{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DVCG45HLHYDIVQ6ABUUZA67OWD","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":"5bcbc871c91ff901a2fdf14a173b08ef2db3af71c5256eb01f9c3c03c4e9128c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T11:57:40Z","title_canon_sha256":"65ae2aa73475ca8acedc89d4d05c670dc991a2e49b87d72055be50d777523f25"},"schema_version":"1.0","source":{"id":"2407.20756","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20756","created_at":"2026-07-05T11:52:00Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20756v5","created_at":"2026-07-05T11:52:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20756","created_at":"2026-07-05T11:52:00Z"},{"alias_kind":"pith_short_12","alias_value":"DVCG45HLHYDI","created_at":"2026-07-05T11:52:00Z"},{"alias_kind":"pith_short_16","alias_value":"DVCG45HLHYDIVQ6A","created_at":"2026-07-05T11:52:00Z"},{"alias_kind":"pith_short_8","alias_value":"DVCG45HL","created_at":"2026-07-05T11:52:00Z"}],"graph_snapshots":[{"event_id":"sha256:da83ae5c0fa2a23fbf443b76f9d5414a05296b2f242b81fd77fd5adaf32ecd2f","target":"graph","created_at":"2026-07-05T11:52:00Z","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/2407.20756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have recently emerged, demonstrating remarkable vision-understanding capabilities. However, training these models requires large-scale datasets, which brings challenges related to efficiency, effectiveness, and quality of web data. In this paper, we introduce SynthVLM, a new data synthesis and curation method for generating image-caption pairs. Unlike traditional methods, where captions are generated from images, SynthVLM utilizes advanced diffusion models and high-quality captions to synthesize and select images from text captions, thereby creating precisely alig","authors_text":"Bin Cui, Bozhou Li, Chong Chen, Conghui He, Hao Liang, Wentao Xiong, Wentao Zhang, Zheng Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T11:57:40Z","title":"SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20756","kind":"arxiv","version":5},"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":"sha256:05a408e5f63ae1f668d2d88da07a2c2c5cd5a02321acefa8fbf238b206643614","target":"record","created_at":"2026-07-05T11:52:00Z","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":"5bcbc871c91ff901a2fdf14a173b08ef2db3af71c5256eb01f9c3c03c4e9128c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T11:57:40Z","title_canon_sha256":"65ae2aa73475ca8acedc89d4d05c670dc991a2e49b87d72055be50d777523f25"},"schema_version":"1.0","source":{"id":"2407.20756","kind":"arxiv","version":5}},"canonical_sha256":"1d446e74eb3e068ac3c00d29907beeb0e73eb76047ba0a8c012b587caa087016","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d446e74eb3e068ac3c00d29907beeb0e73eb76047ba0a8c012b587caa087016","first_computed_at":"2026-07-05T11:52:00.303051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:00.303051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pLLCI3fgQPJJcmLbD6rPe8HLSLldB+nH4UvadGWgTlkhcfWJzq+OxHuIl/BzST6eOmuwSC9EFo0ZUfLI6yhQAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:00.303524Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.20756","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05a408e5f63ae1f668d2d88da07a2c2c5cd5a02321acefa8fbf238b206643614","sha256:da83ae5c0fa2a23fbf443b76f9d5414a05296b2f242b81fd77fd5adaf32ecd2f"],"state_sha256":"4569bf1c5b76c292b8bb847b212a8e94c27d59ba031aba3fb52ef7c2601d7bd8"}