{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:M4OIGFMIIZJHS2DYP5CLEBM3AV","short_pith_number":"pith:M4OIGFMI","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"},"canonical_sha256":"671c83158846527968787f44b2059b05561d46ce415ff9e1083fbbd488a13862","source":{"kind":"arxiv","id":"2607.14499","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:M4OIGFMIIZJHS2DYP5CLEBM3AV","target":"record","payload":{"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"},"canonical_sha256":"671c83158846527968787f44b2059b05561d46ce415ff9e1083fbbd488a13862","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"},"source_kind":"arxiv","source_id":"2607.14499","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-17T00:21:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yNtpR8ZgGqi9ORt6CJSFptScelkOrR7fpSVFG0CblHw3c9od+VD1bqIPvl/8ajauU1hhvCAogl7JUnK++1XRDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T13:14:53.187615Z"},"content_sha256":"dd8df924b8cd7495dbb254aca5f561a59786a9e9691f1208a223f4f13880bd43","schema_version":"1.0","event_id":"sha256:dd8df924b8cd7495dbb254aca5f561a59786a9e9691f1208a223f4f13880bd43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:M4OIGFMIIZJHS2DYP5CLEBM3AV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-17T00:21:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d5k6lIpcdOL+ATfjiHc3tb4I0EPQ79QgbuzdLOMrAH8QkJzVSRmbjCFXD9OAgyOWXYnrb1CUVSiTZYfH+6uHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T13:14:53.188676Z"},"content_sha256":"fc248cf20d0dd3642efc1eee7ad007f73d8519c884c4446eac3a8ae088c8b912","schema_version":"1.0","event_id":"sha256:fc248cf20d0dd3642efc1eee7ad007f73d8519c884c4446eac3a8ae088c8b912"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:M4OIGFMIIZJHS2DYP5CLEBM3AV","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/ICCV.2015.279) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"IEEE Computer Society. ISBN 9781467383912. doi: 10.1109/ICCV .2015.279. URL https://doi.org/10.1109/ICCV.2015.279","arxiv_id":"2607.14499","detector":"doi_compliance","evidence":{"ref_index":2015,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1109/iccv","reconstructed_doi":"10.1109/ICCV.2015.279"},"severity":"advisory","ref_index":2015,"audited_at":"2026-08-02T01:59:36.184122Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/ICCV.2015.279","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"9da5fc2111778d087ec34f8e289f6cbfe389b0942c1e41973b01c50c7b56fe8e","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":17029,"payload_sha256":"78890a5a41628b6db570a5959a0181141da2c7fa1a2c48ad3d8c32e89d120ea8","signature_b64":"sn/xL7pUY/O5mHloJb9stM4i0qsM04z1AGlVCzhJdTZZslCihQBkUZ9bCalwg5Jaxqb/zwpFRQ+ejovfhHxVDg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-02T02:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mo7COdWdwCFZgrv2/tAuilf1O0qILEZ5W7C6oCcn8S8o3hMGGmFdmVEgkVc9xxqqyp2yze0VK0lQadTdik1QDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T13:14:53.193049Z"},"content_sha256":"58f7a7104161d2e275369823b65e20d2c70974704c3dbb4503ea1d287235a05b","schema_version":"1.0","event_id":"sha256:58f7a7104161d2e275369823b65e20d2c70974704c3dbb4503ea1d287235a05b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV/bundle.json","state_url":"https://pith.science/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-02T13:14:53Z","links":{"resolver":"https://pith.science/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV","bundle":"https://pith.science/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV/bundle.json","state":"https://pith.science/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M4OIGFMIIZJHS2DYP5CLEBM3AV/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C2JSx75TPO3JFak09Ygm4+EMsl2O0LMbJK0k7jyH0978qnP6vnzn1YNVHYaM3t/NAY85LUg5rhQLvhSK/EaqAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T13:14:53.196084Z","bundle_sha256":"a9caf3c5e01aef6de7c5de98eb521702fa00ecf4f63a259a35d08bf6d2084d7b"}}