{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LQOX6UTFZHQ2ZLOJGKM6TF3PMR","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":"d53cd9d29fc1789d794dc3bc0cbab6ed8214972e5b91a5d3ac6b9e3138a0a4a4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-15T18:58:11Z","title_canon_sha256":"260be27a35a27c260cfb95e2fd6023b1753114a1a5cd64ea71ba3458e9b177fd"},"schema_version":"1.0","source":{"id":"2312.10032","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10032","created_at":"2026-07-05T12:05:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10032v4","created_at":"2026-07-05T12:05:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10032","created_at":"2026-07-05T12:05:58Z"},{"alias_kind":"pith_short_12","alias_value":"LQOX6UTFZHQ2","created_at":"2026-07-05T12:05:58Z"},{"alias_kind":"pith_short_16","alias_value":"LQOX6UTFZHQ2ZLOJ","created_at":"2026-07-05T12:05:58Z"},{"alias_kind":"pith_short_8","alias_value":"LQOX6UTF","created_at":"2026-07-05T12:05:58Z"}],"graph_snapshots":[{"event_id":"sha256:65f74c09a425f0ef6c9c85091635765f7f932602416397e320a0112ed5b034ed","target":"graph","created_at":"2026-07-05T12:05:58Z","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/2312.10032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have recently achieved impressive general-purpose vision-language capabilities through visual instruction tuning. However, current MLLMs primarily focus on image-level or box-level understanding, falling short in achieving fine-grained vision-language alignment at pixel level. Besides, the lack of mask-based instruction data limits their advancements. In this paper, we propose Osprey, a mask-text instruction tuning approach, to extend MLLMs by incorporating fine-grained mask regions into language instruction, aiming at achieving pixel-wise visual unders","authors_text":"Chi Qin, Dongqi Tang, Jianke Zhu, Jian Liu, Lei Zhang, Wentong Li, Xinjie Luo, Yuqian Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-15T18:58:11Z","title":"Osprey: Pixel Understanding with Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10032","kind":"arxiv","version":4},"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":"sha256:65d6f3d64f6c28acdd2c6db2ed0493a8aa7bcd00a4b1b50039edb91407a07068","target":"record","created_at":"2026-07-05T12:05:58Z","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":"d53cd9d29fc1789d794dc3bc0cbab6ed8214972e5b91a5d3ac6b9e3138a0a4a4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-15T18:58:11Z","title_canon_sha256":"260be27a35a27c260cfb95e2fd6023b1753114a1a5cd64ea71ba3458e9b177fd"},"schema_version":"1.0","source":{"id":"2312.10032","kind":"arxiv","version":4}},"canonical_sha256":"5c1d7f5265c9e1acadc93299e9976f644e0395d30a0677b59838594962b6b8cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c1d7f5265c9e1acadc93299e9976f644e0395d30a0677b59838594962b6b8cd","first_computed_at":"2026-07-05T12:05:58.724477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:58.724477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qipm8N1at46ENESpslRkTMSZHzUGE18uat4S1UjbuAVzBGKNl2D6YS7BxRmkotP+GiFPoqHP68uAuVgpWiyyAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:58.725057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.10032","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65d6f3d64f6c28acdd2c6db2ed0493a8aa7bcd00a4b1b50039edb91407a07068","sha256:65f74c09a425f0ef6c9c85091635765f7f932602416397e320a0112ed5b034ed"],"state_sha256":"a64134fe8b97d4d0f93993c64f395eec0213d22e9537322cb023209fc8c20620"}