{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WQM6LFRS5FSLQH5EIENT3J6YA3","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":"dde388c88b1039d8547f042603877ecb2c288a4813d3824119ef934639033e09","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-03T06:40:21Z","title_canon_sha256":"3490db219fc64a9feeacd0d8bb06ef82d4988dc3ee9232f06616a0b32ba9f2fb"},"schema_version":"1.0","source":{"id":"2503.01222","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01222","created_at":"2026-07-05T11:07:21Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01222v2","created_at":"2026-07-05T11:07:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01222","created_at":"2026-07-05T11:07:21Z"},{"alias_kind":"pith_short_12","alias_value":"WQM6LFRS5FSL","created_at":"2026-07-05T11:07:21Z"},{"alias_kind":"pith_short_16","alias_value":"WQM6LFRS5FSLQH5E","created_at":"2026-07-05T11:07:21Z"},{"alias_kind":"pith_short_8","alias_value":"WQM6LFRS","created_at":"2026-07-05T11:07:21Z"}],"graph_snapshots":[{"event_id":"sha256:9a6bca0c7837874806a19cd1cbd1cdedd84e6eef7279e4b4f5069228fda98848","target":"graph","created_at":"2026-07-05T11:07:21Z","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/2503.01222/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-resolution (HR) image perception remains a key challenge in multimodal large language models (MLLMs). To overcome the limitations of existing methods, this paper shifts away from prior dedicated heuristic approaches and revisits the most fundamental idea to HR perception by enhancing the long-context capability of MLLMs, driven by recent advances in long-context techniques like retrieval-augmented generation (RAG) for general LLMs. Towards this end, this paper presents the first study exploring the use of RAG to address HR perception challenges. Specifically, we propose Retrieval-Augmente","authors_text":"Bo Du, Dacheng Tao, Liang Ding, Li Shen, Wenbin Wang, Yingjie Wang, Yongcheng Jing, Yong Luo","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-03T06:40:21Z","title":"Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01222","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:fef0247a73cd57fe3624e1a94bbe72f5217ab2309702e14cee8da90a4e7e321a","target":"record","created_at":"2026-07-05T11:07:21Z","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":"dde388c88b1039d8547f042603877ecb2c288a4813d3824119ef934639033e09","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-03T06:40:21Z","title_canon_sha256":"3490db219fc64a9feeacd0d8bb06ef82d4988dc3ee9232f06616a0b32ba9f2fb"},"schema_version":"1.0","source":{"id":"2503.01222","kind":"arxiv","version":2}},"canonical_sha256":"b419e59632e964b81fa4411b3da7d806f350b84a5a9b87c0c4bb14b2ed05af34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b419e59632e964b81fa4411b3da7d806f350b84a5a9b87c0c4bb14b2ed05af34","first_computed_at":"2026-07-05T11:07:21.105045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:21.105045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m9/t/zREB2pgyFkz5fwfWIVKgmQ5P2tJNuhW/P8CDmb3ComZ2tMXOBIYCh7RFtRP6zuh2aw9PMA6ZhneJiyAAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:21.105565Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01222","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fef0247a73cd57fe3624e1a94bbe72f5217ab2309702e14cee8da90a4e7e321a","sha256:9a6bca0c7837874806a19cd1cbd1cdedd84e6eef7279e4b4f5069228fda98848"],"state_sha256":"98548a31fb308f0692df1534ba4f44208e8b824b7969569c9061fa1ca29a762d"}