{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RLBPL3HLLV3IGL6ZKGGWRCLPVZ","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":"76cd31349dc8b44cbafdbcfef283a58f55948b2a89d1a8f23e667f2ba6d5a53c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-25T17:59:13Z","title_canon_sha256":"b4c4b265d95e1f691c8ebf76db51edcf01d524aca141e80249435d34be014b22"},"schema_version":"1.0","source":{"id":"2409.17143","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17143","created_at":"2026-07-05T09:11:44Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17143v1","created_at":"2026-07-05T09:11:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17143","created_at":"2026-07-05T09:11:44Z"},{"alias_kind":"pith_short_12","alias_value":"RLBPL3HLLV3I","created_at":"2026-07-05T09:11:44Z"},{"alias_kind":"pith_short_16","alias_value":"RLBPL3HLLV3IGL6Z","created_at":"2026-07-05T09:11:44Z"},{"alias_kind":"pith_short_8","alias_value":"RLBPL3HL","created_at":"2026-07-05T09:11:44Z"}],"graph_snapshots":[{"event_id":"sha256:fd0c5f8f9b31459040c9c8c0e2e013c77440939bbc8d1955586f882c1dbc1196","target":"graph","created_at":"2026-07-05T09:11:44Z","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/2409.17143/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compared with Large Language Models (LLMs), Large Vision-Language Models (LVLMs) can also accept images as input, thus showcasing more interesting emergent capabilities and demonstrating impressive performance on various vision-language tasks. Motivated by text prompting in LLMs, visual prompting has been explored to enhance LVLMs' capabilities of perceiving visual information. However, previous visual prompting techniques solely process visual inputs without considering text queries, limiting the models' ability to follow text instructions to complete tasks. To fill this gap, in this work, we","authors_text":"Runpeng Yu, Weihao Yu, Xinchao Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-25T17:59:13Z","title":"Attention Prompting on Image for Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17143","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":"sha256:8a8fd97121a1379766ec69b3ada853f404119b296c97087ab817769ddb079c9d","target":"record","created_at":"2026-07-05T09:11:44Z","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":"76cd31349dc8b44cbafdbcfef283a58f55948b2a89d1a8f23e667f2ba6d5a53c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-25T17:59:13Z","title_canon_sha256":"b4c4b265d95e1f691c8ebf76db51edcf01d524aca141e80249435d34be014b22"},"schema_version":"1.0","source":{"id":"2409.17143","kind":"arxiv","version":1}},"canonical_sha256":"8ac2f5eceb5d76832fd9518d68896fae5fbe875f54672f4ce79f4bdad21e02a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ac2f5eceb5d76832fd9518d68896fae5fbe875f54672f4ce79f4bdad21e02a0","first_computed_at":"2026-07-05T09:11:44.769166Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:44.769166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4ezf7nEEtxwHBBj+pretfbKYbkaDFBjyP/H7oZo7NKd2wKX3Z8VEpq2AulTkPsMzhtR2rFPeMqxqffvsSBKICA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:44.769630Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17143","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a8fd97121a1379766ec69b3ada853f404119b296c97087ab817769ddb079c9d","sha256:fd0c5f8f9b31459040c9c8c0e2e013c77440939bbc8d1955586f882c1dbc1196"],"state_sha256":"5690f9d3d3b85507c5c4709c8f59d6d8f40c3d1e658466969237e2be4ef00813"}