{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3Y7MRK2TWWN2BI3VW654X2ISY7","short_pith_number":"pith:3Y7MRK2T","canonical_record":{"source":{"id":"2606.24333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T09:11:24Z","cross_cats_sorted":[],"title_canon_sha256":"485c246f02795c0ce7170f6365e110cf2244f489caa5d9c0d474b656e62cab87","abstract_canon_sha256":"9b0d6d376e5077239dec068848d5fad08b8432722898106c9778635a95d89ab8"},"schema_version":"1.0"},"canonical_sha256":"de3ec8ab53b59ba0a375b7bbcbe912c7f8ac54e9b5e0d99c8fcaf086cc55cd99","source":{"kind":"arxiv","id":"2606.24333","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24333","created_at":"2026-06-24T01:14:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24333v1","created_at":"2026-06-24T01:14:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24333","created_at":"2026-06-24T01:14:50Z"},{"alias_kind":"pith_short_12","alias_value":"3Y7MRK2TWWN2","created_at":"2026-06-24T01:14:50Z"},{"alias_kind":"pith_short_16","alias_value":"3Y7MRK2TWWN2BI3V","created_at":"2026-06-24T01:14:50Z"},{"alias_kind":"pith_short_8","alias_value":"3Y7MRK2T","created_at":"2026-06-24T01:14:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3Y7MRK2TWWN2BI3VW654X2ISY7","target":"record","payload":{"canonical_record":{"source":{"id":"2606.24333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T09:11:24Z","cross_cats_sorted":[],"title_canon_sha256":"485c246f02795c0ce7170f6365e110cf2244f489caa5d9c0d474b656e62cab87","abstract_canon_sha256":"9b0d6d376e5077239dec068848d5fad08b8432722898106c9778635a95d89ab8"},"schema_version":"1.0"},"canonical_sha256":"de3ec8ab53b59ba0a375b7bbcbe912c7f8ac54e9b5e0d99c8fcaf086cc55cd99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:50.383428Z","signature_b64":"I1t99hWlruZg7hBxza5r81811N8UY+GPf0QkcAr8uFK08A47UtHosfHnYLgFtSy1H2Ewkgvb+nI0Dljge8wECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de3ec8ab53b59ba0a375b7bbcbe912c7f8ac54e9b5e0d99c8fcaf086cc55cd99","last_reissued_at":"2026-06-24T01:14:50.383001Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:50.383001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.24333","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bkXH+S7y+f6wqPCa9vBreHq6/41gt63LYGXWb6tybNfRgNeSSanxIZlCzMwuHl6EH68wDR2BdnrFBGdMkleRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T21:28:06.994493Z"},"content_sha256":"bfb4b27227669112c5624b8e86c900dfec9bcdcaa92f779f1c5b75f4192884fb","schema_version":"1.0","event_id":"sha256:bfb4b27227669112c5624b8e86c900dfec9bcdcaa92f779f1c5b75f4192884fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3Y7MRK2TWWN2BI3VW654X2ISY7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Ma, Jiahao Lyu, Jiahui Yang, Jian Luan, Pei Fu, Shaojie Zhang, Yu Zhou, Zhenbo Luo, Zhenhang Li","submitted_at":"2026-06-23T09:11:24Z","abstract_excerpt":"In-Image Machine Translation (IIMT) aims to translate scene text in an image and render the translated text back into the original regions while preserving the overall visual appearance. Recent unified multimodal models provide a promising solution by combining visual-text understanding and image generation within a single framework. However, directly adapting such models to IIMT remains challenging. In particular, they often suffer from understanding-generation conflicts, where the translation inferred during understanding is inconsistent with the text supervision used in generation, and spat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24333","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/2606.24333/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1jZBiJ6ykIx+8a6Rp0m0cODvMUKsO4PSOWQlBRsB049CIsnzr4kIGwGeIV8+eBAr4nuh4LECpBJI0M4NWgqgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T21:28:06.994854Z"},"content_sha256":"e33952cc49cd42d55883f115580ed39e00ff1b53cbceec8cfd902f422d76019a","schema_version":"1.0","event_id":"sha256:e33952cc49cd42d55883f115580ed39e00ff1b53cbceec8cfd902f422d76019a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3Y7MRK2TWWN2BI3VW654X2ISY7/bundle.json","state_url":"https://pith.science/pith/3Y7MRK2TWWN2BI3VW654X2ISY7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3Y7MRK2TWWN2BI3VW654X2ISY7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-27T21:28:06Z","links":{"resolver":"https://pith.science/pith/3Y7MRK2TWWN2BI3VW654X2ISY7","bundle":"https://pith.science/pith/3Y7MRK2TWWN2BI3VW654X2ISY7/bundle.json","state":"https://pith.science/pith/3Y7MRK2TWWN2BI3VW654X2ISY7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3Y7MRK2TWWN2BI3VW654X2ISY7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3Y7MRK2TWWN2BI3VW654X2ISY7","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":"9b0d6d376e5077239dec068848d5fad08b8432722898106c9778635a95d89ab8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T09:11:24Z","title_canon_sha256":"485c246f02795c0ce7170f6365e110cf2244f489caa5d9c0d474b656e62cab87"},"schema_version":"1.0","source":{"id":"2606.24333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24333","created_at":"2026-06-24T01:14:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24333v1","created_at":"2026-06-24T01:14:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24333","created_at":"2026-06-24T01:14:50Z"},{"alias_kind":"pith_short_12","alias_value":"3Y7MRK2TWWN2","created_at":"2026-06-24T01:14:50Z"},{"alias_kind":"pith_short_16","alias_value":"3Y7MRK2TWWN2BI3V","created_at":"2026-06-24T01:14:50Z"},{"alias_kind":"pith_short_8","alias_value":"3Y7MRK2T","created_at":"2026-06-24T01:14:50Z"}],"graph_snapshots":[{"event_id":"sha256:e33952cc49cd42d55883f115580ed39e00ff1b53cbceec8cfd902f422d76019a","target":"graph","created_at":"2026-06-24T01:14:50Z","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/2606.24333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-Image Machine Translation (IIMT) aims to translate scene text in an image and render the translated text back into the original regions while preserving the overall visual appearance. Recent unified multimodal models provide a promising solution by combining visual-text understanding and image generation within a single framework. However, directly adapting such models to IIMT remains challenging. In particular, they often suffer from understanding-generation conflicts, where the translation inferred during understanding is inconsistent with the text supervision used in generation, and spat","authors_text":"Can Ma, Jiahao Lyu, Jiahui Yang, Jian Luan, Pei Fu, Shaojie Zhang, Yu Zhou, Zhenbo Luo, Zhenhang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T09:11:24Z","title":"UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24333","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:bfb4b27227669112c5624b8e86c900dfec9bcdcaa92f779f1c5b75f4192884fb","target":"record","created_at":"2026-06-24T01:14:50Z","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":"9b0d6d376e5077239dec068848d5fad08b8432722898106c9778635a95d89ab8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T09:11:24Z","title_canon_sha256":"485c246f02795c0ce7170f6365e110cf2244f489caa5d9c0d474b656e62cab87"},"schema_version":"1.0","source":{"id":"2606.24333","kind":"arxiv","version":1}},"canonical_sha256":"de3ec8ab53b59ba0a375b7bbcbe912c7f8ac54e9b5e0d99c8fcaf086cc55cd99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de3ec8ab53b59ba0a375b7bbcbe912c7f8ac54e9b5e0d99c8fcaf086cc55cd99","first_computed_at":"2026-06-24T01:14:50.383001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:50.383001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I1t99hWlruZg7hBxza5r81811N8UY+GPf0QkcAr8uFK08A47UtHosfHnYLgFtSy1H2Ewkgvb+nI0Dljge8wECQ==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:50.383428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfb4b27227669112c5624b8e86c900dfec9bcdcaa92f779f1c5b75f4192884fb","sha256:e33952cc49cd42d55883f115580ed39e00ff1b53cbceec8cfd902f422d76019a"],"state_sha256":"8beba543e8b85acfb3a2ca38db0d41c8f4c7bcd2371cdc662d4078c6e18d9500"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9E0/6M3QDma8D08Sjar7gkrkW0FBZXq+3RMrsEnVmvoaIHWFsWFbB967Rb13hiHL4ueVT57QTarb2ytm2Qi7Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T21:28:06.997030Z","bundle_sha256":"a76f2915bd612f9bb1d2a1e7dd743df60a5eac293b598dc9a49eec6e6a9c66c4"}}