{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SNFTFBSLSHM4H4ZFQIHJCRCREW","short_pith_number":"pith:SNFTFBSL","schema_version":"1.0","canonical_sha256":"934b32864b91d9c3f325820e914451259bf4f031783517325ba0f1f1e6ef3566","source":{"kind":"arxiv","id":"2607.27637","version":1},"attestation_state":"computed","paper":{"title":"MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Wenjie Zhu, Wenjun Zeng, Yabin Zhang","submitted_at":"2026-07-30T03:46:43Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved strong performance on a wide range of vision-language tasks, but often fail under imperfect or shifted contexts. A reliable MLLM should refuse truly out-of-context (OOC) questions with subject-level context shifts while still answering shifted in-context (Shifted IC) questions with non-subject context shifts. Existing benchmarks mainly target OOC or visually unanswerable questions, but overlook answerable Shifted IC cases and cover limited OOC shifts. To fill this gap, we present MMOOC, a large-scale benchmark for evaluating refusal and ro"},"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":"2607.27637","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T03:46:43Z","cross_cats_sorted":[],"title_canon_sha256":"b83f6eb73b5a433c66be7c6dd6b633c598432b414d36414040f95ba14a0228be","abstract_canon_sha256":"61ba5dfb1a459868fce3bf17c6ff38f207fe6f305c3d247106afced24b4d25e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"934b32864b91d9c3f325820e914451259bf4f031783517325ba0f1f1e6ef3566","last_reissued_at":"2026-07-31T01:28:51.983095Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:28:51.983095Z"},"graph_snapshot":{"paper":{"title":"MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Wenjie Zhu, Wenjun Zeng, Yabin Zhang","submitted_at":"2026-07-30T03:46:43Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved strong performance on a wide range of vision-language tasks, but often fail under imperfect or shifted contexts. A reliable MLLM should refuse truly out-of-context (OOC) questions with subject-level context shifts while still answering shifted in-context (Shifted IC) questions with non-subject context shifts. Existing benchmarks mainly target OOC or visually unanswerable questions, but overlook answerable Shifted IC cases and cover limited OOC shifts. To fill this gap, we present MMOOC, a large-scale benchmark for evaluating refusal and ro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27637","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/2607.27637/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":"2607.27637","created_at":"2026-07-31T01:28:51.986110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27637v1","created_at":"2026-07-31T01:28:51.986110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27637","created_at":"2026-07-31T01:28:51.986110+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNFTFBSLSHM4","created_at":"2026-07-31T01:28:51.986110+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNFTFBSLSHM4H4ZF","created_at":"2026-07-31T01:28:51.986110+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNFTFBSL","created_at":"2026-07-31T01:28:51.986110+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/SNFTFBSLSHM4H4ZFQIHJCRCREW","json":"https://pith.science/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW.json","graph_json":"https://pith.science/api/pith-number/SNFTFBSLSHM4H4ZFQIHJCRCREW/graph.json","events_json":"https://pith.science/api/pith-number/SNFTFBSLSHM4H4ZFQIHJCRCREW/events.json","paper":"https://pith.science/paper/SNFTFBSL"},"agent_actions":{"view_html":"https://pith.science/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW","download_json":"https://pith.science/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW.json","view_paper":"https://pith.science/paper/SNFTFBSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27637&json=true","fetch_graph":"https://pith.science/api/pith-number/SNFTFBSLSHM4H4ZFQIHJCRCREW/graph.json","fetch_events":"https://pith.science/api/pith-number/SNFTFBSLSHM4H4ZFQIHJCRCREW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW/action/storage_attestation","attest_author":"https://pith.science/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW/action/author_attestation","sign_citation":"https://pith.science/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW/action/citation_signature","submit_replication":"https://pith.science/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW/action/replication_record"}},"created_at":"2026-07-31T01:28:51.986110+00:00","updated_at":"2026-07-31T01:28:51.986110+00:00"}