{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DVCG45HLHYDIVQ6ABUUZA67OWD","short_pith_number":"pith:DVCG45HL","canonical_record":{"source":{"id":"2407.20756","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T11:57:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"65ae2aa73475ca8acedc89d4d05c670dc991a2e49b87d72055be50d777523f25","abstract_canon_sha256":"5bcbc871c91ff901a2fdf14a173b08ef2db3af71c5256eb01f9c3c03c4e9128c"},"schema_version":"1.0"},"canonical_sha256":"1d446e74eb3e068ac3c00d29907beeb0e73eb76047ba0a8c012b587caa087016","source":{"kind":"arxiv","id":"2407.20756","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DVCG45HLHYDIVQ6ABUUZA67OWD","target":"record","payload":{"canonical_record":{"source":{"id":"2407.20756","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T11:57:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"65ae2aa73475ca8acedc89d4d05c670dc991a2e49b87d72055be50d777523f25","abstract_canon_sha256":"5bcbc871c91ff901a2fdf14a173b08ef2db3af71c5256eb01f9c3c03c4e9128c"},"schema_version":"1.0"},"canonical_sha256":"1d446e74eb3e068ac3c00d29907beeb0e73eb76047ba0a8c012b587caa087016","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:00.303524Z","signature_b64":"pLLCI3fgQPJJcmLbD6rPe8HLSLldB+nH4UvadGWgTlkhcfWJzq+OxHuIl/BzST6eOmuwSC9EFo0ZUfLI6yhQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d446e74eb3e068ac3c00d29907beeb0e73eb76047ba0a8c012b587caa087016","last_reissued_at":"2026-07-05T11:52:00.303051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:00.303051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.20756","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:52:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BeG5OwGoDyoSYEgq9De6jKx14Y8ScghmwHpM8BCGxygCpEGXRTq3DIzImV+sUs/TpGoDdSuEEgFdSh5PQqJYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:07:59.658878Z"},"content_sha256":"05a408e5f63ae1f668d2d88da07a2c2c5cd5a02321acefa8fbf238b206643614","schema_version":"1.0","event_id":"sha256:05a408e5f63ae1f668d2d88da07a2c2c5cd5a02321acefa8fbf238b206643614"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DVCG45HLHYDIVQ6ABUUZA67OWD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bin Cui, Bozhou Li, Chong Chen, Conghui He, Hao Liang, Wentao Xiong, Wentao Zhang, Zheng Liu","submitted_at":"2024-07-30T11:57:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20756","kind":"arxiv","version":5},"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/2407.20756/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":"2026-07-05T11:52:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0dux0RaznjoihW9HMChkvKmgIj7IGGBDZU+QE/ssaeylt1993LP4RrVdxSzG0y/Fs7NJrONjV14bJwwIGNfsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:07:59.659454Z"},"content_sha256":"da83ae5c0fa2a23fbf443b76f9d5414a05296b2f242b81fd77fd5adaf32ecd2f","schema_version":"1.0","event_id":"sha256:da83ae5c0fa2a23fbf443b76f9d5414a05296b2f242b81fd77fd5adaf32ecd2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DVCG45HLHYDIVQ6ABUUZA67OWD/bundle.json","state_url":"https://pith.science/pith/DVCG45HLHYDIVQ6ABUUZA67OWD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DVCG45HLHYDIVQ6ABUUZA67OWD/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":"2026-08-06T17:07:59Z","links":{"resolver":"https://pith.science/pith/DVCG45HLHYDIVQ6ABUUZA67OWD","bundle":"https://pith.science/pith/DVCG45HLHYDIVQ6ABUUZA67OWD/bundle.json","state":"https://pith.science/pith/DVCG45HLHYDIVQ6ABUUZA67OWD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DVCG45HLHYDIVQ6ABUUZA67OWD/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+GHEK79E0BDioqeO4WOTAtuV3sGRNZFgYpQVg0/wmpEpqT7+Y5YzfSs6UErUnj6WRgzFfeM6SLEy6+DIN3PTAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:07:59.664206Z","bundle_sha256":"7d7e372ff7c60c05fd9eac588d4a3fe9dae73a50c5bc56419d77cc0086b07224"}}