{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PQUBL2X7H477YEIWELIDA6HDHU","short_pith_number":"pith:PQUBL2X7","canonical_record":{"source":{"id":"2410.04439","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T10:25:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff51eda884a1b6e278b3fbeb46c0ed3dac784f4c31b747a38cf8da61cb6690fc","abstract_canon_sha256":"c37493e3d5f915d987a9d52f25bd534832b8f32b261494f342411434d575f6c8"},"schema_version":"1.0"},"canonical_sha256":"7c2815eaff3f3ffc111622d03078e33d2a118ae0e56ce32134192f31902f49a7","source":{"kind":"arxiv","id":"2410.04439","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04439","created_at":"2026-07-05T09:16:34Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04439v1","created_at":"2026-07-05T09:16:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04439","created_at":"2026-07-05T09:16:34Z"},{"alias_kind":"pith_short_12","alias_value":"PQUBL2X7H477","created_at":"2026-07-05T09:16:34Z"},{"alias_kind":"pith_short_16","alias_value":"PQUBL2X7H477YEIW","created_at":"2026-07-05T09:16:34Z"},{"alias_kind":"pith_short_8","alias_value":"PQUBL2X7","created_at":"2026-07-05T09:16:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PQUBL2X7H477YEIWELIDA6HDHU","target":"record","payload":{"canonical_record":{"source":{"id":"2410.04439","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T10:25:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff51eda884a1b6e278b3fbeb46c0ed3dac784f4c31b747a38cf8da61cb6690fc","abstract_canon_sha256":"c37493e3d5f915d987a9d52f25bd534832b8f32b261494f342411434d575f6c8"},"schema_version":"1.0"},"canonical_sha256":"7c2815eaff3f3ffc111622d03078e33d2a118ae0e56ce32134192f31902f49a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:34.369269Z","signature_b64":"tirFRzgx508Grq4lLbidnw6HvnKdaZZ8PlUikbvUTKu2kOQbH8WVqk5Mr8V1MkR0qK8aHSJAHouh94R1qv1PDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c2815eaff3f3ffc111622d03078e33d2a118ae0e56ce32134192f31902f49a7","last_reissued_at":"2026-07-05T09:16:34.368864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:34.368864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.04439","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":"2026-07-05T09:16:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tKyKdAJPgycpuP2g09kNtjcCsrLDjDOYxcHeQYnaxjaLiZC5OT4cGVYZO0SFs319RKPNUzgbwFk/vACHqSzCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:32:49.262757Z"},"content_sha256":"4825be710ffc56a8ef763176633274c42b0f0c10747085eeec84ac1904de661d","schema_version":"1.0","event_id":"sha256:4825be710ffc56a8ef763176633274c42b0f0c10747085eeec84ac1904de661d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PQUBL2X7H477YEIWELIDA6HDHU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Empowering Backbone Models for Visual Text Generation with Input Granularity Control and Glyph-Aware Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guohao Li, Jiachen Liu, Jinsong Su, Wanru Zhuang, Wenbo Li, Xinyan Xiao, Xue Xu, Zhibin Lan","submitted_at":"2024-10-06T10:25:39Z","abstract_excerpt":"Diffusion-based text-to-image models have demonstrated impressive achievements in diversity and aesthetics but struggle to generate images with legible visual texts. Existing backbone models have limitations such as misspelling, failing to generate texts, and lack of support for Chinese text, but their development shows promising potential. In this paper, we propose a series of methods, aiming to empower backbone models to generate visual texts in English and Chinese. We first conduct a preliminary study revealing that Byte Pair Encoding (BPE) tokenization and the insufficient learning of cros"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04439","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/2410.04439/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":"2026-07-05T09:16:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lizp91XXFLIh8PLrWFZjQ60vKCfBuFdPMalqctVfZa6brPleqyA+iCyAL83fKx3+YYUIPN4YIpRVAgIyTaa5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:32:49.263626Z"},"content_sha256":"c6f89d9c4c21651161c9c0b501fed5d521b64a6ab708fddf2bfc5f236878d631","schema_version":"1.0","event_id":"sha256:c6f89d9c4c21651161c9c0b501fed5d521b64a6ab708fddf2bfc5f236878d631"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQUBL2X7H477YEIWELIDA6HDHU/bundle.json","state_url":"https://pith.science/pith/PQUBL2X7H477YEIWELIDA6HDHU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQUBL2X7H477YEIWELIDA6HDHU/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":"2026-08-15T19:32:49Z","links":{"resolver":"https://pith.science/pith/PQUBL2X7H477YEIWELIDA6HDHU","bundle":"https://pith.science/pith/PQUBL2X7H477YEIWELIDA6HDHU/bundle.json","state":"https://pith.science/pith/PQUBL2X7H477YEIWELIDA6HDHU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQUBL2X7H477YEIWELIDA6HDHU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PQUBL2X7H477YEIWELIDA6HDHU","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":"c37493e3d5f915d987a9d52f25bd534832b8f32b261494f342411434d575f6c8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T10:25:39Z","title_canon_sha256":"ff51eda884a1b6e278b3fbeb46c0ed3dac784f4c31b747a38cf8da61cb6690fc"},"schema_version":"1.0","source":{"id":"2410.04439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04439","created_at":"2026-07-05T09:16:34Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04439v1","created_at":"2026-07-05T09:16:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04439","created_at":"2026-07-05T09:16:34Z"},{"alias_kind":"pith_short_12","alias_value":"PQUBL2X7H477","created_at":"2026-07-05T09:16:34Z"},{"alias_kind":"pith_short_16","alias_value":"PQUBL2X7H477YEIW","created_at":"2026-07-05T09:16:34Z"},{"alias_kind":"pith_short_8","alias_value":"PQUBL2X7","created_at":"2026-07-05T09:16:34Z"}],"graph_snapshots":[{"event_id":"sha256:c6f89d9c4c21651161c9c0b501fed5d521b64a6ab708fddf2bfc5f236878d631","target":"graph","created_at":"2026-07-05T09:16:34Z","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/2410.04439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion-based text-to-image models have demonstrated impressive achievements in diversity and aesthetics but struggle to generate images with legible visual texts. Existing backbone models have limitations such as misspelling, failing to generate texts, and lack of support for Chinese text, but their development shows promising potential. In this paper, we propose a series of methods, aiming to empower backbone models to generate visual texts in English and Chinese. We first conduct a preliminary study revealing that Byte Pair Encoding (BPE) tokenization and the insufficient learning of cros","authors_text":"Guohao Li, Jiachen Liu, Jinsong Su, Wanru Zhuang, Wenbo Li, Xinyan Xiao, Xue Xu, Zhibin Lan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T10:25:39Z","title":"Empowering Backbone Models for Visual Text Generation with Input Granularity Control and Glyph-Aware Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04439","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":"sha256:4825be710ffc56a8ef763176633274c42b0f0c10747085eeec84ac1904de661d","target":"record","created_at":"2026-07-05T09:16:34Z","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":"c37493e3d5f915d987a9d52f25bd534832b8f32b261494f342411434d575f6c8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T10:25:39Z","title_canon_sha256":"ff51eda884a1b6e278b3fbeb46c0ed3dac784f4c31b747a38cf8da61cb6690fc"},"schema_version":"1.0","source":{"id":"2410.04439","kind":"arxiv","version":1}},"canonical_sha256":"7c2815eaff3f3ffc111622d03078e33d2a118ae0e56ce32134192f31902f49a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c2815eaff3f3ffc111622d03078e33d2a118ae0e56ce32134192f31902f49a7","first_computed_at":"2026-07-05T09:16:34.368864Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:34.368864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tirFRzgx508Grq4lLbidnw6HvnKdaZZ8PlUikbvUTKu2kOQbH8WVqk5Mr8V1MkR0qK8aHSJAHouh94R1qv1PDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:34.369269Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4825be710ffc56a8ef763176633274c42b0f0c10747085eeec84ac1904de661d","sha256:c6f89d9c4c21651161c9c0b501fed5d521b64a6ab708fddf2bfc5f236878d631"],"state_sha256":"5ad1bce0941f91c7ed58fce1886c7504df74467d1b0d10a85ae1823c2822c8fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TBnMFIcFTA99SCunR6NFXg/HRZc+624NhaNf3Mp5QzjidPRR8mtS2xj6GT5nsoTOemAYsZzEYXuoB+3D1r33Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T19:32:49.271455Z","bundle_sha256":"b161c14e5d5abb2c48d54d787855413e8174cebe446ee62b069d6687589a1df7"}}