{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F3YEBCTNINM65MWD7PSHDQYXWG","short_pith_number":"pith:F3YEBCTN","schema_version":"1.0","canonical_sha256":"2ef0408a6d4359eeb2c3fbe471c317b1824389951e8f0a96118cc4bfc57b7b48","source":{"kind":"arxiv","id":"2605.31469","version":1},"attestation_state":"computed","paper":{"title":"Scaling Conversational Hungarian ASR: The BEA-Dialogue+ Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Katalin M\\'ady, M\\'at\\'e Gedeon, P\\'eter Mihajlik, Piroska Zs\\'ofia Barta","submitted_at":"2026-05-29T16:01:25Z","abstract_excerpt":"Conversational automatic speech recognition in Hungarian is constrained by the limited amount of publicly available dialogue-style training data. The BEA-Dialogue corpus addresses this need, but its strictly speaker-disjoint train/dev/eval split reduces the usable material to only 85 hours. In this paper, we introduce BEA-Dialogue+, an expanded version of the corpus that relaxes the split criterion for experimenters and dialogue partners while preserving complete separation of the primary speakers. This results in 200 hours of transcribed natural conversations and enables a controlled study of"},"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":"2605.31469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T16:01:25Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"e827f6fb463110342d64cb28e00a07a88f1f9ee4a8979ca20f5317bec1cce937","abstract_canon_sha256":"337a2c218527e8a74c3e646e74420faea89cfb0e55d9121e6fe011204d4b5301"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:04:07.712311Z","signature_b64":"BOuZO/egYF8R3tQQfxed41wi0pHVfa+3nUgAIl3lNK9zmZLAcMswSvXOQ7qc3oEBAaqxtBfyHrF7M+KaGXQWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ef0408a6d4359eeb2c3fbe471c317b1824389951e8f0a96118cc4bfc57b7b48","last_reissued_at":"2026-06-01T02:04:07.711414Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:04:07.711414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Conversational Hungarian ASR: The BEA-Dialogue+ Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Katalin M\\'ady, M\\'at\\'e Gedeon, P\\'eter Mihajlik, Piroska Zs\\'ofia Barta","submitted_at":"2026-05-29T16:01:25Z","abstract_excerpt":"Conversational automatic speech recognition in Hungarian is constrained by the limited amount of publicly available dialogue-style training data. The BEA-Dialogue corpus addresses this need, but its strictly speaker-disjoint train/dev/eval split reduces the usable material to only 85 hours. In this paper, we introduce BEA-Dialogue+, an expanded version of the corpus that relaxes the split criterion for experimenters and dialogue partners while preserving complete separation of the primary speakers. This results in 200 hours of transcribed natural conversations and enables a controlled study of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31469","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/2605.31469/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":"2605.31469","created_at":"2026-06-01T02:04:07.711569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31469v1","created_at":"2026-06-01T02:04:07.711569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31469","created_at":"2026-06-01T02:04:07.711569+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3YEBCTNINM6","created_at":"2026-06-01T02:04:07.711569+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3YEBCTNINM65MWD","created_at":"2026-06-01T02:04:07.711569+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3YEBCTN","created_at":"2026-06-01T02:04:07.711569+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/F3YEBCTNINM65MWD7PSHDQYXWG","json":"https://pith.science/pith/F3YEBCTNINM65MWD7PSHDQYXWG.json","graph_json":"https://pith.science/api/pith-number/F3YEBCTNINM65MWD7PSHDQYXWG/graph.json","events_json":"https://pith.science/api/pith-number/F3YEBCTNINM65MWD7PSHDQYXWG/events.json","paper":"https://pith.science/paper/F3YEBCTN"},"agent_actions":{"view_html":"https://pith.science/pith/F3YEBCTNINM65MWD7PSHDQYXWG","download_json":"https://pith.science/pith/F3YEBCTNINM65MWD7PSHDQYXWG.json","view_paper":"https://pith.science/paper/F3YEBCTN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31469&json=true","fetch_graph":"https://pith.science/api/pith-number/F3YEBCTNINM65MWD7PSHDQYXWG/graph.json","fetch_events":"https://pith.science/api/pith-number/F3YEBCTNINM65MWD7PSHDQYXWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3YEBCTNINM65MWD7PSHDQYXWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3YEBCTNINM65MWD7PSHDQYXWG/action/storage_attestation","attest_author":"https://pith.science/pith/F3YEBCTNINM65MWD7PSHDQYXWG/action/author_attestation","sign_citation":"https://pith.science/pith/F3YEBCTNINM65MWD7PSHDQYXWG/action/citation_signature","submit_replication":"https://pith.science/pith/F3YEBCTNINM65MWD7PSHDQYXWG/action/replication_record"}},"created_at":"2026-06-01T02:04:07.711569+00:00","updated_at":"2026-06-01T02:04:07.711569+00:00"}