{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WTVWGK7H47R74QGVFDEDKIGJH5","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":"e9924a80a75ab3eaa7c099361e1012eef9cc19ebd8038f0d27a19685aef54e3d","cross_cats_sorted":["cs.AI","cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-25T07:46:57Z","title_canon_sha256":"37f4c1436bca86e959b248a18aae4ddd9ea6aba430e7ccc1f248e2827aa1a21f"},"schema_version":"1.0","source":{"id":"2402.16021","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16021","created_at":"2026-07-05T11:16:48Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16021v2","created_at":"2026-07-05T11:16:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16021","created_at":"2026-07-05T11:16:48Z"},{"alias_kind":"pith_short_12","alias_value":"WTVWGK7H47R7","created_at":"2026-07-05T11:16:48Z"},{"alias_kind":"pith_short_16","alias_value":"WTVWGK7H47R74QGV","created_at":"2026-07-05T11:16:48Z"},{"alias_kind":"pith_short_8","alias_value":"WTVWGK7H","created_at":"2026-07-05T11:16:48Z"}],"graph_snapshots":[{"event_id":"sha256:1d5107b19edc7350d37edac8add959ee897c016af760487ce749bf379d0a67b4","target":"graph","created_at":"2026-07-05T11:16:48Z","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/2402.16021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The capability to jointly process multi-modal information is becoming an essential task. However, the limited number of paired multi-modal data and the large computational requirements in multi-modal learning hinder the development. We propose a novel Tri-Modal Translation (TMT) model that translates between arbitrary modalities spanning speech, image, and text. We introduce a novel viewpoint, where we interpret different modalities as different languages, and treat multi-modal translation as a well-established machine translation problem. To this end, we tokenize speech and image data into di","authors_text":"Hyeongseop Rha, Jee-weon Jung, Minsu Kim, Shinji Watanabe, Siddhant Arora, Soumi Maiti, Xuankai Chang, Yong Man Ro","cross_cats":["cs.AI","cs.CV","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-25T07:46:57Z","title":"TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16021","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":"sha256:10d0ec35b0925fd13aff394efde813b6afeb3fc14b248ddb4751905b2d90b22c","target":"record","created_at":"2026-07-05T11:16:48Z","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":"e9924a80a75ab3eaa7c099361e1012eef9cc19ebd8038f0d27a19685aef54e3d","cross_cats_sorted":["cs.AI","cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-25T07:46:57Z","title_canon_sha256":"37f4c1436bca86e959b248a18aae4ddd9ea6aba430e7ccc1f248e2827aa1a21f"},"schema_version":"1.0","source":{"id":"2402.16021","kind":"arxiv","version":2}},"canonical_sha256":"b4eb632be7e7e3fe40d528c83520c93f6b9ad8cb1bc7a3f566c56a5d813fa2cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4eb632be7e7e3fe40d528c83520c93f6b9ad8cb1bc7a3f566c56a5d813fa2cd","first_computed_at":"2026-07-05T11:16:48.743805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:48.743805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RhUC7ojIPe82C2k4gKpJdYsID4P3nqLc5QU6TcDWdB/n0NlvHXraHVnnPn1xa1vtBR/moVyRIJAqJuGH8mrJCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:48.744343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16021","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10d0ec35b0925fd13aff394efde813b6afeb3fc14b248ddb4751905b2d90b22c","sha256:1d5107b19edc7350d37edac8add959ee897c016af760487ce749bf379d0a67b4"],"state_sha256":"4a762c0ba65d8c5bb70ffe64ef2f6f15b84b543a5cf81e5b787b8e2af5c6bfb9"}