{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3QF3W7GSKUXF4BX4R73WCAISFE","short_pith_number":"pith:3QF3W7GS","schema_version":"1.0","canonical_sha256":"dc0bbb7cd2552e5e06fc8ff7610112292cb6f6629125478b5877e0ffe2b447a1","source":{"kind":"arxiv","id":"2411.18499","version":3},"attestation_state":"computed","paper":{"title":"OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanhao Li, Hao Zhang, Jiajun Song, Kaipeng Zhang, Lirui Zhao, Pengfei Zhou, Shuo Liu, Tianhua Li, Wenqi Shao, Xiaojun Chang, Xiaopeng Peng, Yefei He, Yue Yang, Yu Qiao, Yuqi Lin, Yuxuan Xie, Zhaopan Xu, Ziyao Guo","submitted_at":"2024-11-27T16:39:04Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding and generation tasks. However, generating interleaved image-text content remains a challenge, which requires integrated multimodal understanding and generation abilities. While the progress in unified models offers new solutions, existing benchmarks are insufficient for evaluating these methods due to limitations in data size and diversity. To bridge this gap, we introduce OpenING, a comprehensive benchmark comprising 5,400 high-quality human-annotated instances across 56 real-world tasks. OpenING co"},"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":"2411.18499","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T16:39:04Z","cross_cats_sorted":[],"title_canon_sha256":"97c91c92fde5802c17a3ea16a34a8e2797d89b6de0c5a1c4fd17521d72d27417","abstract_canon_sha256":"972ae45824f2083c7af42b5b0215811ea1f25f8cf359fe3215c1533f4b9d1193"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:17.848349Z","signature_b64":"Nvyt5MrWra7DQA5RzdxV1OAsmiPm9V93IZpTXHc2hXwt+kxuqcWiG4cqWx5QbUcgOIMwCv/RjwCldzQBnMbqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc0bbb7cd2552e5e06fc8ff7610112292cb6f6629125478b5877e0ffe2b447a1","last_reissued_at":"2026-07-05T10:41:17.847813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:17.847813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanhao Li, Hao Zhang, Jiajun Song, Kaipeng Zhang, Lirui Zhao, Pengfei Zhou, Shuo Liu, Tianhua Li, Wenqi Shao, Xiaojun Chang, Xiaopeng Peng, Yefei He, Yue Yang, Yu Qiao, Yuqi Lin, Yuxuan Xie, Zhaopan Xu, Ziyao Guo","submitted_at":"2024-11-27T16:39:04Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding and generation tasks. However, generating interleaved image-text content remains a challenge, which requires integrated multimodal understanding and generation abilities. While the progress in unified models offers new solutions, existing benchmarks are insufficient for evaluating these methods due to limitations in data size and diversity. To bridge this gap, we introduce OpenING, a comprehensive benchmark comprising 5,400 high-quality human-annotated instances across 56 real-world tasks. OpenING co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18499","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/2411.18499/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":"2411.18499","created_at":"2026-07-05T10:41:17.847884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18499v3","created_at":"2026-07-05T10:41:17.847884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18499","created_at":"2026-07-05T10:41:17.847884+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QF3W7GSKUXF","created_at":"2026-07-05T10:41:17.847884+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QF3W7GSKUXF4BX4","created_at":"2026-07-05T10:41:17.847884+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QF3W7GS","created_at":"2026-07-05T10:41:17.847884+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/3QF3W7GSKUXF4BX4R73WCAISFE","json":"https://pith.science/pith/3QF3W7GSKUXF4BX4R73WCAISFE.json","graph_json":"https://pith.science/api/pith-number/3QF3W7GSKUXF4BX4R73WCAISFE/graph.json","events_json":"https://pith.science/api/pith-number/3QF3W7GSKUXF4BX4R73WCAISFE/events.json","paper":"https://pith.science/paper/3QF3W7GS"},"agent_actions":{"view_html":"https://pith.science/pith/3QF3W7GSKUXF4BX4R73WCAISFE","download_json":"https://pith.science/pith/3QF3W7GSKUXF4BX4R73WCAISFE.json","view_paper":"https://pith.science/paper/3QF3W7GS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18499&json=true","fetch_graph":"https://pith.science/api/pith-number/3QF3W7GSKUXF4BX4R73WCAISFE/graph.json","fetch_events":"https://pith.science/api/pith-number/3QF3W7GSKUXF4BX4R73WCAISFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QF3W7GSKUXF4BX4R73WCAISFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QF3W7GSKUXF4BX4R73WCAISFE/action/storage_attestation","attest_author":"https://pith.science/pith/3QF3W7GSKUXF4BX4R73WCAISFE/action/author_attestation","sign_citation":"https://pith.science/pith/3QF3W7GSKUXF4BX4R73WCAISFE/action/citation_signature","submit_replication":"https://pith.science/pith/3QF3W7GSKUXF4BX4R73WCAISFE/action/replication_record"}},"created_at":"2026-07-05T10:41:17.847884+00:00","updated_at":"2026-07-05T10:41:17.847884+00:00"}