{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z2SD7AGAJTNF26GPZCEWB7VH3K","short_pith_number":"pith:Z2SD7AGA","schema_version":"1.0","canonical_sha256":"cea43f80c04cda5d78cfc88960fea7da9ec9352cd3a217bf07ed159aba7de607","source":{"kind":"arxiv","id":"2507.07306","version":1},"attestation_state":"computed","paper":{"title":"ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.AI","authors_text":"Ao Sun, Ching Wing Kwok, Jiaen Liu, Jianyuan Zhan, Sheng Fu, Sicheng Lai, Takatomo Saito, Wei Dai, Xudong Xiao, Yian Wang, Yichen Lu, Zongheng Wu","submitted_at":"2025-07-09T22:05:46Z","abstract_excerpt":"LLM-based translation agents have achieved highly human-like translation results and are capable of handling longer and more complex contexts with greater efficiency. However, they are typically limited to text-only inputs. In this paper, we introduce ViDove, a translation agent system designed for multimodal input. Inspired by the workflow of human translators, ViDove leverages visual and contextual background information to enhance the translation process. Additionally, we integrate a multimodal memory system and long-short term memory modules enriched with domain-specific knowledge, enablin"},"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":"2507.07306","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-09T22:05:46Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"c2b8026a8da13d9b3c5b26bed65a7086bb7b54783a4273a1138574f448595ca8","abstract_canon_sha256":"ffabc48a8c3d782399bba9ad8f984f1b0890d939c5bc9bd779210f8df4e3e829"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:55.555545Z","signature_b64":"AobFFbgMFby9p9dQl+iXd9G1NJAxVDQ7IDg9rT2UNoAyTnYRU1G9NmHIDWh8fMu2ujsFGKFK+ohMbUxP1BjbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cea43f80c04cda5d78cfc88960fea7da9ec9352cd3a217bf07ed159aba7de607","last_reissued_at":"2026-07-05T11:34:55.555043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:55.555043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.AI","authors_text":"Ao Sun, Ching Wing Kwok, Jiaen Liu, Jianyuan Zhan, Sheng Fu, Sicheng Lai, Takatomo Saito, Wei Dai, Xudong Xiao, Yian Wang, Yichen Lu, Zongheng Wu","submitted_at":"2025-07-09T22:05:46Z","abstract_excerpt":"LLM-based translation agents have achieved highly human-like translation results and are capable of handling longer and more complex contexts with greater efficiency. However, they are typically limited to text-only inputs. In this paper, we introduce ViDove, a translation agent system designed for multimodal input. Inspired by the workflow of human translators, ViDove leverages visual and contextual background information to enhance the translation process. Additionally, we integrate a multimodal memory system and long-short term memory modules enriched with domain-specific knowledge, enablin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07306","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/2507.07306/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":"2507.07306","created_at":"2026-07-05T11:34:55.555097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07306v1","created_at":"2026-07-05T11:34:55.555097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07306","created_at":"2026-07-05T11:34:55.555097+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2SD7AGAJTNF","created_at":"2026-07-05T11:34:55.555097+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2SD7AGAJTNF26GP","created_at":"2026-07-05T11:34:55.555097+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2SD7AGA","created_at":"2026-07-05T11:34:55.555097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02035","citing_title":"VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z2SD7AGAJTNF26GPZCEWB7VH3K","json":"https://pith.science/pith/Z2SD7AGAJTNF26GPZCEWB7VH3K.json","graph_json":"https://pith.science/api/pith-number/Z2SD7AGAJTNF26GPZCEWB7VH3K/graph.json","events_json":"https://pith.science/api/pith-number/Z2SD7AGAJTNF26GPZCEWB7VH3K/events.json","paper":"https://pith.science/paper/Z2SD7AGA"},"agent_actions":{"view_html":"https://pith.science/pith/Z2SD7AGAJTNF26GPZCEWB7VH3K","download_json":"https://pith.science/pith/Z2SD7AGAJTNF26GPZCEWB7VH3K.json","view_paper":"https://pith.science/paper/Z2SD7AGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07306&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2SD7AGAJTNF26GPZCEWB7VH3K/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2SD7AGAJTNF26GPZCEWB7VH3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2SD7AGAJTNF26GPZCEWB7VH3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2SD7AGAJTNF26GPZCEWB7VH3K/action/storage_attestation","attest_author":"https://pith.science/pith/Z2SD7AGAJTNF26GPZCEWB7VH3K/action/author_attestation","sign_citation":"https://pith.science/pith/Z2SD7AGAJTNF26GPZCEWB7VH3K/action/citation_signature","submit_replication":"https://pith.science/pith/Z2SD7AGAJTNF26GPZCEWB7VH3K/action/replication_record"}},"created_at":"2026-07-05T11:34:55.555097+00:00","updated_at":"2026-07-05T11:34:55.555097+00:00"}