{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YNHEM4NLGEJAG5BR2OMWXTZZU2","short_pith_number":"pith:YNHEM4NL","canonical_record":{"source":{"id":"2406.00505","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-01T17:27:34Z","cross_cats_sorted":[],"title_canon_sha256":"9b1604652a1ed5a3802a56aaa88f42176619388f3ccfb1bb9efefd910de4b179","abstract_canon_sha256":"98b02d770800183456b9386743c013a7b28a03b5a18b74cf9e42808bd1f99a42"},"schema_version":"1.0"},"canonical_sha256":"c34e4671ab3112037431d3996bcf39a6afdb84242e7eb71b552636cbc7cdfd19","source":{"kind":"arxiv","id":"2406.00505","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00505","created_at":"2026-07-05T09:24:35Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00505v2","created_at":"2026-07-05T09:24:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00505","created_at":"2026-07-05T09:24:35Z"},{"alias_kind":"pith_short_12","alias_value":"YNHEM4NLGEJA","created_at":"2026-07-05T09:24:35Z"},{"alias_kind":"pith_short_16","alias_value":"YNHEM4NLGEJAG5BR","created_at":"2026-07-05T09:24:35Z"},{"alias_kind":"pith_short_8","alias_value":"YNHEM4NL","created_at":"2026-07-05T09:24:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YNHEM4NLGEJAG5BR2OMWXTZZU2","target":"record","payload":{"canonical_record":{"source":{"id":"2406.00505","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-01T17:27:34Z","cross_cats_sorted":[],"title_canon_sha256":"9b1604652a1ed5a3802a56aaa88f42176619388f3ccfb1bb9efefd910de4b179","abstract_canon_sha256":"98b02d770800183456b9386743c013a7b28a03b5a18b74cf9e42808bd1f99a42"},"schema_version":"1.0"},"canonical_sha256":"c34e4671ab3112037431d3996bcf39a6afdb84242e7eb71b552636cbc7cdfd19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:35.840892Z","signature_b64":"gWFuj5RWbwbx5HbJs831825JR4CQsDiuV/hqXT907YKJWkja+x49GU2Fkzx1e7aEWjzQlP37njD/svWwCH9FBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c34e4671ab3112037431d3996bcf39a6afdb84242e7eb71b552636cbc7cdfd19","last_reissued_at":"2026-07-05T09:24:35.840369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:35.840369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.00505","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":"2026-07-05T09:24:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FhnM6mWAKkZLNWQ+exWaqnLieXBRRpytE97n6D9wPxLzHKf8nbIxP7GW8Yg7yw1U+lGm1oZAklorivQ7KD/9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:38:59.772542Z"},"content_sha256":"c7dc8dadc6d72bbb40ac89f5592255ce469e744913a5e8cc168cc8dc7e256480","schema_version":"1.0","event_id":"sha256:c7dc8dadc6d72bbb40ac89f5592255ce469e744913a5e8cc168cc8dc7e256480"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YNHEM4NLGEJAG5BR2OMWXTZZU2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Text Generation on Images with Synthetic Captions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joy Song, Jun Young Koh, Sang Hyun Park","submitted_at":"2024-06-01T17:27:34Z","abstract_excerpt":"The recent emergence of latent diffusion models such as SDXL and SD 1.5 has shown significant capability in generating highly detailed and realistic images. Despite their remarkable ability to produce images, generating accurate text within images still remains a challenging task. In this paper, we examine the validity of fine-tuning approaches in generating legible text within the image. We propose a low-cost approach by leveraging SDXL without any time-consuming training on large-scale datasets. The proposed strategy employs a fine-tuning technique that examines the effects of data refinemen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00505","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/2406.00505/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":"2026-07-05T09:24:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/YSzxZCbhwwmDy8jEp4Z4+J9wWM8yKaCChhWWVxeRkEA/JNH+oMnxrLDpFp208awQxVZTTPuKD2JUfxQXddtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:38:59.773598Z"},"content_sha256":"99851e602cbf3e6c1ca3e1da050020210cb95f0cebc2f9b5e1fde747b08e9181","schema_version":"1.0","event_id":"sha256:99851e602cbf3e6c1ca3e1da050020210cb95f0cebc2f9b5e1fde747b08e9181"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YNHEM4NLGEJAG5BR2OMWXTZZU2/bundle.json","state_url":"https://pith.science/pith/YNHEM4NLGEJAG5BR2OMWXTZZU2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YNHEM4NLGEJAG5BR2OMWXTZZU2/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":"2026-08-10T12:38:59Z","links":{"resolver":"https://pith.science/pith/YNHEM4NLGEJAG5BR2OMWXTZZU2","bundle":"https://pith.science/pith/YNHEM4NLGEJAG5BR2OMWXTZZU2/bundle.json","state":"https://pith.science/pith/YNHEM4NLGEJAG5BR2OMWXTZZU2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YNHEM4NLGEJAG5BR2OMWXTZZU2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YNHEM4NLGEJAG5BR2OMWXTZZU2","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":"98b02d770800183456b9386743c013a7b28a03b5a18b74cf9e42808bd1f99a42","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-01T17:27:34Z","title_canon_sha256":"9b1604652a1ed5a3802a56aaa88f42176619388f3ccfb1bb9efefd910de4b179"},"schema_version":"1.0","source":{"id":"2406.00505","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00505","created_at":"2026-07-05T09:24:35Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00505v2","created_at":"2026-07-05T09:24:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00505","created_at":"2026-07-05T09:24:35Z"},{"alias_kind":"pith_short_12","alias_value":"YNHEM4NLGEJA","created_at":"2026-07-05T09:24:35Z"},{"alias_kind":"pith_short_16","alias_value":"YNHEM4NLGEJAG5BR","created_at":"2026-07-05T09:24:35Z"},{"alias_kind":"pith_short_8","alias_value":"YNHEM4NL","created_at":"2026-07-05T09:24:35Z"}],"graph_snapshots":[{"event_id":"sha256:99851e602cbf3e6c1ca3e1da050020210cb95f0cebc2f9b5e1fde747b08e9181","target":"graph","created_at":"2026-07-05T09:24:35Z","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/2406.00505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent emergence of latent diffusion models such as SDXL and SD 1.5 has shown significant capability in generating highly detailed and realistic images. Despite their remarkable ability to produce images, generating accurate text within images still remains a challenging task. In this paper, we examine the validity of fine-tuning approaches in generating legible text within the image. We propose a low-cost approach by leveraging SDXL without any time-consuming training on large-scale datasets. The proposed strategy employs a fine-tuning technique that examines the effects of data refinemen","authors_text":"Joy Song, Jun Young Koh, Sang Hyun Park","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-01T17:27:34Z","title":"Improving Text Generation on Images with Synthetic Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00505","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:c7dc8dadc6d72bbb40ac89f5592255ce469e744913a5e8cc168cc8dc7e256480","target":"record","created_at":"2026-07-05T09:24:35Z","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":"98b02d770800183456b9386743c013a7b28a03b5a18b74cf9e42808bd1f99a42","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-01T17:27:34Z","title_canon_sha256":"9b1604652a1ed5a3802a56aaa88f42176619388f3ccfb1bb9efefd910de4b179"},"schema_version":"1.0","source":{"id":"2406.00505","kind":"arxiv","version":2}},"canonical_sha256":"c34e4671ab3112037431d3996bcf39a6afdb84242e7eb71b552636cbc7cdfd19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c34e4671ab3112037431d3996bcf39a6afdb84242e7eb71b552636cbc7cdfd19","first_computed_at":"2026-07-05T09:24:35.840369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:35.840369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gWFuj5RWbwbx5HbJs831825JR4CQsDiuV/hqXT907YKJWkja+x49GU2Fkzx1e7aEWjzQlP37njD/svWwCH9FBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:35.840892Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00505","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7dc8dadc6d72bbb40ac89f5592255ce469e744913a5e8cc168cc8dc7e256480","sha256:99851e602cbf3e6c1ca3e1da050020210cb95f0cebc2f9b5e1fde747b08e9181"],"state_sha256":"a5a344cbb104753f88df0a74c42eddcffb555d9150836938919f95e8483718a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ehu5KGQZ+naU1c96+StRM8wgeVnuPjzp8JxUMvWZanEA3hAyyomgIXm94QSk8dSUHRWWFMycY5bohfgVKE1JDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:38:59.780882Z","bundle_sha256":"3b22bdf92b6d035067b1e14b991b6c6dbb7a65e07bba481cfe3cec4b75c60909"}}