{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z2SD7AGAJTNF26GPZCEWB7VH3K","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":"ffabc48a8c3d782399bba9ad8f984f1b0890d939c5bc9bd779210f8df4e3e829","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-09T22:05:46Z","title_canon_sha256":"c2b8026a8da13d9b3c5b26bed65a7086bb7b54783a4273a1138574f448595ca8"},"schema_version":"1.0","source":{"id":"2507.07306","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07306","created_at":"2026-07-05T11:34:55Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07306v1","created_at":"2026-07-05T11:34:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07306","created_at":"2026-07-05T11:34:55Z"},{"alias_kind":"pith_short_12","alias_value":"Z2SD7AGAJTNF","created_at":"2026-07-05T11:34:55Z"},{"alias_kind":"pith_short_16","alias_value":"Z2SD7AGAJTNF26GP","created_at":"2026-07-05T11:34:55Z"},{"alias_kind":"pith_short_8","alias_value":"Z2SD7AGA","created_at":"2026-07-05T11:34:55Z"}],"graph_snapshots":[{"event_id":"sha256:47fce9141014d579c7f5d2ca5d88c0603533fc9d9f65c90499ad7d15494d2cc5","target":"graph","created_at":"2026-07-05T11:34:55Z","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/2507.07306/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-09T22:05:46Z","title":"ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07306","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:ec8bbce3a02534d23fe1c542ebb5d47ebd23e26e46b020ba2480e32fa2481d3c","target":"record","created_at":"2026-07-05T11:34:55Z","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":"ffabc48a8c3d782399bba9ad8f984f1b0890d939c5bc9bd779210f8df4e3e829","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-09T22:05:46Z","title_canon_sha256":"c2b8026a8da13d9b3c5b26bed65a7086bb7b54783a4273a1138574f448595ca8"},"schema_version":"1.0","source":{"id":"2507.07306","kind":"arxiv","version":1}},"canonical_sha256":"cea43f80c04cda5d78cfc88960fea7da9ec9352cd3a217bf07ed159aba7de607","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cea43f80c04cda5d78cfc88960fea7da9ec9352cd3a217bf07ed159aba7de607","first_computed_at":"2026-07-05T11:34:55.555043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:55.555043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AobFFbgMFby9p9dQl+iXd9G1NJAxVDQ7IDg9rT2UNoAyTnYRU1G9NmHIDWh8fMu2ujsFGKFK+ohMbUxP1BjbCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:55.555545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07306","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec8bbce3a02534d23fe1c542ebb5d47ebd23e26e46b020ba2480e32fa2481d3c","sha256:47fce9141014d579c7f5d2ca5d88c0603533fc9d9f65c90499ad7d15494d2cc5"],"state_sha256":"e6ff244c074ca14d25bf5c52e0a9af9257a19bf37a4b9c04bdf6319fd8a20923"}