{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:37F3WBPGESORJXZQI4TWF5F4OT","short_pith_number":"pith:37F3WBPG","schema_version":"1.0","canonical_sha256":"dfcbbb05e6249d14df30472762f4bc74ed8bac451fdc4f17d412a6a442cda2fe","source":{"kind":"arxiv","id":"2406.08820","version":1},"attestation_state":"computed","paper":{"title":"DisfluencySpeech -- Single-Speaker Conversational Speech Dataset with Paralanguage","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Dorien Herremans, Kyra Wang","submitted_at":"2024-06-13T05:23:22Z","abstract_excerpt":"Laughing, sighing, stuttering, and other forms of paralanguage do not contribute any direct lexical meaning to speech, but they provide crucial propositional context that aids semantic and pragmatic processes such as irony. It is thus important for artificial social agents to both understand and be able to generate speech with semantically-important paralanguage. Most speech datasets do not include transcribed non-lexical speech sounds and disfluencies, while those that do are typically multi-speaker datasets where each speaker provides relatively little audio. This makes it challenging to tra"},"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":"2406.08820","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-13T05:23:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e9bcc66bab34a7c818b2ae45687b3534893247c56b9608d2468cb7c5b375b9f2","abstract_canon_sha256":"2189db032a22b917cfb36b07f61e39ac314e5d04fd3e24dc67e933c3c4411854"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:23.895536Z","signature_b64":"YAQorr0qZJTLQFG19YNkndxbDiNrK5oGX9jJff0XedddQNZNX7WPZksM+DWSWj2Ej50L27c2tb5TXXMjkjWdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfcbbb05e6249d14df30472762f4bc74ed8bac451fdc4f17d412a6a442cda2fe","last_reissued_at":"2026-07-05T08:31:23.895052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:23.895052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DisfluencySpeech -- Single-Speaker Conversational Speech Dataset with Paralanguage","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Dorien Herremans, Kyra Wang","submitted_at":"2024-06-13T05:23:22Z","abstract_excerpt":"Laughing, sighing, stuttering, and other forms of paralanguage do not contribute any direct lexical meaning to speech, but they provide crucial propositional context that aids semantic and pragmatic processes such as irony. It is thus important for artificial social agents to both understand and be able to generate speech with semantically-important paralanguage. Most speech datasets do not include transcribed non-lexical speech sounds and disfluencies, while those that do are typically multi-speaker datasets where each speaker provides relatively little audio. This makes it challenging to tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08820","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/2406.08820/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":"2406.08820","created_at":"2026-07-05T08:31:23.895109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08820v1","created_at":"2026-07-05T08:31:23.895109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08820","created_at":"2026-07-05T08:31:23.895109+00:00"},{"alias_kind":"pith_short_12","alias_value":"37F3WBPGESOR","created_at":"2026-07-05T08:31:23.895109+00:00"},{"alias_kind":"pith_short_16","alias_value":"37F3WBPGESORJXZQ","created_at":"2026-07-05T08:31:23.895109+00:00"},{"alias_kind":"pith_short_8","alias_value":"37F3WBPG","created_at":"2026-07-05T08:31:23.895109+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/37F3WBPGESORJXZQI4TWF5F4OT","json":"https://pith.science/pith/37F3WBPGESORJXZQI4TWF5F4OT.json","graph_json":"https://pith.science/api/pith-number/37F3WBPGESORJXZQI4TWF5F4OT/graph.json","events_json":"https://pith.science/api/pith-number/37F3WBPGESORJXZQI4TWF5F4OT/events.json","paper":"https://pith.science/paper/37F3WBPG"},"agent_actions":{"view_html":"https://pith.science/pith/37F3WBPGESORJXZQI4TWF5F4OT","download_json":"https://pith.science/pith/37F3WBPGESORJXZQI4TWF5F4OT.json","view_paper":"https://pith.science/paper/37F3WBPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08820&json=true","fetch_graph":"https://pith.science/api/pith-number/37F3WBPGESORJXZQI4TWF5F4OT/graph.json","fetch_events":"https://pith.science/api/pith-number/37F3WBPGESORJXZQI4TWF5F4OT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37F3WBPGESORJXZQI4TWF5F4OT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37F3WBPGESORJXZQI4TWF5F4OT/action/storage_attestation","attest_author":"https://pith.science/pith/37F3WBPGESORJXZQI4TWF5F4OT/action/author_attestation","sign_citation":"https://pith.science/pith/37F3WBPGESORJXZQI4TWF5F4OT/action/citation_signature","submit_replication":"https://pith.science/pith/37F3WBPGESORJXZQI4TWF5F4OT/action/replication_record"}},"created_at":"2026-07-05T08:31:23.895109+00:00","updated_at":"2026-07-05T08:31:23.895109+00:00"}