{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PQDEYPYRY53532LJYYLZJY4BC7","short_pith_number":"pith:PQDEYPYR","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"},"canonical_sha256":"7c064c3f11c777dde969c61794e38117d6a6c759e1b750aad73aa2c6e9e7cec2","source":{"kind":"arxiv","id":"2506.07502","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07502","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07502v1","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07502","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"PQDEYPYRY535","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"PQDEYPYRY53532LJ","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"PQDEYPYR","created_at":"2026-07-05T11:18:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PQDEYPYRY53532LJYYLZJY4BC7","target":"record","payload":{"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"},"canonical_sha256":"7c064c3f11c777dde969c61794e38117d6a6c759e1b750aad73aa2c6e9e7cec2","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"},"source_kind":"arxiv","source_id":"2506.07502","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OozJhxcHjEWAfY+AXHN/XtSTgBwFoAHGpbdo74zQ6cLIVptNLZngNkI3lBKpJTAA0omaEpSzlHaOIzLMK+rcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:47:04.310413Z"},"content_sha256":"a541857b72942b4b17ecf6114e4eb46ed39772f966e007c4087c5f8e2885b9c7","schema_version":"1.0","event_id":"sha256:a541857b72942b4b17ecf6114e4eb46ed39772f966e007c4087c5f8e2885b9c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PQDEYPYRY53532LJYYLZJY4BC7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lrcrOfr1TIqa+/r/KLbOFqcIbPyfsH6Pqxc5vL41YuYYWWXW/7woUeoYI94HFovQ/Ng652yQqT1gvgYaBQdYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:47:04.311098Z"},"content_sha256":"466ea54d69b432946f5cd73198f3a16625f10e275b4eefda7c586c8565dac519","schema_version":"1.0","event_id":"sha256:466ea54d69b432946f5cd73198f3a16625f10e275b4eefda7c586c8565dac519"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQDEYPYRY53532LJYYLZJY4BC7/bundle.json","state_url":"https://pith.science/pith/PQDEYPYRY53532LJYYLZJY4BC7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQDEYPYRY53532LJYYLZJY4BC7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-31T20:47:04Z","links":{"resolver":"https://pith.science/pith/PQDEYPYRY53532LJYYLZJY4BC7","bundle":"https://pith.science/pith/PQDEYPYRY53532LJYYLZJY4BC7/bundle.json","state":"https://pith.science/pith/PQDEYPYRY53532LJYYLZJY4BC7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQDEYPYRY53532LJYYLZJY4BC7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PQDEYPYRY53532LJYYLZJY4BC7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"33f9664a3ef1acde3a0617367517840e4a0911e1879cab3b850c070203964083","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T07:27:22Z","title_canon_sha256":"b0c8b507c349b89e3cc9467a7c62eae64f411c571b944604932e543c380bb3f4"},"schema_version":"1.0","source":{"id":"2506.07502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07502","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07502v1","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07502","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"PQDEYPYRY535","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"PQDEYPYRY53532LJ","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"PQDEYPYR","created_at":"2026-07-05T11:18:28Z"}],"graph_snapshots":[{"event_id":"sha256:466ea54d69b432946f5cd73198f3a16625f10e275b4eefda7c586c8565dac519","target":"graph","created_at":"2026-07-05T11:18:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.07502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Haotian Guo, Jing Han, Shengfan Shen, Shihao Gao, Weihao Gan, Wulong Xiang, Yongfeng Tu, Zixing Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T07:27:22Z","title":"DEBATE: A Dataset for Disentangling Textual Ambiguity in Mandarin Through Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07502","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a541857b72942b4b17ecf6114e4eb46ed39772f966e007c4087c5f8e2885b9c7","target":"record","created_at":"2026-07-05T11:18:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"33f9664a3ef1acde3a0617367517840e4a0911e1879cab3b850c070203964083","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T07:27:22Z","title_canon_sha256":"b0c8b507c349b89e3cc9467a7c62eae64f411c571b944604932e543c380bb3f4"},"schema_version":"1.0","source":{"id":"2506.07502","kind":"arxiv","version":1}},"canonical_sha256":"7c064c3f11c777dde969c61794e38117d6a6c759e1b750aad73aa2c6e9e7cec2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c064c3f11c777dde969c61794e38117d6a6c759e1b750aad73aa2c6e9e7cec2","first_computed_at":"2026-07-05T11:18:28.425337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:28.425337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"txtcL3X94h2zejzkeFgU3BWEXlpZVU1kXg4Ggxa+FlCUzeza7WnFNQH8JAkbE4zHVlWWAJzPYoXJLnMTqO/GCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:28.425848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a541857b72942b4b17ecf6114e4eb46ed39772f966e007c4087c5f8e2885b9c7","sha256:466ea54d69b432946f5cd73198f3a16625f10e275b4eefda7c586c8565dac519"],"state_sha256":"fa56bd44bb3a0ceff632c86a7179490b6cd76336baee078ca75b4ca3f4ecf79e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QAdwrkmBg8d2rFNk0uYMmIWwh2tLH3IOFMeRldmH8AQuCqJrJL2JINEoYgvCkaCovVP5vsVO252z8ehOj9EzCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T20:47:04.315651Z","bundle_sha256":"7a58eab8027802727d855ca3b64b2ea6878bd0568a9eef12ce1628545f032e64"}}