{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QVYLTILMBDT2P65NYM7G4JOEJL","short_pith_number":"pith:QVYLTILM","canonical_record":{"source":{"id":"2508.12263","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-17T07:18:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"624190ffd66854ae23057debd5813afd3139ef9ad17f2dab1dd72b65a3707bb1","abstract_canon_sha256":"fbf2197273afd875552872eda58c78eb0644ed6f9ecedb58af3eee655b75fa54"},"schema_version":"1.0"},"canonical_sha256":"8570b9a16c08e7a7fbadc33e6e25c44aff850b22aace58f754689498cb306ff8","source":{"kind":"arxiv","id":"2508.12263","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12263","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12263v2","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12263","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_12","alias_value":"QVYLTILMBDT2","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_16","alias_value":"QVYLTILMBDT2P65N","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_8","alias_value":"QVYLTILM","created_at":"2026-07-05T12:01:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QVYLTILMBDT2P65NYM7G4JOEJL","target":"record","payload":{"canonical_record":{"source":{"id":"2508.12263","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-17T07:18:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"624190ffd66854ae23057debd5813afd3139ef9ad17f2dab1dd72b65a3707bb1","abstract_canon_sha256":"fbf2197273afd875552872eda58c78eb0644ed6f9ecedb58af3eee655b75fa54"},"schema_version":"1.0"},"canonical_sha256":"8570b9a16c08e7a7fbadc33e6e25c44aff850b22aace58f754689498cb306ff8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:25.549624Z","signature_b64":"y9U12OKHbQBqg5GOJAhSRa9gEmn9+CYPLz0tij47nuHSvjGrIothlysozUu4ldYkqHgvlAbrjjlYjiQeTZZcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8570b9a16c08e7a7fbadc33e6e25c44aff850b22aace58f754689498cb306ff8","last_reissued_at":"2026-07-05T12:01:25.548739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:25.548739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.12263","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:01:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sM0xt6EtPFmcHyiD09FJXbPnJISEN1dSQa3Ah6EvGMQ+qrgSgHLneELXp1dNx/VWAuMOzfIzjraLMxKcZMoWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:23:03.670812Z"},"content_sha256":"1bebae36258dbe4e792721ab76e918738a2d821cdc4dc37801960a7df38f68f6","schema_version":"1.0","event_id":"sha256:1bebae36258dbe4e792721ab76e918738a2d821cdc4dc37801960a7df38f68f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QVYLTILMBDT2P65NYM7G4JOEJL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Region-Level Context-Aware Multimodal Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Debin Zhao, Hongliang Wei, Xianqi Zhang, Xiaopeng Fan, Xingtao Wang","submitted_at":"2025-08-17T07:18:43Z","abstract_excerpt":"Despite significant progress, existing research on Multimodal Large Language Models (MLLMs) mainly focuses on general visual understanding, overlooking the ability to integrate textual context associated with objects for a more context-aware multimodal understanding -- an ability we refer to as Region-level Context-aware Multimodal Understanding (RCMU). To address this limitation, we first formulate the RCMU task, which requires models to respond to user instructions by integrating both image content and textual information of regions or objects. To equip MLLMs with RCMU capabilities, we propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12263","kind":"arxiv","version":2},"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/2508.12263/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":"2026-07-05T12:01:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8aPttM40GqXZUa86l/GSp+R+5vB7fKwDMjHHfx+CIc2HtI78bULJEfgURxuAaQgV0mDr55Qt5PGKHx2a15qrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:23:03.671329Z"},"content_sha256":"88e1d80f444066148f1e32442cf0250fdf5d94bdc6e265d4c3d89da39c83d476","schema_version":"1.0","event_id":"sha256:88e1d80f444066148f1e32442cf0250fdf5d94bdc6e265d4c3d89da39c83d476"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QVYLTILMBDT2P65NYM7G4JOEJL/bundle.json","state_url":"https://pith.science/pith/QVYLTILMBDT2P65NYM7G4JOEJL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QVYLTILMBDT2P65NYM7G4JOEJL/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":"2026-08-09T08:23:03Z","links":{"resolver":"https://pith.science/pith/QVYLTILMBDT2P65NYM7G4JOEJL","bundle":"https://pith.science/pith/QVYLTILMBDT2P65NYM7G4JOEJL/bundle.json","state":"https://pith.science/pith/QVYLTILMBDT2P65NYM7G4JOEJL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QVYLTILMBDT2P65NYM7G4JOEJL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QVYLTILMBDT2P65NYM7G4JOEJL","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":"fbf2197273afd875552872eda58c78eb0644ed6f9ecedb58af3eee655b75fa54","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-17T07:18:43Z","title_canon_sha256":"624190ffd66854ae23057debd5813afd3139ef9ad17f2dab1dd72b65a3707bb1"},"schema_version":"1.0","source":{"id":"2508.12263","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12263","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12263v2","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12263","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_12","alias_value":"QVYLTILMBDT2","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_16","alias_value":"QVYLTILMBDT2P65N","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_8","alias_value":"QVYLTILM","created_at":"2026-07-05T12:01:25Z"}],"graph_snapshots":[{"event_id":"sha256:88e1d80f444066148f1e32442cf0250fdf5d94bdc6e265d4c3d89da39c83d476","target":"graph","created_at":"2026-07-05T12:01:25Z","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/2508.12263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant progress, existing research on Multimodal Large Language Models (MLLMs) mainly focuses on general visual understanding, overlooking the ability to integrate textual context associated with objects for a more context-aware multimodal understanding -- an ability we refer to as Region-level Context-aware Multimodal Understanding (RCMU). To address this limitation, we first formulate the RCMU task, which requires models to respond to user instructions by integrating both image content and textual information of regions or objects. To equip MLLMs with RCMU capabilities, we propo","authors_text":"Debin Zhao, Hongliang Wei, Xianqi Zhang, Xiaopeng Fan, Xingtao Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-17T07:18:43Z","title":"Region-Level Context-Aware Multimodal Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12263","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":"sha256:1bebae36258dbe4e792721ab76e918738a2d821cdc4dc37801960a7df38f68f6","target":"record","created_at":"2026-07-05T12:01:25Z","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":"fbf2197273afd875552872eda58c78eb0644ed6f9ecedb58af3eee655b75fa54","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-17T07:18:43Z","title_canon_sha256":"624190ffd66854ae23057debd5813afd3139ef9ad17f2dab1dd72b65a3707bb1"},"schema_version":"1.0","source":{"id":"2508.12263","kind":"arxiv","version":2}},"canonical_sha256":"8570b9a16c08e7a7fbadc33e6e25c44aff850b22aace58f754689498cb306ff8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8570b9a16c08e7a7fbadc33e6e25c44aff850b22aace58f754689498cb306ff8","first_computed_at":"2026-07-05T12:01:25.548739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:25.548739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y9U12OKHbQBqg5GOJAhSRa9gEmn9+CYPLz0tij47nuHSvjGrIothlysozUu4ldYkqHgvlAbrjjlYjiQeTZZcBA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:25.549624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.12263","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bebae36258dbe4e792721ab76e918738a2d821cdc4dc37801960a7df38f68f6","sha256:88e1d80f444066148f1e32442cf0250fdf5d94bdc6e265d4c3d89da39c83d476"],"state_sha256":"a7eca59779b0d50fb5b5d219c746f5f0100dd2df0184bbaba09468d9ac72fa55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d47wcAPO8H/HwvpnfQ8C6k+/rU+7ymd3u5idn6FjLvUpXQIOYe22nFexlV4ywus7Cu8zD7WCD7biZ9S+JsMiDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:23:03.675305Z","bundle_sha256":"3f1149380ea55e3f3d99ad4ffa1a6eb15acc6bce8a1211b2759fa6695c653047"}}