{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EZJBZHZVEMEGZ7VOWY7OW67KFT","short_pith_number":"pith:EZJBZHZV","schema_version":"1.0","canonical_sha256":"26521c9f3523086cfeaeb63eeb7bea2ccc35ea5a802e922531e649f637240f17","source":{"kind":"arxiv","id":"2312.07254","version":1},"attestation_state":"computed","paper":{"title":"The GUA-Speech System Description for CNVSRC Challenge 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baozhong Ma, Binbin Zhang, Chao Lei, Fuping Pan, Shengqiang Li","submitted_at":"2023-12-12T13:35:33Z","abstract_excerpt":"This study describes our system for Task 1 Single-speaker Visual Speech Recognition (VSR) fixed track in the Chinese Continuous Visual Speech Recognition Challenge (CNVSRC) 2023. Specifically, we use intermediate connectionist temporal classification (Inter CTC) residual modules to relax the conditional independence assumption of CTC in our model. Then we use a bi-transformer decoder to enable the model to capture both past and future contextual information. In addition, we use Chinese characters as the modeling units to improve the recognition accuracy of our model. Finally, we use a recurren"},"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":"2312.07254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T13:35:33Z","cross_cats_sorted":[],"title_canon_sha256":"351bdcab4f9cd7d35decb4a8bc2ffdb052438931619b39231382fd88576bba08","abstract_canon_sha256":"2faaadf96b06d659a2ee7e16f7e70579748741aba978c7509ee753d5a1a5b975"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:17.263878Z","signature_b64":"skTL97hSHuvV+hydfxeKNM7xGTfPv/da64BWRTMxgjkTRaO6cAcIXZs4GT0GxiCpPP2SRx+mqX526Dy9sBrHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26521c9f3523086cfeaeb63eeb7bea2ccc35ea5a802e922531e649f637240f17","last_reissued_at":"2026-07-05T07:23:17.263400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:17.263400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The GUA-Speech System Description for CNVSRC Challenge 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baozhong Ma, Binbin Zhang, Chao Lei, Fuping Pan, Shengqiang Li","submitted_at":"2023-12-12T13:35:33Z","abstract_excerpt":"This study describes our system for Task 1 Single-speaker Visual Speech Recognition (VSR) fixed track in the Chinese Continuous Visual Speech Recognition Challenge (CNVSRC) 2023. Specifically, we use intermediate connectionist temporal classification (Inter CTC) residual modules to relax the conditional independence assumption of CTC in our model. Then we use a bi-transformer decoder to enable the model to capture both past and future contextual information. In addition, we use Chinese characters as the modeling units to improve the recognition accuracy of our model. Finally, we use a recurren"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07254","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/2312.07254/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":"2312.07254","created_at":"2026-07-05T07:23:17.263462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07254v1","created_at":"2026-07-05T07:23:17.263462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07254","created_at":"2026-07-05T07:23:17.263462+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZJBZHZVEMEG","created_at":"2026-07-05T07:23:17.263462+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZJBZHZVEMEGZ7VO","created_at":"2026-07-05T07:23:17.263462+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZJBZHZV","created_at":"2026-07-05T07:23:17.263462+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/EZJBZHZVEMEGZ7VOWY7OW67KFT","json":"https://pith.science/pith/EZJBZHZVEMEGZ7VOWY7OW67KFT.json","graph_json":"https://pith.science/api/pith-number/EZJBZHZVEMEGZ7VOWY7OW67KFT/graph.json","events_json":"https://pith.science/api/pith-number/EZJBZHZVEMEGZ7VOWY7OW67KFT/events.json","paper":"https://pith.science/paper/EZJBZHZV"},"agent_actions":{"view_html":"https://pith.science/pith/EZJBZHZVEMEGZ7VOWY7OW67KFT","download_json":"https://pith.science/pith/EZJBZHZVEMEGZ7VOWY7OW67KFT.json","view_paper":"https://pith.science/paper/EZJBZHZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07254&json=true","fetch_graph":"https://pith.science/api/pith-number/EZJBZHZVEMEGZ7VOWY7OW67KFT/graph.json","fetch_events":"https://pith.science/api/pith-number/EZJBZHZVEMEGZ7VOWY7OW67KFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZJBZHZVEMEGZ7VOWY7OW67KFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZJBZHZVEMEGZ7VOWY7OW67KFT/action/storage_attestation","attest_author":"https://pith.science/pith/EZJBZHZVEMEGZ7VOWY7OW67KFT/action/author_attestation","sign_citation":"https://pith.science/pith/EZJBZHZVEMEGZ7VOWY7OW67KFT/action/citation_signature","submit_replication":"https://pith.science/pith/EZJBZHZVEMEGZ7VOWY7OW67KFT/action/replication_record"}},"created_at":"2026-07-05T07:23:17.263462+00:00","updated_at":"2026-07-05T07:23:17.263462+00:00"}