{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JUPFQMQ2GFHQHHHO4Q3UEOD5HM","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":"8bd25d538c3ecb1bff033e467ada63b0ffc57806cde29b4c0d68bf4dee4e1da6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-05T14:23:27Z","title_canon_sha256":"aa8a0580094285a1a3648c9852133234969b501146f7b5e0238c68d76f1b65e4"},"schema_version":"1.0","source":{"id":"2205.02670","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02670","created_at":"2026-07-05T05:31:14Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02670v3","created_at":"2026-07-05T05:31:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02670","created_at":"2026-07-05T05:31:14Z"},{"alias_kind":"pith_short_12","alias_value":"JUPFQMQ2GFHQ","created_at":"2026-07-05T05:31:14Z"},{"alias_kind":"pith_short_16","alias_value":"JUPFQMQ2GFHQHHHO","created_at":"2026-07-05T05:31:14Z"},{"alias_kind":"pith_short_8","alias_value":"JUPFQMQ2","created_at":"2026-07-05T05:31:14Z"}],"graph_snapshots":[{"event_id":"sha256:b70483afbd16943ed27f3114e101a32f724c02bb38c6d0340309feb8ca754330","target":"graph","created_at":"2026-07-05T05:31:14Z","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/2205.02670/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Content mismatch usually occurs when data from one modality is translated to another, e.g. language learners producing mispronunciations (errors in speech) when reading a sentence (target text) aloud. However, most existing alignment algorithms assume that the content involved in the two modalities is perfectly matched, thus leading to difficulty in locating such mismatch between speech and text. In this work, we develop an unsupervised learning algorithm that can infer the relationship between content-mismatched cross-modal sequential data, especially for speech-text sequences. More specifica","authors_text":"Gu Xiangming, Huang Hengguan, Wang Hao, Wang Ye, Wei Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-05T14:23:27Z","title":"Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02670","kind":"arxiv","version":3},"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":"sha256:65d9582cb51cd3bc1c50663a7e56b69c48579ff29e516e9e10ecfdc2e3a2657b","target":"record","created_at":"2026-07-05T05:31:14Z","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":"8bd25d538c3ecb1bff033e467ada63b0ffc57806cde29b4c0d68bf4dee4e1da6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-05T14:23:27Z","title_canon_sha256":"aa8a0580094285a1a3648c9852133234969b501146f7b5e0238c68d76f1b65e4"},"schema_version":"1.0","source":{"id":"2205.02670","kind":"arxiv","version":3}},"canonical_sha256":"4d1e58321a314f039ceee43742387d3b09c0d32de43ea57457cae94275a9981c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d1e58321a314f039ceee43742387d3b09c0d32de43ea57457cae94275a9981c","first_computed_at":"2026-07-05T05:31:14.464724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:31:14.464724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C4ijNjhrNTv86wo+go6hSGq0UbsHDXjhK3yUaCY1d3EVEPc9VIJsbhUSUU2t/mFIE4Jv1NahpRhLOv5ay/YfDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:31:14.465142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.02670","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65d9582cb51cd3bc1c50663a7e56b69c48579ff29e516e9e10ecfdc2e3a2657b","sha256:b70483afbd16943ed27f3114e101a32f724c02bb38c6d0340309feb8ca754330"],"state_sha256":"991242795a1d37388274ca3e0da08c7da49d0e85823e0eec73f8d2bcddf2075e"}