{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LIOFACNKTFNJRJ4MW7Q4GP4IFP","short_pith_number":"pith:LIOFACNK","schema_version":"1.0","canonical_sha256":"5a1c5009aa995a98a78cb7e1c33f882be35685913755855f91a87271201429f8","source":{"kind":"arxiv","id":"2606.09169","version":1},"attestation_state":"computed","paper":{"title":"IMUG-Bench: Benchmarking Unified Multimodal Models on Interleaved Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.AI","authors_text":"Bo Dai, Chunwei Wang, Hangshuo Cao, Haoran Li, Kaixuan Wang, Lingyi Meng, Qi Kang, Tengju Ru, Weitong Lian, Yechi Liu, Yichen Zhu, Yu-Jie Yuan, Yu Zhang, Zecong Tang, Zhejun Cui","submitted_at":"2026-06-08T08:08:20Z","abstract_excerpt":"In recent years, unified multimodal models (UMMs) have emerged to support both understanding and generation within a single framework. Mastering dynamic, multi-turn interleaved image-text dialogues is a crucial task for UMMs in real-world applications. However, existing benchmarks fail to evaluate this important task, as they are often limited to single-turn or static settings, and typically overlook exposure bias in multi-turn interactions. To bridge this gap, we propose IMUG-Bench, a comprehensive benchmark for multi-turn interleaved image-text dialogue of UMMs that jointly evaluates their u"},"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":"2606.09169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T08:08:20Z","cross_cats_sorted":["cs.CV","cs.MM"],"title_canon_sha256":"be90d15e7f05a5a0da87bcaf4b1dbd915eb47aac12d16fe02acd97895e3e46c8","abstract_canon_sha256":"de4e7b8ea3f135955ac71245b6bfe3f3e1cc623ce0f9b433a2eb5d3fab5cb64b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:04.396610Z","signature_b64":"dkX0kIy95OLdqYQWEqH81CKETiyqbXZ1W28I3+Q3BK9d8NQICg663PnNAOjHZ0rnc7e1KoSCCiyHKPPVb4CbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a1c5009aa995a98a78cb7e1c33f882be35685913755855f91a87271201429f8","last_reissued_at":"2026-06-09T02:08:04.395634Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:04.395634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IMUG-Bench: Benchmarking Unified Multimodal Models on Interleaved Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.AI","authors_text":"Bo Dai, Chunwei Wang, Hangshuo Cao, Haoran Li, Kaixuan Wang, Lingyi Meng, Qi Kang, Tengju Ru, Weitong Lian, Yechi Liu, Yichen Zhu, Yu-Jie Yuan, Yu Zhang, Zecong Tang, Zhejun Cui","submitted_at":"2026-06-08T08:08:20Z","abstract_excerpt":"In recent years, unified multimodal models (UMMs) have emerged to support both understanding and generation within a single framework. Mastering dynamic, multi-turn interleaved image-text dialogues is a crucial task for UMMs in real-world applications. However, existing benchmarks fail to evaluate this important task, as they are often limited to single-turn or static settings, and typically overlook exposure bias in multi-turn interactions. To bridge this gap, we propose IMUG-Bench, a comprehensive benchmark for multi-turn interleaved image-text dialogue of UMMs that jointly evaluates their u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09169","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/2606.09169/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":"2606.09169","created_at":"2026-06-09T02:08:04.395796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09169v1","created_at":"2026-06-09T02:08:04.395796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09169","created_at":"2026-06-09T02:08:04.395796+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIOFACNKTFNJ","created_at":"2026-06-09T02:08:04.395796+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIOFACNKTFNJRJ4M","created_at":"2026-06-09T02:08:04.395796+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIOFACNK","created_at":"2026-06-09T02:08:04.395796+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LIOFACNKTFNJRJ4MW7Q4GP4IFP","json":"https://pith.science/pith/LIOFACNKTFNJRJ4MW7Q4GP4IFP.json","graph_json":"https://pith.science/api/pith-number/LIOFACNKTFNJRJ4MW7Q4GP4IFP/graph.json","events_json":"https://pith.science/api/pith-number/LIOFACNKTFNJRJ4MW7Q4GP4IFP/events.json","paper":"https://pith.science/paper/LIOFACNK"},"agent_actions":{"view_html":"https://pith.science/pith/LIOFACNKTFNJRJ4MW7Q4GP4IFP","download_json":"https://pith.science/pith/LIOFACNKTFNJRJ4MW7Q4GP4IFP.json","view_paper":"https://pith.science/paper/LIOFACNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09169&json=true","fetch_graph":"https://pith.science/api/pith-number/LIOFACNKTFNJRJ4MW7Q4GP4IFP/graph.json","fetch_events":"https://pith.science/api/pith-number/LIOFACNKTFNJRJ4MW7Q4GP4IFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIOFACNKTFNJRJ4MW7Q4GP4IFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIOFACNKTFNJRJ4MW7Q4GP4IFP/action/storage_attestation","attest_author":"https://pith.science/pith/LIOFACNKTFNJRJ4MW7Q4GP4IFP/action/author_attestation","sign_citation":"https://pith.science/pith/LIOFACNKTFNJRJ4MW7Q4GP4IFP/action/citation_signature","submit_replication":"https://pith.science/pith/LIOFACNKTFNJRJ4MW7Q4GP4IFP/action/replication_record"}},"created_at":"2026-06-09T02:08:04.395796+00:00","updated_at":"2026-06-09T02:08:04.395796+00:00"}