{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M4OIGFMIIZJHS2DYP5CLEBM3AV","short_pith_number":"pith:M4OIGFMI","schema_version":"1.0","canonical_sha256":"671c83158846527968787f44b2059b05561d46ce415ff9e1083fbbd488a13862","source":{"kind":"arxiv","id":"2607.14499","version":1},"attestation_state":"computed","paper":{"title":"Contextualized Evaluation of Vision Language Models through Dynamic, Multi-turn Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bingyang Wang, Huiqi Zou, Yijiang Li, Ziang Xiao","submitted_at":"2026-07-16T02:25:03Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have made substantial advances on benchmarks, yet their real-world effectiveness remains uncertain. This gap stems from the fundamental misalignment between benchmarks in controlled, static settings and the dynamic, interactive, and contextualized nature of real-world applications. To bridge this gap, we propose CEDI (Contextualized Evaluations of MLLMs through Dynamic, multi-round Interactions), a framework that recasts evaluation as a three-party interaction between an evaluatee model, an automated examiner, and a grader. The examiner conducts multi-"},"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":"2607.14499","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T02:25:03Z","cross_cats_sorted":[],"title_canon_sha256":"a37de5457de4d0ac9a14bd1dfd21ba82e5297fc063f12fcc2272eb807d982ba3","abstract_canon_sha256":"76b262fdc4cb9b4b760f9abd6cb8e6cfd28e1597142b24a232b449cd287c5fdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:21:15.625724Z","signature_b64":"EYm3ILGXdmgu6oQUaXa2YCvou4+qBv+jXn3EyYIvcs9kuQSCjanHCBpsBlUWmoNOqB7nPqxd837AG6BuwoXDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"671c83158846527968787f44b2059b05561d46ce415ff9e1083fbbd488a13862","last_reissued_at":"2026-07-17T00:21:15.624909Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:21:15.624909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextualized Evaluation of Vision Language Models through Dynamic, Multi-turn Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bingyang Wang, Huiqi Zou, Yijiang Li, Ziang Xiao","submitted_at":"2026-07-16T02:25:03Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have made substantial advances on benchmarks, yet their real-world effectiveness remains uncertain. This gap stems from the fundamental misalignment between benchmarks in controlled, static settings and the dynamic, interactive, and contextualized nature of real-world applications. To bridge this gap, we propose CEDI (Contextualized Evaluations of MLLMs through Dynamic, multi-round Interactions), a framework that recasts evaluation as a three-party interaction between an evaluatee model, an automated examiner, and a grader. The examiner conducts multi-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14499","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/2607.14499/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":"2607.14499","created_at":"2026-07-17T00:21:15.625328+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14499v1","created_at":"2026-07-17T00:21:15.625328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14499","created_at":"2026-07-17T00:21:15.625328+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4OIGFMIIZJH","created_at":"2026-07-17T00:21:15.625328+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4OIGFMIIZJHS2DY","created_at":"2026-07-17T00:21:15.625328+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4OIGFMI","created_at":"2026-07-17T00:21:15.625328+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/M4OIGFMIIZJHS2DYP5CLEBM3AV","json":"https://pith.science/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV.json","graph_json":"https://pith.science/api/pith-number/M4OIGFMIIZJHS2DYP5CLEBM3AV/graph.json","events_json":"https://pith.science/api/pith-number/M4OIGFMIIZJHS2DYP5CLEBM3AV/events.json","paper":"https://pith.science/paper/M4OIGFMI"},"agent_actions":{"view_html":"https://pith.science/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV","download_json":"https://pith.science/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV.json","view_paper":"https://pith.science/paper/M4OIGFMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14499&json=true","fetch_graph":"https://pith.science/api/pith-number/M4OIGFMIIZJHS2DYP5CLEBM3AV/graph.json","fetch_events":"https://pith.science/api/pith-number/M4OIGFMIIZJHS2DYP5CLEBM3AV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV/action/storage_attestation","attest_author":"https://pith.science/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV/action/author_attestation","sign_citation":"https://pith.science/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV/action/citation_signature","submit_replication":"https://pith.science/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV/action/replication_record"}},"created_at":"2026-07-17T00:21:15.625328+00:00","updated_at":"2026-07-17T00:21:15.625328+00:00"}