{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DCC6O3Y2JRL6MFHSLLBKAH67CP","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":"4ea7e5c1f17250ee6fa79e730769e7c1542f1f4448e76880d942fafb327e1f00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-11T04:44:03Z","title_canon_sha256":"90178e23052e1b73ccbbe6ab863e7317b2be6ce817f4bc5d1ac4c257b474adaf"},"schema_version":"1.0","source":{"id":"2505.06840","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06840","created_at":"2026-07-05T11:01:37Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06840v1","created_at":"2026-07-05T11:01:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06840","created_at":"2026-07-05T11:01:37Z"},{"alias_kind":"pith_short_12","alias_value":"DCC6O3Y2JRL6","created_at":"2026-07-05T11:01:37Z"},{"alias_kind":"pith_short_16","alias_value":"DCC6O3Y2JRL6MFHS","created_at":"2026-07-05T11:01:37Z"},{"alias_kind":"pith_short_8","alias_value":"DCC6O3Y2","created_at":"2026-07-05T11:01:37Z"}],"graph_snapshots":[{"event_id":"sha256:51b436661670a58c20621ad340021d01eb45acaa77935d9d6d8cabdc1fce4f2f","target":"graph","created_at":"2026-07-05T11:01:37Z","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/2505.06840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-resolution (HR) images are pivotal for enhancing the recognition and understanding capabilities of multimodal large language models (MLLMs). However, directly increasing image resolution can significantly escalate computational demands. In this study, we propose a method called Chain of Region-of-Interest (CoRoI) for Visual Instruction Tuning, aimed at alleviating the computational burden associated with high-resolution images for MLLMs. Drawing inspiration from the selective nature of the human visual system, we recognize that not all regions within high-resolution images carry equal imp","authors_text":"Bernie Wang, Boran Han, Shuai Zhang, Yixin Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-11T04:44:03Z","title":"Visual Instruction Tuning with Chain of Region-of-Interest"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06840","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:ef3d776b516dadcc11b85f532e67791821cbff22c4be158da5a7c607b7611a69","target":"record","created_at":"2026-07-05T11:01:37Z","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":"4ea7e5c1f17250ee6fa79e730769e7c1542f1f4448e76880d942fafb327e1f00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-11T04:44:03Z","title_canon_sha256":"90178e23052e1b73ccbbe6ab863e7317b2be6ce817f4bc5d1ac4c257b474adaf"},"schema_version":"1.0","source":{"id":"2505.06840","kind":"arxiv","version":1}},"canonical_sha256":"1885e76f1a4c57e614f25ac2a01fdf13d03fd10473f88aca0a970eec0b4df2a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1885e76f1a4c57e614f25ac2a01fdf13d03fd10473f88aca0a970eec0b4df2a7","first_computed_at":"2026-07-05T11:01:37.708732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:37.708732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JRfGRgiqDXORW0Gl+qKA8ELRG1e8JWOmiT+3l2MMNu0+823D4En96AXdt2pyv7NKtoYHDERnhS1P0Wbn6q+eBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:37.709187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06840","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef3d776b516dadcc11b85f532e67791821cbff22c4be158da5a7c607b7611a69","sha256:51b436661670a58c20621ad340021d01eb45acaa77935d9d6d8cabdc1fce4f2f"],"state_sha256":"fe634c7a1ae8f0a87af1edbb404d2be40635de7f22c8071d2447eb6a0eeaf893"}