b1e4423c77f7ed1f5020ddcae34430","last_reissued_at":"2026-07-05T11:22:10.046455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:10.046455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BUT System for the MLC-SLM Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Alexander Polok, Dominik Klement, Jan \\v{C}ernock\\'y, Jiangyu Han, Luk\\'a\\v{s} Burget, Samuele Cornell","submitted_at":"2025-06-16T12:28:35Z","abstract_excerpt":"We present a two-speaker automatic speech recognition (ASR) system that combines DiCoW -- a diarization-conditioned variant of Whisper -- with DiariZen, a diarization pipeline built on top of Pyannote. We first evaluate both systems in out-of-domain (OOD) multilingual scenarios without any fine-tuning. In this scenario, DiariZen consistently outperforms the baseline Pyannote diarization model, demonstrating strong generalization. Despite being fine-tuned on English-only data for target-speaker ASR, DiCoW retains solid multilingual performance, indicating that encoder modifications preserve Whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13414","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/2506.13414/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":"2506.13414","created_at":"2026-07-05T11:22:10.046511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13414v1","created_at":"2026-07-05T11:22:10.046511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13414","created_at":"2026-07-05T11:22:10.046511+00:00"},{"alias_kind":"pith_short_12","alias_value":"SA7LEACKK3T4","created_at":"2026-07-05T11:22:10.046511+00:00"},{"alias_kind":"pith_short_16","alias_value":"SA7LEACKK3T43SBY","created_at":"2026-07-05T11:22:10.046511+00:00"},{"alias_kind":"pith_short_8","alias_value":"SA7LEACK","created_at":"2026-07-05T11:22:10.046511+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13414","citing_title":"BUT System for the MLC-SLM Challenge","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SA7LEACKK3T43SBYVUISY44UQ6","json":"https://pith.science/pith/SA7LEACKK3T43SBYVUISY44UQ6.json","graph_json":"https://pith.science/api/pith-number/SA7LEACKK3T43SBYVUISY44UQ6/graph.json","events_json":"https://pith.science/api/pith-number/SA7LEACKK3T43SBYVUISY44UQ6/events.json","paper":"https://pith.science/paper/SA7LEACK"},"agent_actions":{"view_html":"https://pith.science/pith/SA7LEACKK3T43SBYVUISY44UQ6","download_json":"https://pith.science/pith/SA7LEACKK3T43SBYVUISY44UQ6.json","view_paper":"https://pith.science/paper/SA7LEACK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13414&json=true","fetch_graph":"https://pith.science/api/pith-number/SA7LEACKK3T43SBYVUISY44UQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/SA7LEACKK3T43SBYVUISY44UQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SA7LEACKK3T43SBYVUISY44UQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SA7LEACKK3T43SBYVUISY44UQ6/action/storage_attestation","attest_author":"https://pith.science/pith/SA7LEACKK3T43SBYVUISY44UQ6/action/author_attestation","sign_citation":"https://pith.science/pith/SA7LEACKK3T43SBYVUISY44UQ6/action/citation_signature","submit_replication":"https://pith.science/pith/SA7LEACKK3T43SBYVUISY44UQ6/action/replication_record"}},"created_at":"2026-07-05T11:22:10.046511+00:00","updated_at":"2026-07-05T11:22:10.046511+00:00"}