{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:S6KUP7KDP52VLDFWL7KWP54UXH","short_pith_number":"pith:S6KUP7KD","canonical_record":{"source":{"id":"2307.04087","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-09T03:25:14Z","cross_cats_sorted":[],"title_canon_sha256":"fef5fd14ea0f950ed54f56492cddfdbb3416604d136c8b610d3d500488c5590a","abstract_canon_sha256":"91a5620e97570e98120b25c40766901de764f4b2311a332b6d99f2f816a2ae7f"},"schema_version":"1.0"},"canonical_sha256":"979547fd437f75558cb65fd567f794b9de80573990c042e776f51cdd93d6382b","source":{"kind":"arxiv","id":"2307.04087","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04087","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04087v3","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04087","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"S6KUP7KDP52V","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"S6KUP7KDP52VLDFW","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"S6KUP7KD","created_at":"2026-07-05T07:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:S6KUP7KDP52VLDFWL7KWP54UXH","target":"record","payload":{"canonical_record":{"source":{"id":"2307.04087","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-09T03:25:14Z","cross_cats_sorted":[],"title_canon_sha256":"fef5fd14ea0f950ed54f56492cddfdbb3416604d136c8b610d3d500488c5590a","abstract_canon_sha256":"91a5620e97570e98120b25c40766901de764f4b2311a332b6d99f2f816a2ae7f"},"schema_version":"1.0"},"canonical_sha256":"979547fd437f75558cb65fd567f794b9de80573990c042e776f51cdd93d6382b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:28.844580Z","signature_b64":"jspCPR7L70qg+1ret7sqkeIBcS5N96qkSJLrtzrro7YIori9B4UPNksyY+0xpMqAsRo3S+9xYmaLwv7LY4kTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"979547fd437f75558cb65fd567f794b9de80573990c042e776f51cdd93d6382b","last_reissued_at":"2026-07-05T07:28:28.844057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:28.844057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.04087","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uZ8vbGWfJyan8JG1w5QTcLGtiEw563FACJXhEUbVPT/9xowcCCaZz6OI2mZQzR2f8IrZZ1oPfrQ4m9Wbrl7EBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:51:22.204243Z"},"content_sha256":"201b64afa0ee2401a46a768e8b9a7da0d1f9f667a2d5e73c16b2c1c73e4eff3c","schema_version":"1.0","event_id":"sha256:201b64afa0ee2401a46a768e8b9a7da0d1f9f667a2d5e73c16b2c1c73e4eff3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:S6KUP7KDP52VLDFWL7KWP54UXH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SVIT: Scaling up Visual Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boya Wu, Bo Zhao, Muyang He, Tiejun Huang","submitted_at":"2023-07-09T03:25:14Z","abstract_excerpt":"Thanks to the emerging of foundation models, the large language and vision models are integrated to acquire the multimodal ability of visual captioning, question answering, etc. Although existing multimodal models present impressive performance of visual understanding and reasoning, their limits are still largely under-explored due to the scarcity of high-quality instruction tuning data. To push the limits of multimodal capability, we Scale up Visual Instruction Tuning (SVIT) by constructing a dataset of 4.2 million visual instruction tuning data including 1.6M conversation question-answer (QA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04087","kind":"arxiv","version":3},"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/2307.04087/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":"2026-07-05T07:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nOqQ9oUfXRtEa3/wq/txsfelPNEeq0ZhnjmvrDbl4vlWmIs+yXTxCSySmDBRjTs09O3nyJo47sx832NBHr7pDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:51:22.204935Z"},"content_sha256":"f1c590ca39490bece58809d13781266e24cdb52bfe777ac309ef77c0a10f6ce7","schema_version":"1.0","event_id":"sha256:f1c590ca39490bece58809d13781266e24cdb52bfe777ac309ef77c0a10f6ce7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S6KUP7KDP52VLDFWL7KWP54UXH/bundle.json","state_url":"https://pith.science/pith/S6KUP7KDP52VLDFWL7KWP54UXH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S6KUP7KDP52VLDFWL7KWP54UXH/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":"2026-08-05T23:51:22Z","links":{"resolver":"https://pith.science/pith/S6KUP7KDP52VLDFWL7KWP54UXH","bundle":"https://pith.science/pith/S6KUP7KDP52VLDFWL7KWP54UXH/bundle.json","state":"https://pith.science/pith/S6KUP7KDP52VLDFWL7KWP54UXH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S6KUP7KDP52VLDFWL7KWP54UXH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:S6KUP7KDP52VLDFWL7KWP54UXH","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":"91a5620e97570e98120b25c40766901de764f4b2311a332b6d99f2f816a2ae7f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-09T03:25:14Z","title_canon_sha256":"fef5fd14ea0f950ed54f56492cddfdbb3416604d136c8b610d3d500488c5590a"},"schema_version":"1.0","source":{"id":"2307.04087","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04087","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04087v3","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04087","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"S6KUP7KDP52V","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"S6KUP7KDP52VLDFW","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"S6KUP7KD","created_at":"2026-07-05T07:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:f1c590ca39490bece58809d13781266e24cdb52bfe777ac309ef77c0a10f6ce7","target":"graph","created_at":"2026-07-05T07:28:28Z","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/2307.04087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Thanks to the emerging of foundation models, the large language and vision models are integrated to acquire the multimodal ability of visual captioning, question answering, etc. Although existing multimodal models present impressive performance of visual understanding and reasoning, their limits are still largely under-explored due to the scarcity of high-quality instruction tuning data. To push the limits of multimodal capability, we Scale up Visual Instruction Tuning (SVIT) by constructing a dataset of 4.2 million visual instruction tuning data including 1.6M conversation question-answer (QA","authors_text":"Boya Wu, Bo Zhao, Muyang He, Tiejun Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-09T03:25:14Z","title":"SVIT: Scaling up Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04087","kind":"arxiv","version":3},"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":"sha256:201b64afa0ee2401a46a768e8b9a7da0d1f9f667a2d5e73c16b2c1c73e4eff3c","target":"record","created_at":"2026-07-05T07:28:28Z","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":"91a5620e97570e98120b25c40766901de764f4b2311a332b6d99f2f816a2ae7f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-09T03:25:14Z","title_canon_sha256":"fef5fd14ea0f950ed54f56492cddfdbb3416604d136c8b610d3d500488c5590a"},"schema_version":"1.0","source":{"id":"2307.04087","kind":"arxiv","version":3}},"canonical_sha256":"979547fd437f75558cb65fd567f794b9de80573990c042e776f51cdd93d6382b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"979547fd437f75558cb65fd567f794b9de80573990c042e776f51cdd93d6382b","first_computed_at":"2026-07-05T07:28:28.844057Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:28.844057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jspCPR7L70qg+1ret7sqkeIBcS5N96qkSJLrtzrro7YIori9B4UPNksyY+0xpMqAsRo3S+9xYmaLwv7LY4kTBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:28.844580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.04087","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:201b64afa0ee2401a46a768e8b9a7da0d1f9f667a2d5e73c16b2c1c73e4eff3c","sha256:f1c590ca39490bece58809d13781266e24cdb52bfe777ac309ef77c0a10f6ce7"],"state_sha256":"c9ba5e5c639ec235911433067297150d5e299e1a6837c2a81b0b56239199d165"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vtoxJUKjN2r37WzXTdhir7m6y7Qfb0qcG3sC5gXe4qXT0kIzaLmZo9UEqk1JInwh/lwQ9ItlWbdgAe70onQ5Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:51:22.209868Z","bundle_sha256":"986af70fdf8ebff9b41e940e64bddfbab15946d220b3d325bb2c2e9f0b8246ce"}}