{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GBKJBII6N4SW7DVKLUTSZBECZ4","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":"0ad5c0a83d3c71bf72af742c885d57c24e9d8982496db6226279544dbbd67b9f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T10:37:56Z","title_canon_sha256":"f90232fe7f990c451c54ea5486f5da1b777c734de390d00464f3d2b1b38a8de6"},"schema_version":"1.0","source":{"id":"2305.11579","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11579","created_at":"2026-07-05T06:19:04Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11579v2","created_at":"2026-07-05T06:19:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11579","created_at":"2026-07-05T06:19:04Z"},{"alias_kind":"pith_short_12","alias_value":"GBKJBII6N4SW","created_at":"2026-07-05T06:19:04Z"},{"alias_kind":"pith_short_16","alias_value":"GBKJBII6N4SW7DVK","created_at":"2026-07-05T06:19:04Z"},{"alias_kind":"pith_short_8","alias_value":"GBKJBII6","created_at":"2026-07-05T06:19:04Z"}],"graph_snapshots":[{"event_id":"sha256:df76f2b8cbf6d351d5777ac19aace316f334002f97d7a8a132a267b9160b559a","target":"graph","created_at":"2026-07-05T06:19:04Z","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/2305.11579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, speech-text pre-training methods have shown remarkable success in many speech and natural language processing tasks. However, most previous pre-trained models are usually tailored for one or two specific tasks, but fail to conquer a wide range of speech-text tasks. In addition, existing speech-text pre-training methods fail to explore the contextual information within a dialogue to enrich utterance representations. In this paper, we propose Speech-text dialog Pre-training for spoken dialog understanding with ExpliCiT cRoss-Modal Alignment (SPECTRA), which is the first-ever speech-tex","authors_text":"Chao Wang, Fei Huang, Haoyu Gao, Min Yang, Tianshu Yu, Ting-En Lin, Wentao Ma, Yongbin Li, Yuchuan Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T10:37:56Z","title":"Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11579","kind":"arxiv","version":2},"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:fa5407ddfaafed025e2c5c294755e6b1c96bb95c7cf100bdfec2995818ce3e6e","target":"record","created_at":"2026-07-05T06:19:04Z","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":"0ad5c0a83d3c71bf72af742c885d57c24e9d8982496db6226279544dbbd67b9f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T10:37:56Z","title_canon_sha256":"f90232fe7f990c451c54ea5486f5da1b777c734de390d00464f3d2b1b38a8de6"},"schema_version":"1.0","source":{"id":"2305.11579","kind":"arxiv","version":2}},"canonical_sha256":"305490a11e6f256f8eaa5d272c8482cf35ad434f6e2016c6a78c368cc01dadd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"305490a11e6f256f8eaa5d272c8482cf35ad434f6e2016c6a78c368cc01dadd4","first_computed_at":"2026-07-05T06:19:04.313861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:04.313861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D+8axNZcsC7rYxMGYAa8UpmPwrYn/NO9BICzwkefpJsvKwnL0PP1MD7h6TBY5ygifHc8KsA3ogGxinNyo170Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:04.314401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11579","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa5407ddfaafed025e2c5c294755e6b1c96bb95c7cf100bdfec2995818ce3e6e","sha256:df76f2b8cbf6d351d5777ac19aace316f334002f97d7a8a132a267b9160b559a"],"state_sha256":"c6292697bfe5a623a435768e550a25410c1d379fbb769d182ce0b5344516142d"}