{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FB3QAIVXPARJAYZ6DJHVWEOXIV","short_pith_number":"pith:FB3QAIVX","schema_version":"1.0","canonical_sha256":"28770022b7782290633e1a4f5b11d7457242ff6440dd7033eb2759282917fb4f","source":{"kind":"arxiv","id":"2401.13307","version":1},"attestation_state":"computed","paper":{"title":"ChatterBox: Multi-round Multimodal Referring and Grounding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbin Jiao, Jihao Qiu, Lingxi Xie, Qi Tian, Qixiang Ye, Tianren Ma, Xi Tang, Yuan Zhang, Yunjie Tian","submitted_at":"2024-01-24T09:02:00Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.13307","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T09:02:00Z","cross_cats_sorted":[],"title_canon_sha256":"2ef80e8dc6c495d20413ceef8769fd0b762dec7085885452deeb752a6a7ae486","abstract_canon_sha256":"34b80a5b889bc2f64046e0ee6b86eb8d35cee9df72f8b94de46d06f95094f4af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:03.588361Z","signature_b64":"OukBNIU6sCylnoG0lF7IcDvAA8GpODiNVHBn06F6/pFi9sLyGwKpPP5HFra9OadlLoPNKd+bnW+zUXHmP0D+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28770022b7782290633e1a4f5b11d7457242ff6440dd7033eb2759282917fb4f","last_reissued_at":"2026-07-05T07:37:03.587913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:03.587913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatterBox: Multi-round Multimodal Referring and Grounding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbin Jiao, Jihao Qiu, Lingxi Xie, Qi Tian, Qixiang Ye, Tianren Ma, Xi Tang, Yuan Zhang, Yunjie Tian","submitted_at":"2024-01-24T09:02:00Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13307","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/2401.13307/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.13307","created_at":"2026-07-05T07:37:03.587963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13307v1","created_at":"2026-07-05T07:37:03.587963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13307","created_at":"2026-07-05T07:37:03.587963+00:00"},{"alias_kind":"pith_short_12","alias_value":"FB3QAIVXPARJ","created_at":"2026-07-05T07:37:03.587963+00:00"},{"alias_kind":"pith_short_16","alias_value":"FB3QAIVXPARJAYZ6","created_at":"2026-07-05T07:37:03.587963+00:00"},{"alias_kind":"pith_short_8","alias_value":"FB3QAIVX","created_at":"2026-07-05T07:37:03.587963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18018","citing_title":"See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10554","citing_title":"Grounding Everything in Tokens for Multimodal Large Language Models","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20913","citing_title":"LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FB3QAIVXPARJAYZ6DJHVWEOXIV","json":"https://pith.science/pith/FB3QAIVXPARJAYZ6DJHVWEOXIV.json","graph_json":"https://pith.science/api/pith-number/FB3QAIVXPARJAYZ6DJHVWEOXIV/graph.json","events_json":"https://pith.science/api/pith-number/FB3QAIVXPARJAYZ6DJHVWEOXIV/events.json","paper":"https://pith.science/paper/FB3QAIVX"},"agent_actions":{"view_html":"https://pith.science/pith/FB3QAIVXPARJAYZ6DJHVWEOXIV","download_json":"https://pith.science/pith/FB3QAIVXPARJAYZ6DJHVWEOXIV.json","view_paper":"https://pith.science/paper/FB3QAIVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13307&json=true","fetch_graph":"https://pith.science/api/pith-number/FB3QAIVXPARJAYZ6DJHVWEOXIV/graph.json","fetch_events":"https://pith.science/api/pith-number/FB3QAIVXPARJAYZ6DJHVWEOXIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FB3QAIVXPARJAYZ6DJHVWEOXIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FB3QAIVXPARJAYZ6DJHVWEOXIV/action/storage_attestation","attest_author":"https://pith.science/pith/FB3QAIVXPARJAYZ6DJHVWEOXIV/action/author_attestation","sign_citation":"https://pith.science/pith/FB3QAIVXPARJAYZ6DJHVWEOXIV/action/citation_signature","submit_replication":"https://pith.science/pith/FB3QAIVXPARJAYZ6DJHVWEOXIV/action/replication_record"}},"created_at":"2026-07-05T07:37:03.587963+00:00","updated_at":"2026-07-05T07:37:03.587963+00:00"}