{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FB3QAIVXPARJAYZ6DJHVWEOXIV","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":"34b80a5b889bc2f64046e0ee6b86eb8d35cee9df72f8b94de46d06f95094f4af","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T09:02:00Z","title_canon_sha256":"2ef80e8dc6c495d20413ceef8769fd0b762dec7085885452deeb752a6a7ae486"},"schema_version":"1.0","source":{"id":"2401.13307","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13307","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13307v1","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13307","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"pith_short_12","alias_value":"FB3QAIVXPARJ","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"pith_short_16","alias_value":"FB3QAIVXPARJAYZ6","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"pith_short_8","alias_value":"FB3QAIVX","created_at":"2026-07-05T07:37:03Z"}],"graph_snapshots":[{"event_id":"sha256:a1d04c252ca24bca749cdfe1446e700482b6b085804f57150b2b7e57bcf7605e","target":"graph","created_at":"2026-07-05T07:37:03Z","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/2401.13307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we establish a baseline for a new task named multimodal multi-round referring and grounding (MRG), opening up a promising direction for instance-level multimodal dialogues. We present a new benchmark and an efficient vision-language model for this purpose. The new benchmark, named CB-300K, spans challenges including multi-round dialogue, complex spatial relationships among multiple instances, and consistent reasoning, which are beyond those shown in existing benchmarks. The proposed model, named ChatterBox, utilizes a two-branch architecture to collaboratively handle vision and ","authors_text":"Jianbin Jiao, Jihao Qiu, Lingxi Xie, Qi Tian, Qixiang Ye, Tianren Ma, Xi Tang, Yuan Zhang, Yunjie Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T09:02:00Z","title":"ChatterBox: Multi-round Multimodal Referring and Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13307","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":"sha256:6d56c4d3b38f2cf2fe8b85db9ed8721923975ee0e1a6d1c2caf3dd6c047b284a","target":"record","created_at":"2026-07-05T07:37:03Z","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":"34b80a5b889bc2f64046e0ee6b86eb8d35cee9df72f8b94de46d06f95094f4af","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T09:02:00Z","title_canon_sha256":"2ef80e8dc6c495d20413ceef8769fd0b762dec7085885452deeb752a6a7ae486"},"schema_version":"1.0","source":{"id":"2401.13307","kind":"arxiv","version":1}},"canonical_sha256":"28770022b7782290633e1a4f5b11d7457242ff6440dd7033eb2759282917fb4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28770022b7782290633e1a4f5b11d7457242ff6440dd7033eb2759282917fb4f","first_computed_at":"2026-07-05T07:37:03.587913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:37:03.587913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OukBNIU6sCylnoG0lF7IcDvAA8GpODiNVHBn06F6/pFi9sLyGwKpPP5HFra9OadlLoPNKd+bnW+zUXHmP0D+DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:37:03.588361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.13307","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d56c4d3b38f2cf2fe8b85db9ed8721923975ee0e1a6d1c2caf3dd6c047b284a","sha256:a1d04c252ca24bca749cdfe1446e700482b6b085804f57150b2b7e57bcf7605e"],"state_sha256":"b952a3f085a7b85cfe27f0aa6632b84d8a8161e8cd0d4a05b7bd566d54a050d8"}