{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HMT3SQ2WUJQRKAWTZYGOMKOYH6","short_pith_number":"pith:HMT3SQ2W","schema_version":"1.0","canonical_sha256":"3b27b94356a2611502d3ce0ce629d83f81defeeb90e59afbf634bfeb054c2bbe","source":{"kind":"arxiv","id":"2607.14310","version":1},"attestation_state":"computed","paper":{"title":"Dialogs: a studio-quality expressive conversational Russian speech corpus for dialog assistants","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ilya Latyshev, Ilya Shigabeev","submitted_at":"2026-07-15T19:16:31Z","abstract_excerpt":"We introduce Dialogs, a studio-quality Russian conversational speech corpus for dialog assistants. The dataset contains 20.6 hours of face-to-face acted dialogs recorded in a professional studio (44.1 kHz stereo) and segmented into 11,796 utterances across 3 speakers. Unlike read-speech resources, Dialogs captures turn-taking rhythm and expressive prosody, and provides per-utterance style/emotion labels spanning 12 categories. We validate corpus quality with crowd MOS tests, showing comparable audio quality and intelligibility to strong Russian studio baselines while achieving higher ratings f"},"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":"2607.14310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-15T19:16:31Z","cross_cats_sorted":[],"title_canon_sha256":"6a6ae2736dc731bd918941144565a8606167b2df092fc35885988d2f1346150b","abstract_canon_sha256":"7704b6d802923992f9accfcffb7ac0a884b3c425045a9a28cb4157f7a2fbc41e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:21:04.681460Z","signature_b64":"6ZGMSNbf9788u0+lStVFlRxi4tODvN6oXkQLuFHnFdMYRuxMSw4CMNioXvYtNlQqPZNFUQkc+YYRFbDcUE8bAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b27b94356a2611502d3ce0ce629d83f81defeeb90e59afbf634bfeb054c2bbe","last_reissued_at":"2026-07-17T00:21:04.680510Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:21:04.680510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dialogs: a studio-quality expressive conversational Russian speech corpus for dialog assistants","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ilya Latyshev, Ilya Shigabeev","submitted_at":"2026-07-15T19:16:31Z","abstract_excerpt":"We introduce Dialogs, a studio-quality Russian conversational speech corpus for dialog assistants. The dataset contains 20.6 hours of face-to-face acted dialogs recorded in a professional studio (44.1 kHz stereo) and segmented into 11,796 utterances across 3 speakers. Unlike read-speech resources, Dialogs captures turn-taking rhythm and expressive prosody, and provides per-utterance style/emotion labels spanning 12 categories. We validate corpus quality with crowd MOS tests, showing comparable audio quality and intelligibility to strong Russian studio baselines while achieving higher ratings f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14310","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/2607.14310/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":"2607.14310","created_at":"2026-07-17T00:21:04.681003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14310v1","created_at":"2026-07-17T00:21:04.681003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14310","created_at":"2026-07-17T00:21:04.681003+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMT3SQ2WUJQR","created_at":"2026-07-17T00:21:04.681003+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMT3SQ2WUJQRKAWT","created_at":"2026-07-17T00:21:04.681003+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMT3SQ2W","created_at":"2026-07-17T00:21:04.681003+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/HMT3SQ2WUJQRKAWTZYGOMKOYH6","json":"https://pith.science/pith/HMT3SQ2WUJQRKAWTZYGOMKOYH6.json","graph_json":"https://pith.science/api/pith-number/HMT3SQ2WUJQRKAWTZYGOMKOYH6/graph.json","events_json":"https://pith.science/api/pith-number/HMT3SQ2WUJQRKAWTZYGOMKOYH6/events.json","paper":"https://pith.science/paper/HMT3SQ2W"},"agent_actions":{"view_html":"https://pith.science/pith/HMT3SQ2WUJQRKAWTZYGOMKOYH6","download_json":"https://pith.science/pith/HMT3SQ2WUJQRKAWTZYGOMKOYH6.json","view_paper":"https://pith.science/paper/HMT3SQ2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14310&json=true","fetch_graph":"https://pith.science/api/pith-number/HMT3SQ2WUJQRKAWTZYGOMKOYH6/graph.json","fetch_events":"https://pith.science/api/pith-number/HMT3SQ2WUJQRKAWTZYGOMKOYH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMT3SQ2WUJQRKAWTZYGOMKOYH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMT3SQ2WUJQRKAWTZYGOMKOYH6/action/storage_attestation","attest_author":"https://pith.science/pith/HMT3SQ2WUJQRKAWTZYGOMKOYH6/action/author_attestation","sign_citation":"https://pith.science/pith/HMT3SQ2WUJQRKAWTZYGOMKOYH6/action/citation_signature","submit_replication":"https://pith.science/pith/HMT3SQ2WUJQRKAWTZYGOMKOYH6/action/replication_record"}},"created_at":"2026-07-17T00:21:04.681003+00:00","updated_at":"2026-07-17T00:21:04.681003+00:00"}