{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5WSNGUE6KH57NPIT62DYHVV4EL","short_pith_number":"pith:5WSNGUE6","canonical_record":{"source":{"id":"2305.17415","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T08:41:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3a1be42491ae8c1c04aa2a07b37d6c1b7d8939097cb4a97d79d7d55fc97cd3b","abstract_canon_sha256":"d3b80e4bd32913b46fdefb9f1a154db74ea5169fda7d57db682d330aeb08991e"},"schema_version":"1.0"},"canonical_sha256":"eda4d3509e51fbf6bd13f68783d6bc22f56ba370f8bcf18f54e36568a42d8012","source":{"kind":"arxiv","id":"2305.17415","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17415","created_at":"2026-07-05T06:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17415v2","created_at":"2026-07-05T06:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17415","created_at":"2026-07-05T06:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"5WSNGUE6KH57","created_at":"2026-07-05T06:16:50Z"},{"alias_kind":"pith_short_16","alias_value":"5WSNGUE6KH57NPIT","created_at":"2026-07-05T06:16:50Z"},{"alias_kind":"pith_short_8","alias_value":"5WSNGUE6","created_at":"2026-07-05T06:16:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5WSNGUE6KH57NPIT62DYHVV4EL","target":"record","payload":{"canonical_record":{"source":{"id":"2305.17415","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T08:41:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3a1be42491ae8c1c04aa2a07b37d6c1b7d8939097cb4a97d79d7d55fc97cd3b","abstract_canon_sha256":"d3b80e4bd32913b46fdefb9f1a154db74ea5169fda7d57db682d330aeb08991e"},"schema_version":"1.0"},"canonical_sha256":"eda4d3509e51fbf6bd13f68783d6bc22f56ba370f8bcf18f54e36568a42d8012","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:50.830054Z","signature_b64":"+YP1WOPUnDn/yacQ6XaBCWdcajl6YgckanWj5qGYZ+jg2pKFPghi5UBGXvHt0BNke/lC0nzBgyZI0Rtu2VzVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eda4d3509e51fbf6bd13f68783d6bc22f56ba370f8bcf18f54e36568a42d8012","last_reissued_at":"2026-07-05T06:16:50.829569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:50.829569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.17415","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:16:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"573w+4Us3zH7MUZ9iRPJOVizOUsVvEuOFvzIJ5gkJWl4/JphtKqHsGN16PB1ux6N2BIkq3+/jRMuai6gbFIoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T13:48:44.193205Z"},"content_sha256":"ff9e3952e169c143bce2b8713426cc68a89c1a3d25b6aa958d4d72eb7c17b828","schema_version":"1.0","event_id":"sha256:ff9e3952e169c143bce2b8713426cc68a89c1a3d25b6aa958d4d72eb7c17b828"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5WSNGUE6KH57NPIT62DYHVV4EL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Better Text Image Translation with Multimodal Codebook","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Wang, Degen Huang, Jian Luan, Jiawei Yu, Jinsong Su, Wen Zhang, Xiang Li, Zhibin Lan","submitted_at":"2023-05-27T08:41:18Z","abstract_excerpt":"Text image translation (TIT) aims to translate the source texts embedded in the image to target translations, which has a wide range of applications and thus has important research value. However, current studies on TIT are confronted with two main bottlenecks: 1) this task lacks a publicly available TIT dataset, 2) dominant models are constructed in a cascaded manner, which tends to suffer from the error propagation of optical character recognition (OCR). In this work, we first annotate a Chinese-English TIT dataset named OCRMT30K, providing convenience for subsequent studies. Then, we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17415","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/2305.17415/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":"2026-07-05T06:16:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dc5HuQJpkDHjwDlDsInuvHYVzbFl3weyM+6VaoF/rwmVCzl6zi+uJQHW/ZZKIT51rsj+vO5KxpMZTqVhoMdKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T13:48:44.197313Z"},"content_sha256":"a35bb8cadc27ed13237faf365e597a7ae4dbb991608c6adfb0eae56223a429df","schema_version":"1.0","event_id":"sha256:a35bb8cadc27ed13237faf365e597a7ae4dbb991608c6adfb0eae56223a429df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL/bundle.json","state_url":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WSNGUE6KH57NPIT62DYHVV4EL/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":"2026-08-01T13:48:44Z","links":{"resolver":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL","bundle":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL/bundle.json","state":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WSNGUE6KH57NPIT62DYHVV4EL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5WSNGUE6KH57NPIT62DYHVV4EL","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":"d3b80e4bd32913b46fdefb9f1a154db74ea5169fda7d57db682d330aeb08991e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T08:41:18Z","title_canon_sha256":"e3a1be42491ae8c1c04aa2a07b37d6c1b7d8939097cb4a97d79d7d55fc97cd3b"},"schema_version":"1.0","source":{"id":"2305.17415","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17415","created_at":"2026-07-05T06:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17415v2","created_at":"2026-07-05T06:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17415","created_at":"2026-07-05T06:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"5WSNGUE6KH57","created_at":"2026-07-05T06:16:50Z"},{"alias_kind":"pith_short_16","alias_value":"5WSNGUE6KH57NPIT","created_at":"2026-07-05T06:16:50Z"},{"alias_kind":"pith_short_8","alias_value":"5WSNGUE6","created_at":"2026-07-05T06:16:50Z"}],"graph_snapshots":[{"event_id":"sha256:a35bb8cadc27ed13237faf365e597a7ae4dbb991608c6adfb0eae56223a429df","target":"graph","created_at":"2026-07-05T06:16:50Z","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/2305.17415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text image translation (TIT) aims to translate the source texts embedded in the image to target translations, which has a wide range of applications and thus has important research value. However, current studies on TIT are confronted with two main bottlenecks: 1) this task lacks a publicly available TIT dataset, 2) dominant models are constructed in a cascaded manner, which tends to suffer from the error propagation of optical character recognition (OCR). In this work, we first annotate a Chinese-English TIT dataset named OCRMT30K, providing convenience for subsequent studies. Then, we propos","authors_text":"Bin Wang, Degen Huang, Jian Luan, Jiawei Yu, Jinsong Su, Wen Zhang, Xiang Li, Zhibin Lan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T08:41:18Z","title":"Exploring Better Text Image Translation with Multimodal Codebook"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17415","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:ff9e3952e169c143bce2b8713426cc68a89c1a3d25b6aa958d4d72eb7c17b828","target":"record","created_at":"2026-07-05T06:16:50Z","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":"d3b80e4bd32913b46fdefb9f1a154db74ea5169fda7d57db682d330aeb08991e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T08:41:18Z","title_canon_sha256":"e3a1be42491ae8c1c04aa2a07b37d6c1b7d8939097cb4a97d79d7d55fc97cd3b"},"schema_version":"1.0","source":{"id":"2305.17415","kind":"arxiv","version":2}},"canonical_sha256":"eda4d3509e51fbf6bd13f68783d6bc22f56ba370f8bcf18f54e36568a42d8012","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eda4d3509e51fbf6bd13f68783d6bc22f56ba370f8bcf18f54e36568a42d8012","first_computed_at":"2026-07-05T06:16:50.829569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:50.829569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+YP1WOPUnDn/yacQ6XaBCWdcajl6YgckanWj5qGYZ+jg2pKFPghi5UBGXvHt0BNke/lC0nzBgyZI0Rtu2VzVDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:50.830054Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17415","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff9e3952e169c143bce2b8713426cc68a89c1a3d25b6aa958d4d72eb7c17b828","sha256:a35bb8cadc27ed13237faf365e597a7ae4dbb991608c6adfb0eae56223a429df"],"state_sha256":"1dd1ae180eb10aa12434f0b830e7c50f8577670e31dd8fb665959b0dd18e3e1a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4fVJ73AUJ+pB5eF1I9iKw0MWZKRr8Vp2hWnLQTpp+mzP4TGH1R5Uip8DlcCXTvkw9qrIMDX6JjH8lt4YrajSAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T13:48:44.204005Z","bundle_sha256":"10da4539798a3ea50b4bf1b7341037d5e05b8ca3ecfcd554990397b7b4aa698d"}}