{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5ZC5FZ2ZXNCLVMT5SHX4KM7UAG","short_pith_number":"pith:5ZC5FZ2Z","canonical_record":{"source":{"id":"2403.07750","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T15:36:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a58cb21a44245a0708e7daca08c504ba072952b6b6f5e85d24722421326bd130","abstract_canon_sha256":"d428e49ec1a04cae8b9f127458066e30601fa5921e24fda5eb87b3563503b230"},"schema_version":"1.0"},"canonical_sha256":"ee45d2e759bb44bab27d91efc533f401b8cf27a72c1f2dfec7bb5cd04b844518","source":{"kind":"arxiv","id":"2403.07750","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07750","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07750v2","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07750","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"pith_short_12","alias_value":"5ZC5FZ2ZXNCL","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"pith_short_16","alias_value":"5ZC5FZ2ZXNCLVMT5","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"pith_short_8","alias_value":"5ZC5FZ2Z","created_at":"2026-07-05T08:28:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5ZC5FZ2ZXNCLVMT5SHX4KM7UAG","target":"record","payload":{"canonical_record":{"source":{"id":"2403.07750","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T15:36:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a58cb21a44245a0708e7daca08c504ba072952b6b6f5e85d24722421326bd130","abstract_canon_sha256":"d428e49ec1a04cae8b9f127458066e30601fa5921e24fda5eb87b3563503b230"},"schema_version":"1.0"},"canonical_sha256":"ee45d2e759bb44bab27d91efc533f401b8cf27a72c1f2dfec7bb5cd04b844518","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:39.498460Z","signature_b64":"nSjjTddnBI9Lypp1nq8VuNJKruWBkHvwnHlbHaRDD3xKAS0u7+6y5s+HucVIqpHPt5Ccz26XJRfiijNiMpA9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee45d2e759bb44bab27d91efc533f401b8cf27a72c1f2dfec7bb5cd04b844518","last_reissued_at":"2026-07-05T08:28:39.498036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:39.498036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.07750","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":"2026-07-05T08:28:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VdaRbHiTnWbvZJjG8ncyQRueUV+KwE6Od+Xa3r+jX+qcSAbi2znPYpyM+J51m5uNgF+13j1dRWx+1t9seKQlBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T23:58:19.013539Z"},"content_sha256":"3b6662e3a9505b2621522996fe9dcdbf396bb5168976381a5d60a85835af9424","schema_version":"1.0","event_id":"sha256:3b6662e3a9505b2621522996fe9dcdbf396bb5168976381a5d60a85835af9424"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5ZC5FZ2ZXNCLVMT5SHX4KM7UAG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synth$^2$: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anastasija Ilic, Andrea Banino, Charles Blundell, Christos Kaplanis, Dharshan Kumaran, Jovana Mitrovic, Sahand Sharifzadeh, Shreya Pathak","submitted_at":"2024-03-12T15:36:42Z","abstract_excerpt":"The creation of high-quality human-labeled image-caption datasets presents a significant bottleneck in the development of Visual-Language Models (VLMs). In this work, we investigate an approach that leverages the strengths of Large Language Models (LLMs) and image generation models to create synthetic image-text pairs for efficient and effective VLM training. Our method employs a pretrained text-to-image model to synthesize image embeddings from captions generated by an LLM. Despite the text-to-image model and VLM initially being trained on the same data, our approach leverages the image gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07750","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/2403.07750/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":"2026-07-05T08:28:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QtD5ummPfwSw/f5uzO5mi7PPSb+hyPfU0MFlTnhgMUHVSsi0WofsCMpN24Z44wHjIjhw02juR4PJJr0fV4GKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T23:58:19.013905Z"},"content_sha256":"96983bfc567032838d510c2952093379f3572aa71c9f51b80597f7ec92e18827","schema_version":"1.0","event_id":"sha256:96983bfc567032838d510c2952093379f3572aa71c9f51b80597f7ec92e18827"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5ZC5FZ2ZXNCLVMT5SHX4KM7UAG/bundle.json","state_url":"https://pith.science/pith/5ZC5FZ2ZXNCLVMT5SHX4KM7UAG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5ZC5FZ2ZXNCLVMT5SHX4KM7UAG/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":"2026-07-13T23:58:19Z","links":{"resolver":"https://pith.science/pith/5ZC5FZ2ZXNCLVMT5SHX4KM7UAG","bundle":"https://pith.science/pith/5ZC5FZ2ZXNCLVMT5SHX4KM7UAG/bundle.json","state":"https://pith.science/pith/5ZC5FZ2ZXNCLVMT5SHX4KM7UAG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5ZC5FZ2ZXNCLVMT5SHX4KM7UAG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5ZC5FZ2ZXNCLVMT5SHX4KM7UAG","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":"d428e49ec1a04cae8b9f127458066e30601fa5921e24fda5eb87b3563503b230","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T15:36:42Z","title_canon_sha256":"a58cb21a44245a0708e7daca08c504ba072952b6b6f5e85d24722421326bd130"},"schema_version":"1.0","source":{"id":"2403.07750","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07750","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07750v2","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07750","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"pith_short_12","alias_value":"5ZC5FZ2ZXNCL","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"pith_short_16","alias_value":"5ZC5FZ2ZXNCLVMT5","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"pith_short_8","alias_value":"5ZC5FZ2Z","created_at":"2026-07-05T08:28:39Z"}],"graph_snapshots":[{"event_id":"sha256:96983bfc567032838d510c2952093379f3572aa71c9f51b80597f7ec92e18827","target":"graph","created_at":"2026-07-05T08:28:39Z","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/2403.07750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The creation of high-quality human-labeled image-caption datasets presents a significant bottleneck in the development of Visual-Language Models (VLMs). In this work, we investigate an approach that leverages the strengths of Large Language Models (LLMs) and image generation models to create synthetic image-text pairs for efficient and effective VLM training. Our method employs a pretrained text-to-image model to synthesize image embeddings from captions generated by an LLM. Despite the text-to-image model and VLM initially being trained on the same data, our approach leverages the image gener","authors_text":"Anastasija Ilic, Andrea Banino, Charles Blundell, Christos Kaplanis, Dharshan Kumaran, Jovana Mitrovic, Sahand Sharifzadeh, Shreya Pathak","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T15:36:42Z","title":"Synth$^2$: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07750","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":"sha256:3b6662e3a9505b2621522996fe9dcdbf396bb5168976381a5d60a85835af9424","target":"record","created_at":"2026-07-05T08:28:39Z","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":"d428e49ec1a04cae8b9f127458066e30601fa5921e24fda5eb87b3563503b230","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T15:36:42Z","title_canon_sha256":"a58cb21a44245a0708e7daca08c504ba072952b6b6f5e85d24722421326bd130"},"schema_version":"1.0","source":{"id":"2403.07750","kind":"arxiv","version":2}},"canonical_sha256":"ee45d2e759bb44bab27d91efc533f401b8cf27a72c1f2dfec7bb5cd04b844518","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee45d2e759bb44bab27d91efc533f401b8cf27a72c1f2dfec7bb5cd04b844518","first_computed_at":"2026-07-05T08:28:39.498036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:39.498036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nSjjTddnBI9Lypp1nq8VuNJKruWBkHvwnHlbHaRDD3xKAS0u7+6y5s+HucVIqpHPt5Ccz26XJRfiijNiMpA9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:39.498460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.07750","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b6662e3a9505b2621522996fe9dcdbf396bb5168976381a5d60a85835af9424","sha256:96983bfc567032838d510c2952093379f3572aa71c9f51b80597f7ec92e18827"],"state_sha256":"0462683187c5ab2cea988f3fb1274c4f745e716899a49ab7f77dba6839a688ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UWKO7QnthMO86pIf/cxsZHMjzN44PVA51yQF4TwrICLjkHtjvOAmITg104YI9xSVg1e/+r6XnEB7nXkxLpKtCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T23:58:19.020744Z","bundle_sha256":"25358aaf37694920132da3f6dde1e80a9ed31d5ec054474d515f0bff4001e22e"}}