{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WUI4OANWUOZOLE7EESCBOXOGK5","short_pith_number":"pith:WUI4OANW","canonical_record":{"source":{"id":"2411.18363","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T14:11:10Z","cross_cats_sorted":[],"title_canon_sha256":"076e080982d13e378615af58c6662946a8f245ea9329e1b37735215dd79b5b90","abstract_canon_sha256":"a6c5205dfe31bb593c7c30a130dc5d713b5d46c41ea3255632aeff4a5f0df72d"},"schema_version":"1.0"},"canonical_sha256":"b511c701b6a3b2e593e42484175dc6574bb9b6ed36825b3089309dc6a9683512","source":{"kind":"arxiv","id":"2411.18363","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18363","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18363v3","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18363","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"WUI4OANWUOZO","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"WUI4OANWUOZOLE7E","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"WUI4OANW","created_at":"2026-07-05T10:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WUI4OANWUOZOLE7EESCBOXOGK5","target":"record","payload":{"canonical_record":{"source":{"id":"2411.18363","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T14:11:10Z","cross_cats_sorted":[],"title_canon_sha256":"076e080982d13e378615af58c6662946a8f245ea9329e1b37735215dd79b5b90","abstract_canon_sha256":"a6c5205dfe31bb593c7c30a130dc5d713b5d46c41ea3255632aeff4a5f0df72d"},"schema_version":"1.0"},"canonical_sha256":"b511c701b6a3b2e593e42484175dc6574bb9b6ed36825b3089309dc6a9683512","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:28.398002Z","signature_b64":"aZahYDzdpfzSMLQCRBhwj5gbJX1rOskyKnj9lHoD1ZdnEaYOV62Q6uPRybJsuRM8Yj+0OwaZv2jqKDtdwzQzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b511c701b6a3b2e593e42484175dc6574bb9b6ed36825b3089309dc6a9683512","last_reissued_at":"2026-07-05T10:28:28.397509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:28.397509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.18363","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vPUzTItIF36pnI9d9rGeVjiFlW2GTM6ESVJxnlaiMgCgokPbtXQucolg8ew9/I0oOMF35zWIzUV6uCO06tTXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T14:21:03.100312Z"},"content_sha256":"424a548e6c0fff29f498967451382f584ddcd5493439a8ed3b20c5aaa4d7c250","schema_version":"1.0","event_id":"sha256:424a548e6c0fff29f498967451382f584ddcd5493439a8ed3b20c5aaa4d7c250"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WUI4OANWUOZOLE7EESCBOXOGK5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ChatRex: Taming Multimodal LLM for Joint Perception and Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gen Luo, Lei Zhang, Qing Jiang, Tianhe Ren, Yihao Chen, Yuda Xiong, Yuqin Yang, Zhaoyang Zeng","submitted_at":"2024-11-27T14:11:10Z","abstract_excerpt":"Perception and understanding are two pillars of computer vision. While multimodal large language models (MLLM) have demonstrated remarkable visual understanding capabilities, they arguably lack accurate perception abilities, e.g. the stage-of-the-art model Qwen2-VL only achieves a 43.9 recall rate on the COCO dataset, limiting many tasks requiring the combination of perception and understanding. In this work, we aim to bridge this perception gap from both model designing and data development perspectives. We first introduce ChatRex, an MLLM with a decoupled perception design. Instead of having"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18363","kind":"arxiv","version":3},"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/2411.18363/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":"2026-07-05T10:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HSb6HpPT9KkLhujX+7pRlnvruAPYwTuFH8pMUhCCUnF9ueAgNLakAwNBbeGNfK/1cUGnTgPkqR0lKKlO7WrzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T14:21:03.100736Z"},"content_sha256":"7e857db17fd7db91e524fb3703818d03d55126c2c42ea119798faf5fbc93e0c5","schema_version":"1.0","event_id":"sha256:7e857db17fd7db91e524fb3703818d03d55126c2c42ea119798faf5fbc93e0c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WUI4OANWUOZOLE7EESCBOXOGK5/bundle.json","state_url":"https://pith.science/pith/WUI4OANWUOZOLE7EESCBOXOGK5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WUI4OANWUOZOLE7EESCBOXOGK5/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":"2026-07-18T14:21:03Z","links":{"resolver":"https://pith.science/pith/WUI4OANWUOZOLE7EESCBOXOGK5","bundle":"https://pith.science/pith/WUI4OANWUOZOLE7EESCBOXOGK5/bundle.json","state":"https://pith.science/pith/WUI4OANWUOZOLE7EESCBOXOGK5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WUI4OANWUOZOLE7EESCBOXOGK5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WUI4OANWUOZOLE7EESCBOXOGK5","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":"a6c5205dfe31bb593c7c30a130dc5d713b5d46c41ea3255632aeff4a5f0df72d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T14:11:10Z","title_canon_sha256":"076e080982d13e378615af58c6662946a8f245ea9329e1b37735215dd79b5b90"},"schema_version":"1.0","source":{"id":"2411.18363","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18363","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18363v3","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18363","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"WUI4OANWUOZO","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"WUI4OANWUOZOLE7E","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"WUI4OANW","created_at":"2026-07-05T10:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:7e857db17fd7db91e524fb3703818d03d55126c2c42ea119798faf5fbc93e0c5","target":"graph","created_at":"2026-07-05T10:28:28Z","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/2411.18363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Perception and understanding are two pillars of computer vision. While multimodal large language models (MLLM) have demonstrated remarkable visual understanding capabilities, they arguably lack accurate perception abilities, e.g. the stage-of-the-art model Qwen2-VL only achieves a 43.9 recall rate on the COCO dataset, limiting many tasks requiring the combination of perception and understanding. In this work, we aim to bridge this perception gap from both model designing and data development perspectives. We first introduce ChatRex, an MLLM with a decoupled perception design. Instead of having","authors_text":"Gen Luo, Lei Zhang, Qing Jiang, Tianhe Ren, Yihao Chen, Yuda Xiong, Yuqin Yang, Zhaoyang Zeng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T14:11:10Z","title":"ChatRex: Taming Multimodal LLM for Joint Perception and Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18363","kind":"arxiv","version":3},"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":"sha256:424a548e6c0fff29f498967451382f584ddcd5493439a8ed3b20c5aaa4d7c250","target":"record","created_at":"2026-07-05T10:28:28Z","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":"a6c5205dfe31bb593c7c30a130dc5d713b5d46c41ea3255632aeff4a5f0df72d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T14:11:10Z","title_canon_sha256":"076e080982d13e378615af58c6662946a8f245ea9329e1b37735215dd79b5b90"},"schema_version":"1.0","source":{"id":"2411.18363","kind":"arxiv","version":3}},"canonical_sha256":"b511c701b6a3b2e593e42484175dc6574bb9b6ed36825b3089309dc6a9683512","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b511c701b6a3b2e593e42484175dc6574bb9b6ed36825b3089309dc6a9683512","first_computed_at":"2026-07-05T10:28:28.397509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:28.397509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aZahYDzdpfzSMLQCRBhwj5gbJX1rOskyKnj9lHoD1ZdnEaYOV62Q6uPRybJsuRM8Yj+0OwaZv2jqKDtdwzQzBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:28.398002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18363","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:424a548e6c0fff29f498967451382f584ddcd5493439a8ed3b20c5aaa4d7c250","sha256:7e857db17fd7db91e524fb3703818d03d55126c2c42ea119798faf5fbc93e0c5"],"state_sha256":"134d15c2272665b5a3e3cb75ddc49fed7a0c70b6db23f0e506a8b11d40cc7250"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bsV0i+8pFF3Weeq+/ttKov8lzyAPqF5ApRS2WgS5kc/G6yyGmvbirlJ1c1QFt279bKFjHAnQCD2QCE48kBgeBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T14:21:03.103436Z","bundle_sha256":"0ffee34e71fae6c16858f49c35ce45ed6badbaf5d460aeb9fd31dfffdeaa4205"}}