{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DCC6O3Y2JRL6MFHSLLBKAH67CP","short_pith_number":"pith:DCC6O3Y2","canonical_record":{"source":{"id":"2505.06840","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-11T04:44:03Z","cross_cats_sorted":[],"title_canon_sha256":"90178e23052e1b73ccbbe6ab863e7317b2be6ce817f4bc5d1ac4c257b474adaf","abstract_canon_sha256":"4ea7e5c1f17250ee6fa79e730769e7c1542f1f4448e76880d942fafb327e1f00"},"schema_version":"1.0"},"canonical_sha256":"1885e76f1a4c57e614f25ac2a01fdf13d03fd10473f88aca0a970eec0b4df2a7","source":{"kind":"arxiv","id":"2505.06840","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DCC6O3Y2JRL6MFHSLLBKAH67CP","target":"record","payload":{"canonical_record":{"source":{"id":"2505.06840","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-11T04:44:03Z","cross_cats_sorted":[],"title_canon_sha256":"90178e23052e1b73ccbbe6ab863e7317b2be6ce817f4bc5d1ac4c257b474adaf","abstract_canon_sha256":"4ea7e5c1f17250ee6fa79e730769e7c1542f1f4448e76880d942fafb327e1f00"},"schema_version":"1.0"},"canonical_sha256":"1885e76f1a4c57e614f25ac2a01fdf13d03fd10473f88aca0a970eec0b4df2a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:37.709187Z","signature_b64":"JRfGRgiqDXORW0Gl+qKA8ELRG1e8JWOmiT+3l2MMNu0+823D4En96AXdt2pyv7NKtoYHDERnhS1P0Wbn6q+eBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1885e76f1a4c57e614f25ac2a01fdf13d03fd10473f88aca0a970eec0b4df2a7","last_reissued_at":"2026-07-05T11:01:37.708732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:37.708732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.06840","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GtcVsKJkDBGPpvkFxM/uC1VfbOu4rwzrYknDcrAS84g/qY9+ytiYz0vOt1zRAJ5tZO3xzRyM8KxfATJ2Xwm/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:38:38.267893Z"},"content_sha256":"ef3d776b516dadcc11b85f532e67791821cbff22c4be158da5a7c607b7611a69","schema_version":"1.0","event_id":"sha256:ef3d776b516dadcc11b85f532e67791821cbff22c4be158da5a7c607b7611a69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DCC6O3Y2JRL6MFHSLLBKAH67CP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Instruction Tuning with Chain of Region-of-Interest","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernie Wang, Boran Han, Shuai Zhang, Yixin Chen","submitted_at":"2025-05-11T04:44:03Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06840","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.06840/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pin5OZ+BMzGxNZkKGDPWtCwlfFtT2JuKmjta964flGuPdwTbtWV4xMxuDF91yupEg7HJrwJ9VOfp6fWT+d4gDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:38:38.268427Z"},"content_sha256":"51b436661670a58c20621ad340021d01eb45acaa77935d9d6d8cabdc1fce4f2f","schema_version":"1.0","event_id":"sha256:51b436661670a58c20621ad340021d01eb45acaa77935d9d6d8cabdc1fce4f2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DCC6O3Y2JRL6MFHSLLBKAH67CP/bundle.json","state_url":"https://pith.science/pith/DCC6O3Y2JRL6MFHSLLBKAH67CP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DCC6O3Y2JRL6MFHSLLBKAH67CP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T07:38:38Z","links":{"resolver":"https://pith.science/pith/DCC6O3Y2JRL6MFHSLLBKAH67CP","bundle":"https://pith.science/pith/DCC6O3Y2JRL6MFHSLLBKAH67CP/bundle.json","state":"https://pith.science/pith/DCC6O3Y2JRL6MFHSLLBKAH67CP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DCC6O3Y2JRL6MFHSLLBKAH67CP/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DVd7Kh8PjcdZRr7Nq1A++KRAS50M3/xBkbX6P4bbkW3F7n+O+XaxLbSMxKxzcOcttRkar9mUD8qXxj5tPhrSCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T07:38:38.273281Z","bundle_sha256":"f0818eb9f5637bf74cff341ec2cdc199b8dea7fdee5402b16d675e817f983fbf"}}