{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RO7ZSOQSVLLAOI3ULOYF3JCUBX","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":"d23fbd30424d6c00a2796d46cd5d6439c1c79a636412e269b93d2e1ff924fa0b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-05T08:47:34Z","title_canon_sha256":"6187fa1658cd86c4d7c6f9c4933b0e5fdbc901fb7e9072c5f04f6350b9d933ee"},"schema_version":"1.0","source":{"id":"2409.15310","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15310","created_at":"2026-07-05T09:10:52Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15310v1","created_at":"2026-07-05T09:10:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15310","created_at":"2026-07-05T09:10:52Z"},{"alias_kind":"pith_short_12","alias_value":"RO7ZSOQSVLLA","created_at":"2026-07-05T09:10:52Z"},{"alias_kind":"pith_short_16","alias_value":"RO7ZSOQSVLLAOI3U","created_at":"2026-07-05T09:10:52Z"},{"alias_kind":"pith_short_8","alias_value":"RO7ZSOQS","created_at":"2026-07-05T09:10:52Z"}],"graph_snapshots":[{"event_id":"sha256:e41360fda606158b0161299fb180df14c7f88fe14aea1765601acd77ad0ac4cf","target":"graph","created_at":"2026-07-05T09:10:52Z","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/2409.15310/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) equip pre-trained large-language models (LLMs) with visual capabilities. While textual prompting in LLMs has been widely studied, visual prompting has emerged for more fine-grained and free-form visual instructions. This paper presents the first comprehensive survey on visual prompting methods in MLLMs, focusing on visual prompting, prompt generation, compositional reasoning, and prompt learning. We categorize existing visual prompts and discuss generative methods for automatic prompt annotations on the images. We also examine visual prompting methods t","authors_text":"Aaron Chang, Dimitris N. Metaxas, Jingbo Shang, Julian McAuley, Junda Wu, Lina Yao, Ruiyi Zhang, Ryan A. Rossi, Subrata Mitra, Sungchul Kim, Tong Yu, Xintong Li, Yu Xia, Zhaoyang Xia, Zhehao Zhang","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-05T08:47:34Z","title":"Visual Prompting in Multimodal Large Language Models: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15310","kind":"arxiv","version":1},"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:baf7d3ab4309e3216a91e8167ee28214d37e055cdbd0e0c02ed8398a526c5f57","target":"record","created_at":"2026-07-05T09:10:52Z","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":"d23fbd30424d6c00a2796d46cd5d6439c1c79a636412e269b93d2e1ff924fa0b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-05T08:47:34Z","title_canon_sha256":"6187fa1658cd86c4d7c6f9c4933b0e5fdbc901fb7e9072c5f04f6350b9d933ee"},"schema_version":"1.0","source":{"id":"2409.15310","kind":"arxiv","version":1}},"canonical_sha256":"8bbf993a12aad60723745bb05da4540dd36eb5516ac831a28d2c2c6e6f6d6bc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bbf993a12aad60723745bb05da4540dd36eb5516ac831a28d2c2c6e6f6d6bc8","first_computed_at":"2026-07-05T09:10:52.762781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:52.762781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p7UGl8oNf0gwJK2HUGYsaEHEo/s8XGHN2M7Uuky4/lnwTdOdXysSsb58bS6yQabSYuLffBzD4j4lZ2SZHOHRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:52.763617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.15310","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baf7d3ab4309e3216a91e8167ee28214d37e055cdbd0e0c02ed8398a526c5f57","sha256:e41360fda606158b0161299fb180df14c7f88fe14aea1765601acd77ad0ac4cf"],"state_sha256":"56d4f3f977788bf3482deb09aacbe67584a0b51154df826ee581f187f2f3ab6c"}