{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MHLHL4K5WANZ35EFKZ62VR5JYN","short_pith_number":"pith:MHLHL4K5","canonical_record":{"source":{"id":"2412.07012","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T21:44:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4b29099697354b4f79e24d8065edf563890344e40844de5f9f70b8b7b6f404f8","abstract_canon_sha256":"52a9c5301383b74457f6071715f340c4122e36b8f56bafb3aeb9896bc60b6bbf"},"schema_version":"1.0"},"canonical_sha256":"61d675f15db01b9df485567daac7a9c375ab5a556115716ea1cc4c3e1d2cc1c3","source":{"kind":"arxiv","id":"2412.07012","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07012","created_at":"2026-07-05T09:54:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07012v3","created_at":"2026-07-05T09:54:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07012","created_at":"2026-07-05T09:54:48Z"},{"alias_kind":"pith_short_12","alias_value":"MHLHL4K5WANZ","created_at":"2026-07-05T09:54:48Z"},{"alias_kind":"pith_short_16","alias_value":"MHLHL4K5WANZ35EF","created_at":"2026-07-05T09:54:48Z"},{"alias_kind":"pith_short_8","alias_value":"MHLHL4K5","created_at":"2026-07-05T09:54:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MHLHL4K5WANZ35EFKZ62VR5JYN","target":"record","payload":{"canonical_record":{"source":{"id":"2412.07012","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T21:44:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4b29099697354b4f79e24d8065edf563890344e40844de5f9f70b8b7b6f404f8","abstract_canon_sha256":"52a9c5301383b74457f6071715f340c4122e36b8f56bafb3aeb9896bc60b6bbf"},"schema_version":"1.0"},"canonical_sha256":"61d675f15db01b9df485567daac7a9c375ab5a556115716ea1cc4c3e1d2cc1c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:48.991439Z","signature_b64":"NjyCR2kMa0G5yNqrlyM87QVsmkPYw7KAHXGxa+AaOqtHMIJelCppk55Snd7JPTNmIQh6XF6vb+n5MJLZIANJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61d675f15db01b9df485567daac7a9c375ab5a556115716ea1cc4c3e1d2cc1c3","last_reissued_at":"2026-07-05T09:54:48.990941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:48.990941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.07012","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":"2026-07-05T09:54:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AZ8lO8DYMDVmRh9q77naFCEq3Z9DvwIsOfTQNIzWZGn3Ri8rQ5KmtsLA53VjlmHDMvnKyy/AiDzDL9zdBhw7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:30:05.026580Z"},"content_sha256":"e37eafcdacae44767c6e8bab3b483a94f01db8ca52a1eded0aaaaa3b84aca848","schema_version":"1.0","event_id":"sha256:e37eafcdacae44767c6e8bab3b483a94f01db8ca52a1eded0aaaaa3b84aca848"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MHLHL4K5WANZ35EFKZ62VR5JYN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"An Yan, Caiming Xiong, Jieyu Zhang, Juan Carlos Niebles, Jun Wang, Le Xue, Linxin Song, Manli Shu, Ranjay Krishna, Ran Xu, Silvio Savarese, Weikai Huang, Zeyuan Chen, Zixian Ma","submitted_at":"2024-12-09T21:44:02Z","abstract_excerpt":"With the rise of multimodal applications, instruction data has become critical for training multimodal language models capable of understanding complex image-based queries. Existing practices rely on powerful but costly large language models (LLMs) or multimodal language models (MLMs) to produce instruction data. These are often prone to hallucinations, licensing issues and the generation process is often hard to scale and interpret. In this work, we present a programmatic approach that employs scene graphs as symbolic representations of images and human-written programs to systematically synt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07012","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/2412.07012/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":"2026-07-05T09:54:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HyQdSXaI/p23YZ85O39fmobGVAAORQRshIIMI35Bhqi0FOJFcAhyNmZ8TNTrok6gib8Lv5+MtUmBRsg64P+aAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:30:05.027264Z"},"content_sha256":"b218df5249225841c3c119fc21a30b983978d0245ebe609c8ead910a8c4e092b","schema_version":"1.0","event_id":"sha256:b218df5249225841c3c119fc21a30b983978d0245ebe609c8ead910a8c4e092b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MHLHL4K5WANZ35EFKZ62VR5JYN/bundle.json","state_url":"https://pith.science/pith/MHLHL4K5WANZ35EFKZ62VR5JYN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MHLHL4K5WANZ35EFKZ62VR5JYN/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":"2026-08-05T01:30:05Z","links":{"resolver":"https://pith.science/pith/MHLHL4K5WANZ35EFKZ62VR5JYN","bundle":"https://pith.science/pith/MHLHL4K5WANZ35EFKZ62VR5JYN/bundle.json","state":"https://pith.science/pith/MHLHL4K5WANZ35EFKZ62VR5JYN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MHLHL4K5WANZ35EFKZ62VR5JYN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MHLHL4K5WANZ35EFKZ62VR5JYN","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":"52a9c5301383b74457f6071715f340c4122e36b8f56bafb3aeb9896bc60b6bbf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T21:44:02Z","title_canon_sha256":"4b29099697354b4f79e24d8065edf563890344e40844de5f9f70b8b7b6f404f8"},"schema_version":"1.0","source":{"id":"2412.07012","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07012","created_at":"2026-07-05T09:54:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07012v3","created_at":"2026-07-05T09:54:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07012","created_at":"2026-07-05T09:54:48Z"},{"alias_kind":"pith_short_12","alias_value":"MHLHL4K5WANZ","created_at":"2026-07-05T09:54:48Z"},{"alias_kind":"pith_short_16","alias_value":"MHLHL4K5WANZ35EF","created_at":"2026-07-05T09:54:48Z"},{"alias_kind":"pith_short_8","alias_value":"MHLHL4K5","created_at":"2026-07-05T09:54:48Z"}],"graph_snapshots":[{"event_id":"sha256:b218df5249225841c3c119fc21a30b983978d0245ebe609c8ead910a8c4e092b","target":"graph","created_at":"2026-07-05T09:54:48Z","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/2412.07012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rise of multimodal applications, instruction data has become critical for training multimodal language models capable of understanding complex image-based queries. Existing practices rely on powerful but costly large language models (LLMs) or multimodal language models (MLMs) to produce instruction data. These are often prone to hallucinations, licensing issues and the generation process is often hard to scale and interpret. In this work, we present a programmatic approach that employs scene graphs as symbolic representations of images and human-written programs to systematically synt","authors_text":"An Yan, Caiming Xiong, Jieyu Zhang, Juan Carlos Niebles, Jun Wang, Le Xue, Linxin Song, Manli Shu, Ranjay Krishna, Ran Xu, Silvio Savarese, Weikai Huang, Zeyuan Chen, Zixian Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T21:44:02Z","title":"ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07012","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:e37eafcdacae44767c6e8bab3b483a94f01db8ca52a1eded0aaaaa3b84aca848","target":"record","created_at":"2026-07-05T09:54:48Z","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":"52a9c5301383b74457f6071715f340c4122e36b8f56bafb3aeb9896bc60b6bbf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T21:44:02Z","title_canon_sha256":"4b29099697354b4f79e24d8065edf563890344e40844de5f9f70b8b7b6f404f8"},"schema_version":"1.0","source":{"id":"2412.07012","kind":"arxiv","version":3}},"canonical_sha256":"61d675f15db01b9df485567daac7a9c375ab5a556115716ea1cc4c3e1d2cc1c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61d675f15db01b9df485567daac7a9c375ab5a556115716ea1cc4c3e1d2cc1c3","first_computed_at":"2026-07-05T09:54:48.990941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:48.990941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NjyCR2kMa0G5yNqrlyM87QVsmkPYw7KAHXGxa+AaOqtHMIJelCppk55Snd7JPTNmIQh6XF6vb+n5MJLZIANJBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:48.991439Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.07012","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e37eafcdacae44767c6e8bab3b483a94f01db8ca52a1eded0aaaaa3b84aca848","sha256:b218df5249225841c3c119fc21a30b983978d0245ebe609c8ead910a8c4e092b"],"state_sha256":"070cc162dba52475968d3017f23f7ab3eb39d46db14b5e03d996741c454e9a06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h2POgsSKOkS4I+tM77kmyoHHn6q9JiaTM13NSrrft7kR9JAt7djNfzVD+byaIiFuWxxgHFmH0ZpyeWFc1XR8Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:30:05.068101Z","bundle_sha256":"5f32f8c3bc418e60d244cdd168d9a656e83b51f3668a3385c5cf74884168537d"}}