{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PQDEYPYRY53532LJYYLZJY4BC7","short_pith_number":"pith:PQDEYPYR","schema_version":"1.0","canonical_sha256":"7c064c3f11c777dde969c61794e38117d6a6c759e1b750aad73aa2c6e9e7cec2","source":{"kind":"arxiv","id":"2506.07502","version":1},"attestation_state":"computed","paper":{"title":"DEBATE: A Dataset for Disentangling Textual Ambiguity in Mandarin Through Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haotian Guo, Jing Han, Shengfan Shen, Shihao Gao, Weihao Gan, Wulong Xiang, Yongfeng Tu, Zixing Zhang","submitted_at":"2025-06-09T07:27:22Z","abstract_excerpt":"Despite extensive research on textual and visual disambiguation, disambiguation through speech (DTS) remains underexplored. This is largely due to the lack of high-quality datasets that pair spoken sentences with richly ambiguous text. To address this gap, we present DEBATE, a unique public Chinese speech-text dataset designed to study how speech cues and patterns-pronunciation, pause, stress and intonation-can help resolve textual ambiguity and reveal a speaker's true intent. DEBATE contains 1,001 carefully selected ambiguous utterances, each recorded by 10 native speakers, capturing diverse "},"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":"2506.07502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T07:27:22Z","cross_cats_sorted":[],"title_canon_sha256":"b0c8b507c349b89e3cc9467a7c62eae64f411c571b944604932e543c380bb3f4","abstract_canon_sha256":"33f9664a3ef1acde3a0617367517840e4a0911e1879cab3b850c070203964083"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:28.425848Z","signature_b64":"txtcL3X94h2zejzkeFgU3BWEXlpZVU1kXg4Ggxa+FlCUzeza7WnFNQH8JAkbE4zHVlWWAJzPYoXJLnMTqO/GCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c064c3f11c777dde969c61794e38117d6a6c759e1b750aad73aa2c6e9e7cec2","last_reissued_at":"2026-07-05T11:18:28.425337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:28.425337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEBATE: A Dataset for Disentangling Textual Ambiguity in Mandarin Through Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haotian Guo, Jing Han, Shengfan Shen, Shihao Gao, Weihao Gan, Wulong Xiang, Yongfeng Tu, Zixing Zhang","submitted_at":"2025-06-09T07:27:22Z","abstract_excerpt":"Despite extensive research on textual and visual disambiguation, disambiguation through speech (DTS) remains underexplored. This is largely due to the lack of high-quality datasets that pair spoken sentences with richly ambiguous text. To address this gap, we present DEBATE, a unique public Chinese speech-text dataset designed to study how speech cues and patterns-pronunciation, pause, stress and intonation-can help resolve textual ambiguity and reveal a speaker's true intent. DEBATE contains 1,001 carefully selected ambiguous utterances, each recorded by 10 native speakers, capturing diverse "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07502","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/2506.07502/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":"2506.07502","created_at":"2026-07-05T11:18:28.425396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07502v1","created_at":"2026-07-05T11:18:28.425396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07502","created_at":"2026-07-05T11:18:28.425396+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQDEYPYRY535","created_at":"2026-07-05T11:18:28.425396+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQDEYPYRY53532LJ","created_at":"2026-07-05T11:18:28.425396+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQDEYPYR","created_at":"2026-07-05T11:18:28.425396+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/PQDEYPYRY53532LJYYLZJY4BC7","json":"https://pith.science/pith/PQDEYPYRY53532LJYYLZJY4BC7.json","graph_json":"https://pith.science/api/pith-number/PQDEYPYRY53532LJYYLZJY4BC7/graph.json","events_json":"https://pith.science/api/pith-number/PQDEYPYRY53532LJYYLZJY4BC7/events.json","paper":"https://pith.science/paper/PQDEYPYR"},"agent_actions":{"view_html":"https://pith.science/pith/PQDEYPYRY53532LJYYLZJY4BC7","download_json":"https://pith.science/pith/PQDEYPYRY53532LJYYLZJY4BC7.json","view_paper":"https://pith.science/paper/PQDEYPYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07502&json=true","fetch_graph":"https://pith.science/api/pith-number/PQDEYPYRY53532LJYYLZJY4BC7/graph.json","fetch_events":"https://pith.science/api/pith-number/PQDEYPYRY53532LJYYLZJY4BC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQDEYPYRY53532LJYYLZJY4BC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQDEYPYRY53532LJYYLZJY4BC7/action/storage_attestation","attest_author":"https://pith.science/pith/PQDEYPYRY53532LJYYLZJY4BC7/action/author_attestation","sign_citation":"https://pith.science/pith/PQDEYPYRY53532LJYYLZJY4BC7/action/citation_signature","submit_replication":"https://pith.science/pith/PQDEYPYRY53532LJYYLZJY4BC7/action/replication_record"}},"created_at":"2026-07-05T11:18:28.425396+00:00","updated_at":"2026-07-05T11:18:28.425396+00:00"}