{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HHU7C2OOMRNG2BVWYCCSPTF6NO","short_pith_number":"pith:HHU7C2OO","canonical_record":{"source":{"id":"2407.16364","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T10:11:56Z","cross_cats_sorted":[],"title_canon_sha256":"450c974ed88cc257fea4a5e075dda62ad94a55cbc98ceabcac66482cc7b781f8","abstract_canon_sha256":"ac159c3fafdd7ed672aa62db12c1099d9c36c41897586384adcc605d24b5f07b"},"schema_version":"1.0"},"canonical_sha256":"39e9f169ce645a6d06b6c08527ccbe6b8297a5bc3092419579cacd256a7e208c","source":{"kind":"arxiv","id":"2407.16364","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16364","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16364v2","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16364","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"pith_short_12","alias_value":"HHU7C2OOMRNG","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"pith_short_16","alias_value":"HHU7C2OOMRNG2BVW","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"pith_short_8","alias_value":"HHU7C2OO","created_at":"2026-07-05T09:24:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HHU7C2OOMRNG2BVWYCCSPTF6NO","target":"record","payload":{"canonical_record":{"source":{"id":"2407.16364","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T10:11:56Z","cross_cats_sorted":[],"title_canon_sha256":"450c974ed88cc257fea4a5e075dda62ad94a55cbc98ceabcac66482cc7b781f8","abstract_canon_sha256":"ac159c3fafdd7ed672aa62db12c1099d9c36c41897586384adcc605d24b5f07b"},"schema_version":"1.0"},"canonical_sha256":"39e9f169ce645a6d06b6c08527ccbe6b8297a5bc3092419579cacd256a7e208c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:37.107902Z","signature_b64":"a26E19d3sNN0ngifMBsiehGQeb1urR+q0Rsr24is0sNi9l3uxpLZCTsDRdKn5nXNR9tLRVFpMdpj6mygpkODAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39e9f169ce645a6d06b6c08527ccbe6b8297a5bc3092419579cacd256a7e208c","last_reissued_at":"2026-07-05T09:24:37.107374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:37.107374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.16364","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":"2026-07-05T09:24:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jg7qx82R1+dLZ6ysj31ugg/4h97aNSer+rBhSri8EXtrleFBiAWQ33rST8pyTbLHHeOzX+lciQxi/Jt5PQSmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:19:08.578644Z"},"content_sha256":"aa57f69ae4f3dedf675863ad240fbfa755ce8e1b7931e913a0266eebfed1bc3b","schema_version":"1.0","event_id":"sha256:aa57f69ae4f3dedf675863ad240fbfa755ce8e1b7931e913a0266eebfed1bc3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HHU7C2OOMRNG2BVWYCCSPTF6NO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Harmonizing Visual Text Comprehension and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binghong Wu, Can Huang, Chunhui Lin, Hao Liu, Jingqun Tang, Shu Wei, Xin Tan, Yuan Xie, Zhen Zhao, Zhizhong Zhang","submitted_at":"2024-07-23T10:11:56Z","abstract_excerpt":"In this work, we present TextHarmony, a unified and versatile multimodal generative model proficient in comprehending and generating visual text. Simultaneously generating images and texts typically results in performance degradation due to the inherent inconsistency between vision and language modalities. To overcome this challenge, existing approaches resort to modality-specific data for supervised fine-tuning, necessitating distinct model instances. We propose Slide-LoRA, which dynamically aggregates modality-specific and modality-agnostic LoRA experts, partially decoupling the multimodal g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16364","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/2407.16364/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":"2026-07-05T09:24:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zllHBo5sb6be6f1uSnmdJsWDAR5zrmn+RjdfWCiTqSbsGQ4boJAaZkd9s1cVi5eOdTNhwb8O77XTrnzmDq7KCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:19:08.580035Z"},"content_sha256":"f8b092331bc0a7c28eb470a1e12995dabe91d9763e99a9fd2ed451d4d81cb138","schema_version":"1.0","event_id":"sha256:f8b092331bc0a7c28eb470a1e12995dabe91d9763e99a9fd2ed451d4d81cb138"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HHU7C2OOMRNG2BVWYCCSPTF6NO/bundle.json","state_url":"https://pith.science/pith/HHU7C2OOMRNG2BVWYCCSPTF6NO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HHU7C2OOMRNG2BVWYCCSPTF6NO/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":"2026-08-08T17:19:08Z","links":{"resolver":"https://pith.science/pith/HHU7C2OOMRNG2BVWYCCSPTF6NO","bundle":"https://pith.science/pith/HHU7C2OOMRNG2BVWYCCSPTF6NO/bundle.json","state":"https://pith.science/pith/HHU7C2OOMRNG2BVWYCCSPTF6NO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HHU7C2OOMRNG2BVWYCCSPTF6NO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HHU7C2OOMRNG2BVWYCCSPTF6NO","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":"ac159c3fafdd7ed672aa62db12c1099d9c36c41897586384adcc605d24b5f07b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T10:11:56Z","title_canon_sha256":"450c974ed88cc257fea4a5e075dda62ad94a55cbc98ceabcac66482cc7b781f8"},"schema_version":"1.0","source":{"id":"2407.16364","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16364","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16364v2","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16364","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"pith_short_12","alias_value":"HHU7C2OOMRNG","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"pith_short_16","alias_value":"HHU7C2OOMRNG2BVW","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"pith_short_8","alias_value":"HHU7C2OO","created_at":"2026-07-05T09:24:37Z"}],"graph_snapshots":[{"event_id":"sha256:f8b092331bc0a7c28eb470a1e12995dabe91d9763e99a9fd2ed451d4d81cb138","target":"graph","created_at":"2026-07-05T09:24:37Z","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/2407.16364/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we present TextHarmony, a unified and versatile multimodal generative model proficient in comprehending and generating visual text. Simultaneously generating images and texts typically results in performance degradation due to the inherent inconsistency between vision and language modalities. To overcome this challenge, existing approaches resort to modality-specific data for supervised fine-tuning, necessitating distinct model instances. We propose Slide-LoRA, which dynamically aggregates modality-specific and modality-agnostic LoRA experts, partially decoupling the multimodal g","authors_text":"Binghong Wu, Can Huang, Chunhui Lin, Hao Liu, Jingqun Tang, Shu Wei, Xin Tan, Yuan Xie, Zhen Zhao, Zhizhong Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T10:11:56Z","title":"Harmonizing Visual Text Comprehension and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16364","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:aa57f69ae4f3dedf675863ad240fbfa755ce8e1b7931e913a0266eebfed1bc3b","target":"record","created_at":"2026-07-05T09:24:37Z","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":"ac159c3fafdd7ed672aa62db12c1099d9c36c41897586384adcc605d24b5f07b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T10:11:56Z","title_canon_sha256":"450c974ed88cc257fea4a5e075dda62ad94a55cbc98ceabcac66482cc7b781f8"},"schema_version":"1.0","source":{"id":"2407.16364","kind":"arxiv","version":2}},"canonical_sha256":"39e9f169ce645a6d06b6c08527ccbe6b8297a5bc3092419579cacd256a7e208c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39e9f169ce645a6d06b6c08527ccbe6b8297a5bc3092419579cacd256a7e208c","first_computed_at":"2026-07-05T09:24:37.107374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:37.107374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a26E19d3sNN0ngifMBsiehGQeb1urR+q0Rsr24is0sNi9l3uxpLZCTsDRdKn5nXNR9tLRVFpMdpj6mygpkODAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:37.107902Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.16364","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa57f69ae4f3dedf675863ad240fbfa755ce8e1b7931e913a0266eebfed1bc3b","sha256:f8b092331bc0a7c28eb470a1e12995dabe91d9763e99a9fd2ed451d4d81cb138"],"state_sha256":"32c24b319f1b64d15dec9d88a793c0c29326084eff4719b8ca22342758c07362"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ssCj9lskq+mCIGNb2YTLHCZ1I1KaXeQEw7h2OQxIwyD/6vosqlF8CklEPsoVkYcLUBD7n9ovlxQmqwXFHEuZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:19:08.587255Z","bundle_sha256":"fa5be41946df2038df1a9c7d055745b13fa399d80e075c923ff163490c90fca8"}}