{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Y7V2MM6GVB7BNBLLZX4W2QQ7LH","short_pith_number":"pith:Y7V2MM6G","canonical_record":{"source":{"id":"2312.06731","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T09:44:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec26644f2905015a79e730d5e44a8fba7b9d8c2fcc067a5535eb119368c40d1d","abstract_canon_sha256":"8ff24a959581d76fc5f83ce6e1038ab90b82385667d792126c44e74ad146cf0b"},"schema_version":"1.0"},"canonical_sha256":"c7eba633c6a87e16856bcdf96d421f59dcdf747cb4761dc43db99fdbbef3a4ed","source":{"kind":"arxiv","id":"2312.06731","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06731","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06731v6","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06731","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"Y7V2MM6GVB7B","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"pith_short_16","alias_value":"Y7V2MM6GVB7BNBLL","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"pith_short_8","alias_value":"Y7V2MM6G","created_at":"2026-07-05T09:00:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Y7V2MM6GVB7BNBLLZX4W2QQ7LH","target":"record","payload":{"canonical_record":{"source":{"id":"2312.06731","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T09:44:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec26644f2905015a79e730d5e44a8fba7b9d8c2fcc067a5535eb119368c40d1d","abstract_canon_sha256":"8ff24a959581d76fc5f83ce6e1038ab90b82385667d792126c44e74ad146cf0b"},"schema_version":"1.0"},"canonical_sha256":"c7eba633c6a87e16856bcdf96d421f59dcdf747cb4761dc43db99fdbbef3a4ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:00.970572Z","signature_b64":"DW90lxrzFNY7ryThaBFuCEV5CW11s/dQkPeY+TY8GuuvGilChSy4Wi51Ll5fkE3orKPuQc7tgv04mGYp9YmsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7eba633c6a87e16856bcdf96d421f59dcdf747cb4761dc43db99fdbbef3a4ed","last_reissued_at":"2026-07-05T09:00:00.970159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:00.970159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.06731","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j9q+ui+ECMwiz0RNAteZHNzJwGFofkkYf9geA6pozJ8XWYbiJsfTdCBriZG2O1gRmL0rZB0oTAnFGe9WK3KZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T10:33:55.732728Z"},"content_sha256":"0878d76613388007a1782cee3672b1eee0a82614b930385247d08c4d45f6082a","schema_version":"1.0","event_id":"sha256:0878d76613388007a1782cee3672b1eee0a82614b930385247d08c4d45f6082a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Y7V2MM6GVB7BNBLLZX4W2QQ7LH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Henry Hengyuan Zhao, Mike Zheng Shou, Pan Zhou","submitted_at":"2023-12-11T09:44:41Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) demonstrate exceptional problem-solving capabilities, but few research studies aim to gauge the ability to generate visual instruction tuning data. This paper proposes to explore the potential of empowering MLLMs to generate data independently without relying on GPT-4. We introduce Genixer, a comprehensive data generation pipeline consisting of four key steps: (i) instruction data collection, (ii) instruction template design, (iii) empowering MLLMs, and (iv) data generation and filtering. Additionally, we outline two modes of data generation: task-agnos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06731","kind":"arxiv","version":6},"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/2312.06731/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":"2026-07-05T09:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZlX5zhueOjQl1xNZdqf3ENfFoy+rAp8qEwjM7P5q11MPA9ttt1DDoyfwmDY4EjmEtEg/vaej7X9MmXicwXzsAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T10:33:55.733547Z"},"content_sha256":"154fad47ce08ea1644a41822ea4311cbf719f625d456cbb658bb8adc33e54ac5","schema_version":"1.0","event_id":"sha256:154fad47ce08ea1644a41822ea4311cbf719f625d456cbb658bb8adc33e54ac5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y7V2MM6GVB7BNBLLZX4W2QQ7LH/bundle.json","state_url":"https://pith.science/pith/Y7V2MM6GVB7BNBLLZX4W2QQ7LH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y7V2MM6GVB7BNBLLZX4W2QQ7LH/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":"2026-08-12T10:33:55Z","links":{"resolver":"https://pith.science/pith/Y7V2MM6GVB7BNBLLZX4W2QQ7LH","bundle":"https://pith.science/pith/Y7V2MM6GVB7BNBLLZX4W2QQ7LH/bundle.json","state":"https://pith.science/pith/Y7V2MM6GVB7BNBLLZX4W2QQ7LH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y7V2MM6GVB7BNBLLZX4W2QQ7LH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y7V2MM6GVB7BNBLLZX4W2QQ7LH","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":"8ff24a959581d76fc5f83ce6e1038ab90b82385667d792126c44e74ad146cf0b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T09:44:41Z","title_canon_sha256":"ec26644f2905015a79e730d5e44a8fba7b9d8c2fcc067a5535eb119368c40d1d"},"schema_version":"1.0","source":{"id":"2312.06731","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06731","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06731v6","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06731","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"Y7V2MM6GVB7B","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"pith_short_16","alias_value":"Y7V2MM6GVB7BNBLL","created_at":"2026-07-05T09:00:00Z"},{"alias_kind":"pith_short_8","alias_value":"Y7V2MM6G","created_at":"2026-07-05T09:00:00Z"}],"graph_snapshots":[{"event_id":"sha256:154fad47ce08ea1644a41822ea4311cbf719f625d456cbb658bb8adc33e54ac5","target":"graph","created_at":"2026-07-05T09:00:00Z","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/2312.06731/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) demonstrate exceptional problem-solving capabilities, but few research studies aim to gauge the ability to generate visual instruction tuning data. This paper proposes to explore the potential of empowering MLLMs to generate data independently without relying on GPT-4. We introduce Genixer, a comprehensive data generation pipeline consisting of four key steps: (i) instruction data collection, (ii) instruction template design, (iii) empowering MLLMs, and (iv) data generation and filtering. Additionally, we outline two modes of data generation: task-agnos","authors_text":"Henry Hengyuan Zhao, Mike Zheng Shou, Pan Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T09:44:41Z","title":"Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06731","kind":"arxiv","version":6},"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":"sha256:0878d76613388007a1782cee3672b1eee0a82614b930385247d08c4d45f6082a","target":"record","created_at":"2026-07-05T09:00:00Z","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":"8ff24a959581d76fc5f83ce6e1038ab90b82385667d792126c44e74ad146cf0b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T09:44:41Z","title_canon_sha256":"ec26644f2905015a79e730d5e44a8fba7b9d8c2fcc067a5535eb119368c40d1d"},"schema_version":"1.0","source":{"id":"2312.06731","kind":"arxiv","version":6}},"canonical_sha256":"c7eba633c6a87e16856bcdf96d421f59dcdf747cb4761dc43db99fdbbef3a4ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7eba633c6a87e16856bcdf96d421f59dcdf747cb4761dc43db99fdbbef3a4ed","first_computed_at":"2026-07-05T09:00:00.970159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:00.970159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DW90lxrzFNY7ryThaBFuCEV5CW11s/dQkPeY+TY8GuuvGilChSy4Wi51Ll5fkE3orKPuQc7tgv04mGYp9YmsBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:00.970572Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06731","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0878d76613388007a1782cee3672b1eee0a82614b930385247d08c4d45f6082a","sha256:154fad47ce08ea1644a41822ea4311cbf719f625d456cbb658bb8adc33e54ac5"],"state_sha256":"fc3b4db033da06f9a4090fabe1ebbda6fbf082c75e69eb8338e4c37068866bae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u3GFks8Q4DDGC8X6CsL2Zxmp55Vgp5f9BcRw0CX9wJqv2sea50Wih//S14UIZiyf197zqkkMgM6WqquM1NjRAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T10:33:55.748642Z","bundle_sha256":"90352978b486cb8b4902abfecd4809a90822fe54d3313cf745a548c2da6875b5"}}