{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PRQAAYPX54YAFVOXPHRFDVLH7Z","short_pith_number":"pith:PRQAAYPX","schema_version":"1.0","canonical_sha256":"7c600061f7ef3002d5d779e251d567fe4aa765149b810be2ab6f9b4dd8fb2552","source":{"kind":"arxiv","id":"2403.20194","version":2},"attestation_state":"computed","paper":{"title":"ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Capability for Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Chuanhao Li, Hao Zhang, Kaining Ying, Kaipeng Zhang, Ping Luo, Shuo Liu, Tianle Zhang, Wenqi Shao, Yue Yang, Yu Qiao, Yuqi Lin","submitted_at":"2024-03-29T14:15:12Z","abstract_excerpt":"This paper presents ConvBench, a novel multi-turn conversation evaluation benchmark tailored for Large Vision-Language Models (LVLMs). Unlike existing benchmarks that assess individual capabilities in single-turn dialogues, ConvBench adopts a three-level multimodal capability hierarchy, mimicking human cognitive processes by stacking up perception, reasoning, and creativity. Each level focuses on a distinct capability, mirroring the cognitive progression from basic perception to logical reasoning and ultimately to advanced creativity. ConvBench comprises 577 meticulously curated multi-turn con"},"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":"2403.20194","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-03-29T14:15:12Z","cross_cats_sorted":[],"title_canon_sha256":"eb2804330501ca809ed29886ac377091d61eabcc749a5509f2f8da4f9f99dddc","abstract_canon_sha256":"a01a8777a40117b1b8a255e8492ae4e84fe3a2d442b732ed3772e0b3f60ff5d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:58.746240Z","signature_b64":"+QMnac16FDmoFyvo6mfcAg22HjConyXnVpJnosShJR5fflQPhFAf0zNTt/qREguMAsD0VmMQ/FRg4xeIRonzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c600061f7ef3002d5d779e251d567fe4aa765149b810be2ab6f9b4dd8fb2552","last_reissued_at":"2026-07-05T08:11:58.745728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:58.745728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Capability for Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Chuanhao Li, Hao Zhang, Kaining Ying, Kaipeng Zhang, Ping Luo, Shuo Liu, Tianle Zhang, Wenqi Shao, Yue Yang, Yu Qiao, Yuqi Lin","submitted_at":"2024-03-29T14:15:12Z","abstract_excerpt":"This paper presents ConvBench, a novel multi-turn conversation evaluation benchmark tailored for Large Vision-Language Models (LVLMs). Unlike existing benchmarks that assess individual capabilities in single-turn dialogues, ConvBench adopts a three-level multimodal capability hierarchy, mimicking human cognitive processes by stacking up perception, reasoning, and creativity. Each level focuses on a distinct capability, mirroring the cognitive progression from basic perception to logical reasoning and ultimately to advanced creativity. ConvBench comprises 577 meticulously curated multi-turn con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20194","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/2403.20194/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":"2403.20194","created_at":"2026-07-05T08:11:58.745792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.20194v2","created_at":"2026-07-05T08:11:58.745792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20194","created_at":"2026-07-05T08:11:58.745792+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRQAAYPX54YA","created_at":"2026-07-05T08:11:58.745792+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRQAAYPX54YAFVOX","created_at":"2026-07-05T08:11:58.745792+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRQAAYPX","created_at":"2026-07-05T08:11:58.745792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26396","citing_title":"Advancing Creative Physical Intelligence in Large Multimodal Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2504.09925","citing_title":"FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2407.03320","citing_title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12922","citing_title":"When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16821","citing_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRQAAYPX54YAFVOXPHRFDVLH7Z","json":"https://pith.science/pith/PRQAAYPX54YAFVOXPHRFDVLH7Z.json","graph_json":"https://pith.science/api/pith-number/PRQAAYPX54YAFVOXPHRFDVLH7Z/graph.json","events_json":"https://pith.science/api/pith-number/PRQAAYPX54YAFVOXPHRFDVLH7Z/events.json","paper":"https://pith.science/paper/PRQAAYPX"},"agent_actions":{"view_html":"https://pith.science/pith/PRQAAYPX54YAFVOXPHRFDVLH7Z","download_json":"https://pith.science/pith/PRQAAYPX54YAFVOXPHRFDVLH7Z.json","view_paper":"https://pith.science/paper/PRQAAYPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.20194&json=true","fetch_graph":"https://pith.science/api/pith-number/PRQAAYPX54YAFVOXPHRFDVLH7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/PRQAAYPX54YAFVOXPHRFDVLH7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRQAAYPX54YAFVOXPHRFDVLH7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRQAAYPX54YAFVOXPHRFDVLH7Z/action/storage_attestation","attest_author":"https://pith.science/pith/PRQAAYPX54YAFVOXPHRFDVLH7Z/action/author_attestation","sign_citation":"https://pith.science/pith/PRQAAYPX54YAFVOXPHRFDVLH7Z/action/citation_signature","submit_replication":"https://pith.science/pith/PRQAAYPX54YAFVOXPHRFDVLH7Z/action/replication_record"}},"created_at":"2026-07-05T08:11:58.745792+00:00","updated_at":"2026-07-05T08:11:58.745792+00:00"}