{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WTVWGK7H47R74QGVFDEDKIGJH5","short_pith_number":"pith:WTVWGK7H","schema_version":"1.0","canonical_sha256":"b4eb632be7e7e3fe40d528c83520c93f6b9ad8cb1bc7a3f566c56a5d813fa2cd","source":{"kind":"arxiv","id":"2402.16021","version":2},"attestation_state":"computed","paper":{"title":"TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hyeongseop Rha, Jee-weon Jung, Minsu Kim, Shinji Watanabe, Siddhant Arora, Soumi Maiti, Xuankai Chang, Yong Man Ro","submitted_at":"2024-02-25T07:46:57Z","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"},"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":"2402.16021","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-25T07:46:57Z","cross_cats_sorted":["cs.AI","cs.CV","eess.AS"],"title_canon_sha256":"37f4c1436bca86e959b248a18aae4ddd9ea6aba430e7ccc1f248e2827aa1a21f","abstract_canon_sha256":"e9924a80a75ab3eaa7c099361e1012eef9cc19ebd8038f0d27a19685aef54e3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:48.744343Z","signature_b64":"RhUC7ojIPe82C2k4gKpJdYsID4P3nqLc5QU6TcDWdB/n0NlvHXraHVnnPn1xa1vtBR/moVyRIJAqJuGH8mrJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4eb632be7e7e3fe40d528c83520c93f6b9ad8cb1bc7a3f566c56a5d813fa2cd","last_reissued_at":"2026-07-05T11:16:48.743805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:48.743805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hyeongseop Rha, Jee-weon Jung, Minsu Kim, Shinji Watanabe, Siddhant Arora, Soumi Maiti, Xuankai Chang, Yong Man Ro","submitted_at":"2024-02-25T07:46:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16021","kind":"arxiv","version":2},"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/2402.16021/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":"2402.16021","created_at":"2026-07-05T11:16:48.743867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16021v2","created_at":"2026-07-05T11:16:48.743867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16021","created_at":"2026-07-05T11:16:48.743867+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTVWGK7H47R7","created_at":"2026-07-05T11:16:48.743867+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTVWGK7H47R74QGV","created_at":"2026-07-05T11:16:48.743867+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTVWGK7H","created_at":"2026-07-05T11:16:48.743867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.12863","citing_title":"Unified Cross-modal Translation of Score Images, Symbolic Music, and Performance Audio","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WTVWGK7H47R74QGVFDEDKIGJH5","json":"https://pith.science/pith/WTVWGK7H47R74QGVFDEDKIGJH5.json","graph_json":"https://pith.science/api/pith-number/WTVWGK7H47R74QGVFDEDKIGJH5/graph.json","events_json":"https://pith.science/api/pith-number/WTVWGK7H47R74QGVFDEDKIGJH5/events.json","paper":"https://pith.science/paper/WTVWGK7H"},"agent_actions":{"view_html":"https://pith.science/pith/WTVWGK7H47R74QGVFDEDKIGJH5","download_json":"https://pith.science/pith/WTVWGK7H47R74QGVFDEDKIGJH5.json","view_paper":"https://pith.science/paper/WTVWGK7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16021&json=true","fetch_graph":"https://pith.science/api/pith-number/WTVWGK7H47R74QGVFDEDKIGJH5/graph.json","fetch_events":"https://pith.science/api/pith-number/WTVWGK7H47R74QGVFDEDKIGJH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTVWGK7H47R74QGVFDEDKIGJH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTVWGK7H47R74QGVFDEDKIGJH5/action/storage_attestation","attest_author":"https://pith.science/pith/WTVWGK7H47R74QGVFDEDKIGJH5/action/author_attestation","sign_citation":"https://pith.science/pith/WTVWGK7H47R74QGVFDEDKIGJH5/action/citation_signature","submit_replication":"https://pith.science/pith/WTVWGK7H47R74QGVFDEDKIGJH5/action/replication_record"}},"created_at":"2026-07-05T11:16:48.743867+00:00","updated_at":"2026-07-05T11:16:48.743867+00:00"}