{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M76U4JHXZM3P3SYGW5RANBC6HV","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":"fdb13b65745a2339525bccb716d2558ff0e466fe3ae09bf746269b763f382e98","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T13:13:48Z","title_canon_sha256":"d308b85a52e214aaf2ad2082c2320f1ca70dfcab225f5537f288497132484e15"},"schema_version":"1.0","source":{"id":"2305.14042","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14042","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14042v1","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14042","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"pith_short_12","alias_value":"M76U4JHXZM3P","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"pith_short_16","alias_value":"M76U4JHXZM3P3SYG","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"pith_short_8","alias_value":"M76U4JHX","created_at":"2026-07-05T06:13:00Z"}],"graph_snapshots":[{"event_id":"sha256:5c942ce8bb6b9c6642c5c0d1d86d8fd7810578bfeb3147e3881df3579aa1fdd8","target":"graph","created_at":"2026-07-05T06:13:00Z","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/2305.14042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In speech translation, leveraging multimodal data to improve model performance and address limitations of individual modalities has shown significant effectiveness. In this paper, we harness the complementary strengths of speech and text, which are disparate modalities. We observe three levels of modality gap between them, denoted by Modal input representation, Modal semantic, and Modal hidden states. To tackle these gaps, we propose \\textbf{F}use-\\textbf{S}peech-\\textbf{T}ext (\\textbf{FST}), a cross-modal model which supports three distinct input modalities for translation: speech, text, and ","authors_text":"Chengqi Zhao, Jian Tong, Rong Ye, Tao Wang, Wenbiao Yin, Zhicheng Liu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T13:13:48Z","title":"Improving speech translation by fusing speech and text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14042","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:a48b9b8e6e9a974e861fd886e39feeac02088d54777d72745ac29fb044357ae6","target":"record","created_at":"2026-07-05T06:13:00Z","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":"fdb13b65745a2339525bccb716d2558ff0e466fe3ae09bf746269b763f382e98","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T13:13:48Z","title_canon_sha256":"d308b85a52e214aaf2ad2082c2320f1ca70dfcab225f5537f288497132484e15"},"schema_version":"1.0","source":{"id":"2305.14042","kind":"arxiv","version":1}},"canonical_sha256":"67fd4e24f7cb36fdcb06b76206845e3d532322c9ed22b0cf80fe70ca236f0034","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67fd4e24f7cb36fdcb06b76206845e3d532322c9ed22b0cf80fe70ca236f0034","first_computed_at":"2026-07-05T06:13:00.535273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:00.535273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QVPQdvEvvLrU/+WCg1GcozI2lGshtk38zjh2aI72gxv3nhif2mnsUw68mHJxUG6zrdhndKW0Y/mfyEALadIVBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:00.535711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14042","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a48b9b8e6e9a974e861fd886e39feeac02088d54777d72745ac29fb044357ae6","sha256:5c942ce8bb6b9c6642c5c0d1d86d8fd7810578bfeb3147e3881df3579aa1fdd8"],"state_sha256":"97f0927ef000584cc2c7ebef0ee05ace7e8fb686b061560adac389ebc1a85e53"}