{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M4OIGFMIIZJHS2DYP5CLEBM3AV","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"76b262fdc4cb9b4b760f9abd6cb8e6cfd28e1597142b24a232b449cd287c5fdd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T02:25:03Z","title_canon_sha256":"a37de5457de4d0ac9a14bd1dfd21ba82e5297fc063f12fcc2272eb807d982ba3"},"schema_version":"1.0","source":{"id":"2607.14499","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14499","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14499v1","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14499","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"pith_short_12","alias_value":"M4OIGFMIIZJH","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"pith_short_16","alias_value":"M4OIGFMIIZJHS2DY","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"pith_short_8","alias_value":"M4OIGFMI","created_at":"2026-07-17T00:21:15Z"}],"graph_snapshots":[{"event_id":"sha256:fc248cf20d0dd3642efc1eee7ad007f73d8519c884c4446eac3a8ae088c8b912","target":"graph","created_at":"2026-07-17T00:21:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.14499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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-","authors_text":"Bingyang Wang, Huiqi Zou, Yijiang Li, Ziang Xiao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T02:25:03Z","title":"Contextualized Evaluation of Vision Language Models through Dynamic, Multi-turn Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14499","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dd8df924b8cd7495dbb254aca5f561a59786a9e9691f1208a223f4f13880bd43","target":"record","created_at":"2026-07-17T00:21:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"76b262fdc4cb9b4b760f9abd6cb8e6cfd28e1597142b24a232b449cd287c5fdd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T02:25:03Z","title_canon_sha256":"a37de5457de4d0ac9a14bd1dfd21ba82e5297fc063f12fcc2272eb807d982ba3"},"schema_version":"1.0","source":{"id":"2607.14499","kind":"arxiv","version":1}},"canonical_sha256":"671c83158846527968787f44b2059b05561d46ce415ff9e1083fbbd488a13862","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"671c83158846527968787f44b2059b05561d46ce415ff9e1083fbbd488a13862","first_computed_at":"2026-07-17T00:21:15.624909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T00:21:15.624909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EYm3ILGXdmgu6oQUaXa2YCvou4+qBv+jXn3EyYIvcs9kuQSCjanHCBpsBlUWmoNOqB7nPqxd837AG6BuwoXDAQ==","signature_status":"signed_v1","signed_at":"2026-07-17T00:21:15.625724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14499","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd8df924b8cd7495dbb254aca5f561a59786a9e9691f1208a223f4f13880bd43","sha256:fc248cf20d0dd3642efc1eee7ad007f73d8519c884c4446eac3a8ae088c8b912","sha256:58f7a7104161d2e275369823b65e20d2c70974704c3dbb4503ea1d287235a05b"],"state_sha256":"c32961019c57473f425e3d8e24fec8faa87095890327dddac572926ac19427d1"}