{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HTS3IHCUMRQAXYUCG7LUAPMMFS","short_pith_number":"pith:HTS3IHCU","canonical_record":{"source":{"id":"2308.02299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-03T14:17:22Z","cross_cats_sorted":[],"title_canon_sha256":"b9bb585c7f0a7dd9219b477c15552af0cb78a55b5d34a3576ce5e7293d573062","abstract_canon_sha256":"4c31e90d2dd3f02b1a2c25d51c762990428ba222b23f9e3162baae3d29ff9053"},"schema_version":"1.0"},"canonical_sha256":"3ce5b41c5464600be28237d7403d8c2cbd72db565952ab4110aa250e3f33b7db","source":{"kind":"arxiv","id":"2308.02299","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.02299","created_at":"2026-07-05T06:37:40Z"},{"alias_kind":"arxiv_version","alias_value":"2308.02299v1","created_at":"2026-07-05T06:37:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02299","created_at":"2026-07-05T06:37:40Z"},{"alias_kind":"pith_short_12","alias_value":"HTS3IHCUMRQA","created_at":"2026-07-05T06:37:40Z"},{"alias_kind":"pith_short_16","alias_value":"HTS3IHCUMRQAXYUC","created_at":"2026-07-05T06:37:40Z"},{"alias_kind":"pith_short_8","alias_value":"HTS3IHCU","created_at":"2026-07-05T06:37:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HTS3IHCUMRQAXYUCG7LUAPMMFS","target":"record","payload":{"canonical_record":{"source":{"id":"2308.02299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-03T14:17:22Z","cross_cats_sorted":[],"title_canon_sha256":"b9bb585c7f0a7dd9219b477c15552af0cb78a55b5d34a3576ce5e7293d573062","abstract_canon_sha256":"4c31e90d2dd3f02b1a2c25d51c762990428ba222b23f9e3162baae3d29ff9053"},"schema_version":"1.0"},"canonical_sha256":"3ce5b41c5464600be28237d7403d8c2cbd72db565952ab4110aa250e3f33b7db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:40.886093Z","signature_b64":"SyJrTacxXnRDNI1MXiGQU2MDVkRH8HojrXQFmQx2ye/Qp3i+BERGLD8cXSvhOcK922AJYGUa9J1Q5cW/nb0WCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ce5b41c5464600be28237d7403d8c2cbd72db565952ab4110aa250e3f33b7db","last_reissued_at":"2026-07-05T06:37:40.885647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:40.885647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.02299","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":"2026-07-05T06:37:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g3WmVw8gcrPv4j7gTqGCodYfCdCbdyoCIKkVWNBRByeiEwKxwyau9bXjZi+WrHp5OztXTqettJ6Sp2XsJ4X5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:54:35.988864Z"},"content_sha256":"6f90a84aef4365a712b174990add7396939a1a21c44aed8d370b7c1eb6af8b4a","schema_version":"1.0","event_id":"sha256:6f90a84aef4365a712b174990add7396939a1a21c44aed8d370b7c1eb6af8b4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HTS3IHCUMRQAXYUCG7LUAPMMFS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaohui Yu, Fan Wang, Qiang Zhou, Shaofeng Zhang, Sitong Wu, Zhibing Wang","submitted_at":"2023-08-03T14:17:22Z","abstract_excerpt":"In this work, we investigate extending the comprehension of Multi-modal Large Language Models (MLLMs) to regional objects. To this end, we propose to extract features corresponding to regional objects as soft prompts for LLM, which provides a straightforward and scalable approach and eliminates the need for LLM fine-tuning. To effectively extract regional features from regular image features and irregular point cloud features, we present a novel and unified position-assisted feature extraction module. Furthermore, training an MLLM from scratch is highly time-consuming. Thus, we propose increme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02299","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/2308.02299/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":"2026-07-05T06:37:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xXV2sTwhmIYvc1TJogN0RhsCYey3tNV83a+kr2CYUhFONVie2J3YxgTRxYdvg5uLmZyRegyk8CcCzTuLvBDzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:54:35.989238Z"},"content_sha256":"75f6fd43c341d7193a95bb11c721ec6100ea829c689bfaf0239b0e7cd9e77000","schema_version":"1.0","event_id":"sha256:75f6fd43c341d7193a95bb11c721ec6100ea829c689bfaf0239b0e7cd9e77000"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS/bundle.json","state_url":"https://pith.science/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS/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":"2026-07-09T23:54:35Z","links":{"resolver":"https://pith.science/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS","bundle":"https://pith.science/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS/bundle.json","state":"https://pith.science/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HTS3IHCUMRQAXYUCG7LUAPMMFS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HTS3IHCUMRQAXYUCG7LUAPMMFS","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":"4c31e90d2dd3f02b1a2c25d51c762990428ba222b23f9e3162baae3d29ff9053","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-03T14:17:22Z","title_canon_sha256":"b9bb585c7f0a7dd9219b477c15552af0cb78a55b5d34a3576ce5e7293d573062"},"schema_version":"1.0","source":{"id":"2308.02299","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.02299","created_at":"2026-07-05T06:37:40Z"},{"alias_kind":"arxiv_version","alias_value":"2308.02299v1","created_at":"2026-07-05T06:37:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02299","created_at":"2026-07-05T06:37:40Z"},{"alias_kind":"pith_short_12","alias_value":"HTS3IHCUMRQA","created_at":"2026-07-05T06:37:40Z"},{"alias_kind":"pith_short_16","alias_value":"HTS3IHCUMRQAXYUC","created_at":"2026-07-05T06:37:40Z"},{"alias_kind":"pith_short_8","alias_value":"HTS3IHCU","created_at":"2026-07-05T06:37:40Z"}],"graph_snapshots":[{"event_id":"sha256:75f6fd43c341d7193a95bb11c721ec6100ea829c689bfaf0239b0e7cd9e77000","target":"graph","created_at":"2026-07-05T06:37:40Z","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/2308.02299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we investigate extending the comprehension of Multi-modal Large Language Models (MLLMs) to regional objects. To this end, we propose to extract features corresponding to regional objects as soft prompts for LLM, which provides a straightforward and scalable approach and eliminates the need for LLM fine-tuning. To effectively extract regional features from regular image features and irregular point cloud features, we present a novel and unified position-assisted feature extraction module. Furthermore, training an MLLM from scratch is highly time-consuming. Thus, we propose increme","authors_text":"Chaohui Yu, Fan Wang, Qiang Zhou, Shaofeng Zhang, Sitong Wu, Zhibing Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-03T14:17:22Z","title":"RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02299","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":"sha256:6f90a84aef4365a712b174990add7396939a1a21c44aed8d370b7c1eb6af8b4a","target":"record","created_at":"2026-07-05T06:37:40Z","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":"4c31e90d2dd3f02b1a2c25d51c762990428ba222b23f9e3162baae3d29ff9053","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-03T14:17:22Z","title_canon_sha256":"b9bb585c7f0a7dd9219b477c15552af0cb78a55b5d34a3576ce5e7293d573062"},"schema_version":"1.0","source":{"id":"2308.02299","kind":"arxiv","version":1}},"canonical_sha256":"3ce5b41c5464600be28237d7403d8c2cbd72db565952ab4110aa250e3f33b7db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ce5b41c5464600be28237d7403d8c2cbd72db565952ab4110aa250e3f33b7db","first_computed_at":"2026-07-05T06:37:40.885647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:37:40.885647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SyJrTacxXnRDNI1MXiGQU2MDVkRH8HojrXQFmQx2ye/Qp3i+BERGLD8cXSvhOcK922AJYGUa9J1Q5cW/nb0WCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:37:40.886093Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.02299","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f90a84aef4365a712b174990add7396939a1a21c44aed8d370b7c1eb6af8b4a","sha256:75f6fd43c341d7193a95bb11c721ec6100ea829c689bfaf0239b0e7cd9e77000"],"state_sha256":"8da36c04746a5331f2fc9a5765c9b6a1d25234ebf8bf79a9a69a6fdf6ba962f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wv/38s0bztyQLlK3oQlC9qoGblxb11rn/4hUJQPlzzCCXuobDWnF3QlQVYD0QpRUPbANlIfUSHgX87oHccZ+Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T23:54:35.991294Z","bundle_sha256":"8997947f28118ff3e8805b7179cb7dc842a292a002bcd6a89f9558036d66e96e"}}