{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6VFBUGIBTQFVBIS7IWNQANX6TX","short_pith_number":"pith:6VFBUGIB","schema_version":"1.0","canonical_sha256":"f54a1a19019c0b50a25f459b0036fe9de5b5a3537f274e03ea025baa1367da74","source":{"kind":"arxiv","id":"2406.11262","version":2},"attestation_state":"computed","paper":{"title":"Generative Visual Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jefferson Hernandez, Ruben Villegas, Vicente Ordonez","submitted_at":"2024-06-17T07:06:58Z","abstract_excerpt":"We propose to use automatically generated instruction-following data to improve the zero-shot capabilities of a large multimodal model with additional support for generative and image editing tasks. We achieve this by curating a new multimodal instruction-following set using GPT-4V and existing datasets for image generation and editing. Using this instruction set and the existing LLaVA-Finetune instruction set for visual understanding tasks, we produce GenLLaVA, a Generative Large Language and Visual Assistant. GenLLaVA is built through a strategy that combines three types of large pretrained "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.11262","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T07:06:58Z","cross_cats_sorted":[],"title_canon_sha256":"ef234bc70ad8997aed6493226912599511f5c838c8e72259d723e0e26ae66509","abstract_canon_sha256":"e526243858629af0ea4e87da04c82534f43b175c53cf702c883f66477991f031"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:54.510395Z","signature_b64":"d2dW17VDAyhu+bVxKLZcIQYxpXmCZ3m9Etcr1Z5beKIhJDSmnBTx7ZDoZPiFu0tTjMAS6PBLEiU/iv2Lg3E+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f54a1a19019c0b50a25f459b0036fe9de5b5a3537f274e03ea025baa1367da74","last_reissued_at":"2026-07-05T09:14:54.509939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:54.509939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Visual Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jefferson Hernandez, Ruben Villegas, Vicente Ordonez","submitted_at":"2024-06-17T07:06:58Z","abstract_excerpt":"We propose to use automatically generated instruction-following data to improve the zero-shot capabilities of a large multimodal model with additional support for generative and image editing tasks. We achieve this by curating a new multimodal instruction-following set using GPT-4V and existing datasets for image generation and editing. Using this instruction set and the existing LLaVA-Finetune instruction set for visual understanding tasks, we produce GenLLaVA, a Generative Large Language and Visual Assistant. GenLLaVA is built through a strategy that combines three types of large pretrained "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11262","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/2406.11262/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.11262","created_at":"2026-07-05T09:14:54.509995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11262v2","created_at":"2026-07-05T09:14:54.509995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11262","created_at":"2026-07-05T09:14:54.509995+00:00"},{"alias_kind":"pith_short_12","alias_value":"6VFBUGIBTQFV","created_at":"2026-07-05T09:14:54.509995+00:00"},{"alias_kind":"pith_short_16","alias_value":"6VFBUGIBTQFVBIS7","created_at":"2026-07-05T09:14:54.509995+00:00"},{"alias_kind":"pith_short_8","alias_value":"6VFBUGIB","created_at":"2026-07-05T09:14:54.509995+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06814","citing_title":"Diffusion Instruction Tuning","ref_index":2018,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6VFBUGIBTQFVBIS7IWNQANX6TX","json":"https://pith.science/pith/6VFBUGIBTQFVBIS7IWNQANX6TX.json","graph_json":"https://pith.science/api/pith-number/6VFBUGIBTQFVBIS7IWNQANX6TX/graph.json","events_json":"https://pith.science/api/pith-number/6VFBUGIBTQFVBIS7IWNQANX6TX/events.json","paper":"https://pith.science/paper/6VFBUGIB"},"agent_actions":{"view_html":"https://pith.science/pith/6VFBUGIBTQFVBIS7IWNQANX6TX","download_json":"https://pith.science/pith/6VFBUGIBTQFVBIS7IWNQANX6TX.json","view_paper":"https://pith.science/paper/6VFBUGIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11262&json=true","fetch_graph":"https://pith.science/api/pith-number/6VFBUGIBTQFVBIS7IWNQANX6TX/graph.json","fetch_events":"https://pith.science/api/pith-number/6VFBUGIBTQFVBIS7IWNQANX6TX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6VFBUGIBTQFVBIS7IWNQANX6TX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6VFBUGIBTQFVBIS7IWNQANX6TX/action/storage_attestation","attest_author":"https://pith.science/pith/6VFBUGIBTQFVBIS7IWNQANX6TX/action/author_attestation","sign_citation":"https://pith.science/pith/6VFBUGIBTQFVBIS7IWNQANX6TX/action/citation_signature","submit_replication":"https://pith.science/pith/6VFBUGIBTQFVBIS7IWNQANX6TX/action/replication_record"}},"created_at":"2026-07-05T09:14:54.509995+00:00","updated_at":"2026-07-05T09:14:54.509995+00:00"}