{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6VFBUGIBTQFVBIS7IWNQANX6TX","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":"e526243858629af0ea4e87da04c82534f43b175c53cf702c883f66477991f031","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T07:06:58Z","title_canon_sha256":"ef234bc70ad8997aed6493226912599511f5c838c8e72259d723e0e26ae66509"},"schema_version":"1.0","source":{"id":"2406.11262","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11262","created_at":"2026-07-05T09:14:54Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11262v2","created_at":"2026-07-05T09:14:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11262","created_at":"2026-07-05T09:14:54Z"},{"alias_kind":"pith_short_12","alias_value":"6VFBUGIBTQFV","created_at":"2026-07-05T09:14:54Z"},{"alias_kind":"pith_short_16","alias_value":"6VFBUGIBTQFVBIS7","created_at":"2026-07-05T09:14:54Z"},{"alias_kind":"pith_short_8","alias_value":"6VFBUGIB","created_at":"2026-07-05T09:14:54Z"}],"graph_snapshots":[{"event_id":"sha256:019d6eac46c5e2cac9bab3951bf7a8348e806225187813f6f502e795d4a226fb","target":"graph","created_at":"2026-07-05T09:14:54Z","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/2406.11262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jefferson Hernandez, Ruben Villegas, Vicente Ordonez","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T07:06:58Z","title":"Generative Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11262","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":"sha256:0919b8f78b39a1e2202a9f36918cee71a95a49f8ef902daf599b37e613299b78","target":"record","created_at":"2026-07-05T09:14:54Z","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":"e526243858629af0ea4e87da04c82534f43b175c53cf702c883f66477991f031","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T07:06:58Z","title_canon_sha256":"ef234bc70ad8997aed6493226912599511f5c838c8e72259d723e0e26ae66509"},"schema_version":"1.0","source":{"id":"2406.11262","kind":"arxiv","version":2}},"canonical_sha256":"f54a1a19019c0b50a25f459b0036fe9de5b5a3537f274e03ea025baa1367da74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f54a1a19019c0b50a25f459b0036fe9de5b5a3537f274e03ea025baa1367da74","first_computed_at":"2026-07-05T09:14:54.509939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:54.509939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d2dW17VDAyhu+bVxKLZcIQYxpXmCZ3m9Etcr1Z5beKIhJDSmnBTx7ZDoZPiFu0tTjMAS6PBLEiU/iv2Lg3E+AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:54.510395Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11262","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0919b8f78b39a1e2202a9f36918cee71a95a49f8ef902daf599b37e613299b78","sha256:019d6eac46c5e2cac9bab3951bf7a8348e806225187813f6f502e795d4a226fb"],"state_sha256":"ba79515cb20e21ee372d90bab9da80c7f90879104f1b79c296b31820f1248d4b"}