{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2WL5V7VUWGDQAANNUJBCIF2ML5","short_pith_number":"pith:2WL5V7VU","schema_version":"1.0","canonical_sha256":"d597dafeb4b1870001ada24224174c5f739ab1f1726ab032898c34b4289ccd5f","source":{"kind":"arxiv","id":"2602.06442","version":2},"attestation_state":"computed","paper":{"title":"ChatUMM: Robust Context Tracking for Conversational Interleaved Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyu Wang, Fellix Song, Haoji Zhang, Jianwei Zhang, Linqing Wang, Runze He, Shiyi Zhang, Wayne Zhuang, Wenxun Dai, Yansong Tang, Yiji Cheng, Yong Liu, Yule Zhong, Yunlong Lin, Zhiyuan Zhao","submitted_at":"2026-02-06T07:11:50Z","abstract_excerpt":"Unified multimodal models (UMMs) have achieved remarkable progress yet remain constrained by a single-turn interaction paradigm, effectively functioning as solvers for independent requests rather than assistants in continuous dialogue. To bridge this gap, we present ChatUMM. As a conversational unified model, it excels at robust context tracking to sustain interleaved multimodal generation. ChatUMM derives its capabilities from two key innovations: an interleaved multi-turn training strategy that models serialized text-image streams as a continuous conversational flow, and a systematic convers"},"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":"2602.06442","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-06T07:11:50Z","cross_cats_sorted":[],"title_canon_sha256":"1d08c4c5189218b711f133898472c2b2550bb43f9bd0e7aee93187ae2902b09c","abstract_canon_sha256":"d935442037ce5ebd6aa5f6869774e778480596bca14b89066a8b47c63422242e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:38.228819Z","signature_b64":"iX4R3HIAog7of4cQFI3WJEwC4ikmlEz+prwrfgEbqIIk3G0ioACMZasztjRXmzMMR0a4WGAIO79OzclTsjuhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d597dafeb4b1870001ada24224174c5f739ab1f1726ab032898c34b4289ccd5f","last_reissued_at":"2026-06-02T03:04:38.228304Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:38.228304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatUMM: Robust Context Tracking for Conversational Interleaved Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyu Wang, Fellix Song, Haoji Zhang, Jianwei Zhang, Linqing Wang, Runze He, Shiyi Zhang, Wayne Zhuang, Wenxun Dai, Yansong Tang, Yiji Cheng, Yong Liu, Yule Zhong, Yunlong Lin, Zhiyuan Zhao","submitted_at":"2026-02-06T07:11:50Z","abstract_excerpt":"Unified multimodal models (UMMs) have achieved remarkable progress yet remain constrained by a single-turn interaction paradigm, effectively functioning as solvers for independent requests rather than assistants in continuous dialogue. To bridge this gap, we present ChatUMM. As a conversational unified model, it excels at robust context tracking to sustain interleaved multimodal generation. ChatUMM derives its capabilities from two key innovations: an interleaved multi-turn training strategy that models serialized text-image streams as a continuous conversational flow, and a systematic convers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06442","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/2602.06442/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":"2602.06442","created_at":"2026-06-02T03:04:38.228378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.06442v2","created_at":"2026-06-02T03:04:38.228378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06442","created_at":"2026-06-02T03:04:38.228378+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WL5V7VUWGDQ","created_at":"2026-06-02T03:04:38.228378+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WL5V7VUWGDQAANN","created_at":"2026-06-02T03:04:38.228378+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WL5V7VU","created_at":"2026-06-02T03:04:38.228378+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24625","citing_title":"Meta-CoT: Enhancing Granularity and Generalization in Image Editing","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2WL5V7VUWGDQAANNUJBCIF2ML5","json":"https://pith.science/pith/2WL5V7VUWGDQAANNUJBCIF2ML5.json","graph_json":"https://pith.science/api/pith-number/2WL5V7VUWGDQAANNUJBCIF2ML5/graph.json","events_json":"https://pith.science/api/pith-number/2WL5V7VUWGDQAANNUJBCIF2ML5/events.json","paper":"https://pith.science/paper/2WL5V7VU"},"agent_actions":{"view_html":"https://pith.science/pith/2WL5V7VUWGDQAANNUJBCIF2ML5","download_json":"https://pith.science/pith/2WL5V7VUWGDQAANNUJBCIF2ML5.json","view_paper":"https://pith.science/paper/2WL5V7VU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.06442&json=true","fetch_graph":"https://pith.science/api/pith-number/2WL5V7VUWGDQAANNUJBCIF2ML5/graph.json","fetch_events":"https://pith.science/api/pith-number/2WL5V7VUWGDQAANNUJBCIF2ML5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WL5V7VUWGDQAANNUJBCIF2ML5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WL5V7VUWGDQAANNUJBCIF2ML5/action/storage_attestation","attest_author":"https://pith.science/pith/2WL5V7VUWGDQAANNUJBCIF2ML5/action/author_attestation","sign_citation":"https://pith.science/pith/2WL5V7VUWGDQAANNUJBCIF2ML5/action/citation_signature","submit_replication":"https://pith.science/pith/2WL5V7VUWGDQAANNUJBCIF2ML5/action/replication_record"}},"created_at":"2026-06-02T03:04:38.228378+00:00","updated_at":"2026-06-02T03:04:38.228378+00:00"}