{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SNFTFBSLSHM4H4ZFQIHJCRCREW","short_pith_number":"pith:SNFTFBSL","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"},"canonical_sha256":"934b32864b91d9c3f325820e914451259bf4f031783517325ba0f1f1e6ef3566","source":{"kind":"arxiv","id":"2607.27637","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27637","created_at":"2026-07-31T01:28:51Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27637v1","created_at":"2026-07-31T01:28:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27637","created_at":"2026-07-31T01:28:51Z"},{"alias_kind":"pith_short_12","alias_value":"SNFTFBSLSHM4","created_at":"2026-07-31T01:28:51Z"},{"alias_kind":"pith_short_16","alias_value":"SNFTFBSLSHM4H4ZF","created_at":"2026-07-31T01:28:51Z"},{"alias_kind":"pith_short_8","alias_value":"SNFTFBSL","created_at":"2026-07-31T01:28:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SNFTFBSLSHM4H4ZFQIHJCRCREW","target":"record","payload":{"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"},"canonical_sha256":"934b32864b91d9c3f325820e914451259bf4f031783517325ba0f1f1e6ef3566","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"},"source_kind":"arxiv","source_id":"2607.27637","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":"2026-07-31T01:28:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CoxDBL8sM3jkxui5GdA3fDzN2aGspUR1sd6WiQAM+X3bH2yVrsrjW1wKYE4qSgh+ztfpgqL5pe2vGGOMYyyuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:45:09.302619Z"},"content_sha256":"b5b3229101c1eec7b61ba6aa3cbaa06f6852951f27dcb71749897c081a8507cc","schema_version":"1.0","event_id":"sha256:b5b3229101c1eec7b61ba6aa3cbaa06f6852951f27dcb71749897c081a8507cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SNFTFBSLSHM4H4ZFQIHJCRCREW","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:28:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A0Yz5+OqcZyqVI6H9Sn0eaArWVR77fcvatubIUhSJWWW1bc/Vq2sJMi7EKwXdn6DgK/L/Cd38T0EZMmCMmfYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:45:09.303316Z"},"content_sha256":"7fcb78fd0d7f2d32222358963634b25f5bd7d6b2480a4e32b681651aebd5bfab","schema_version":"1.0","event_id":"sha256:7fcb78fd0d7f2d32222358963634b25f5bd7d6b2480a4e32b681651aebd5bfab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW/bundle.json","state_url":"https://pith.science/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW/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":"2026-08-05T06:45:09Z","links":{"resolver":"https://pith.science/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW","bundle":"https://pith.science/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW/bundle.json","state":"https://pith.science/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SNFTFBSLSHM4H4ZFQIHJCRCREW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SNFTFBSLSHM4H4ZFQIHJCRCREW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"61ba5dfb1a459868fce3bf17c6ff38f207fe6f305c3d247106afced24b4d25e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T03:46:43Z","title_canon_sha256":"b83f6eb73b5a433c66be7c6dd6b633c598432b414d36414040f95ba14a0228be"},"schema_version":"1.0","source":{"id":"2607.27637","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27637","created_at":"2026-07-31T01:28:51Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27637v1","created_at":"2026-07-31T01:28:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27637","created_at":"2026-07-31T01:28:51Z"},{"alias_kind":"pith_short_12","alias_value":"SNFTFBSLSHM4","created_at":"2026-07-31T01:28:51Z"},{"alias_kind":"pith_short_16","alias_value":"SNFTFBSLSHM4H4ZF","created_at":"2026-07-31T01:28:51Z"},{"alias_kind":"pith_short_8","alias_value":"SNFTFBSL","created_at":"2026-07-31T01:28:51Z"}],"graph_snapshots":[{"event_id":"sha256:7fcb78fd0d7f2d32222358963634b25f5bd7d6b2480a4e32b681651aebd5bfab","target":"graph","created_at":"2026-07-31T01:28:51Z","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/2607.27637/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lei Zhang, Wenjie Zhu, Wenjun Zeng, Yabin Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T03:46:43Z","title":"MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27637","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:b5b3229101c1eec7b61ba6aa3cbaa06f6852951f27dcb71749897c081a8507cc","target":"record","created_at":"2026-07-31T01:28:51Z","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":"61ba5dfb1a459868fce3bf17c6ff38f207fe6f305c3d247106afced24b4d25e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T03:46:43Z","title_canon_sha256":"b83f6eb73b5a433c66be7c6dd6b633c598432b414d36414040f95ba14a0228be"},"schema_version":"1.0","source":{"id":"2607.27637","kind":"arxiv","version":1}},"canonical_sha256":"934b32864b91d9c3f325820e914451259bf4f031783517325ba0f1f1e6ef3566","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"934b32864b91d9c3f325820e914451259bf4f031783517325ba0f1f1e6ef3566","first_computed_at":"2026-07-31T01:28:51.983095Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:28:51.983095Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27637","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5b3229101c1eec7b61ba6aa3cbaa06f6852951f27dcb71749897c081a8507cc","sha256:7fcb78fd0d7f2d32222358963634b25f5bd7d6b2480a4e32b681651aebd5bfab"],"state_sha256":"cef65374c6917308d3a89f019a4ba0baec00f105819037650fbbe50538fe3433"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ybS077xE5w8cgros2O3i2wQkL/7BRajGTS21yCQI8DD9XluBLTfWPpIDw/JTkehRks0SpSfDXUvYt++5G/BiAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:45:09.307611Z","bundle_sha256":"27b82003ed17f466a96423606d92b8743e8842b39032a8b417cc82e784e32f99"}}