{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4U3XOM7355ESGD72S4IYHUZH2E","short_pith_number":"pith:4U3XOM73","canonical_record":{"source":{"id":"2410.08145","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T17:31:17Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"af7f4d49c27f6c689e65aeb1cf02b8b7948c3dcdd3efc6f44d3368d68e71720b","abstract_canon_sha256":"93d02ce567fab2f36ddf244961119761d804401b9afc9e9971e54459aa875406"},"schema_version":"1.0"},"canonical_sha256":"e5377733fbef49230ffa971183d327d130020b7e13c92c226ccdec19972291ad","source":{"kind":"arxiv","id":"2410.08145","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08145","created_at":"2026-07-05T11:13:13Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08145v2","created_at":"2026-07-05T11:13:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08145","created_at":"2026-07-05T11:13:13Z"},{"alias_kind":"pith_short_12","alias_value":"4U3XOM7355ES","created_at":"2026-07-05T11:13:13Z"},{"alias_kind":"pith_short_16","alias_value":"4U3XOM7355ESGD72","created_at":"2026-07-05T11:13:13Z"},{"alias_kind":"pith_short_8","alias_value":"4U3XOM73","created_at":"2026-07-05T11:13:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4U3XOM7355ESGD72S4IYHUZH2E","target":"record","payload":{"canonical_record":{"source":{"id":"2410.08145","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T17:31:17Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"af7f4d49c27f6c689e65aeb1cf02b8b7948c3dcdd3efc6f44d3368d68e71720b","abstract_canon_sha256":"93d02ce567fab2f36ddf244961119761d804401b9afc9e9971e54459aa875406"},"schema_version":"1.0"},"canonical_sha256":"e5377733fbef49230ffa971183d327d130020b7e13c92c226ccdec19972291ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:13.949532Z","signature_b64":"tW3eGVFYz0RW6JftTSOmAf2UBPpMOWPjzWUIjjMvAXibLLousN4HqySxFklxEgNq9Cci0A7tFEViyuVY2XveBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5377733fbef49230ffa971183d327d130020b7e13c92c226ccdec19972291ad","last_reissued_at":"2026-07-05T11:13:13.948967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:13.948967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.08145","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OoNDBRcNvwB7H/MQHmmfa0rpH+pxu83Q1jfoA2Kj9q96ogHUfZmaYwnLNx2SpCcBdWptaei1zzo7o+Ja4JLuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:58:09.791291Z"},"content_sha256":"45df2bfbbef6c1de594c350b3a1d72db8e56e727224f3377e9f15f5e32b99181","schema_version":"1.0","event_id":"sha256:45df2bfbbef6c1de594c350b3a1d72db8e56e727224f3377e9f15f5e32b99181"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4U3XOM7355ESGD72S4IYHUZH2E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jen-tse Huang, Pinjia He, Qiuzhi Liu, Wenxuan Wang, Xiaoyuan Liu, Youliang Yuan, Zhaopeng Tu","submitted_at":"2024-10-10T17:31:17Z","abstract_excerpt":"This paper explores the problem of commonsense level vision-knowledge conflict in Multimodal Large Language Models (MLLMs), where visual information contradicts model's internal commonsense knowledge. To study this issue, we introduce an automated framework, augmented with human-in-the-loop quality control, to generate inputs designed to simulate and evaluate these conflicts in MLLMs. Using this framework, we have crafted a diagnostic benchmark consisting of 374 original images and 1,122 high-quality question-answer (QA) pairs. The benchmark covers two aspects of conflict and three question ty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08145","kind":"arxiv","version":2},"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/2410.08145/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":"2026-07-05T11:13:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OjPB8QjgGp7bSCkYiNtIlVoilC6ndueBhQLKQy5e6/FGDwLTbZDkr5jVNz0LrJ82joRgOw80y2watV/x6U+iAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:58:09.791682Z"},"content_sha256":"593bc4b48dce50e8be263a929f923f638ab789d92a5962ad9dc2ff63593c4cc8","schema_version":"1.0","event_id":"sha256:593bc4b48dce50e8be263a929f923f638ab789d92a5962ad9dc2ff63593c4cc8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4U3XOM7355ESGD72S4IYHUZH2E/bundle.json","state_url":"https://pith.science/pith/4U3XOM7355ESGD72S4IYHUZH2E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4U3XOM7355ESGD72S4IYHUZH2E/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":"2026-07-06T20:58:09Z","links":{"resolver":"https://pith.science/pith/4U3XOM7355ESGD72S4IYHUZH2E","bundle":"https://pith.science/pith/4U3XOM7355ESGD72S4IYHUZH2E/bundle.json","state":"https://pith.science/pith/4U3XOM7355ESGD72S4IYHUZH2E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4U3XOM7355ESGD72S4IYHUZH2E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4U3XOM7355ESGD72S4IYHUZH2E","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":"93d02ce567fab2f36ddf244961119761d804401b9afc9e9971e54459aa875406","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T17:31:17Z","title_canon_sha256":"af7f4d49c27f6c689e65aeb1cf02b8b7948c3dcdd3efc6f44d3368d68e71720b"},"schema_version":"1.0","source":{"id":"2410.08145","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08145","created_at":"2026-07-05T11:13:13Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08145v2","created_at":"2026-07-05T11:13:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08145","created_at":"2026-07-05T11:13:13Z"},{"alias_kind":"pith_short_12","alias_value":"4U3XOM7355ES","created_at":"2026-07-05T11:13:13Z"},{"alias_kind":"pith_short_16","alias_value":"4U3XOM7355ESGD72","created_at":"2026-07-05T11:13:13Z"},{"alias_kind":"pith_short_8","alias_value":"4U3XOM73","created_at":"2026-07-05T11:13:13Z"}],"graph_snapshots":[{"event_id":"sha256:593bc4b48dce50e8be263a929f923f638ab789d92a5962ad9dc2ff63593c4cc8","target":"graph","created_at":"2026-07-05T11:13:13Z","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/2410.08145/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores the problem of commonsense level vision-knowledge conflict in Multimodal Large Language Models (MLLMs), where visual information contradicts model's internal commonsense knowledge. To study this issue, we introduce an automated framework, augmented with human-in-the-loop quality control, to generate inputs designed to simulate and evaluate these conflicts in MLLMs. Using this framework, we have crafted a diagnostic benchmark consisting of 374 original images and 1,122 high-quality question-answer (QA) pairs. The benchmark covers two aspects of conflict and three question ty","authors_text":"Jen-tse Huang, Pinjia He, Qiuzhi Liu, Wenxuan Wang, Xiaoyuan Liu, Youliang Yuan, Zhaopeng Tu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T17:31:17Z","title":"Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08145","kind":"arxiv","version":2},"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":"sha256:45df2bfbbef6c1de594c350b3a1d72db8e56e727224f3377e9f15f5e32b99181","target":"record","created_at":"2026-07-05T11:13:13Z","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":"93d02ce567fab2f36ddf244961119761d804401b9afc9e9971e54459aa875406","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T17:31:17Z","title_canon_sha256":"af7f4d49c27f6c689e65aeb1cf02b8b7948c3dcdd3efc6f44d3368d68e71720b"},"schema_version":"1.0","source":{"id":"2410.08145","kind":"arxiv","version":2}},"canonical_sha256":"e5377733fbef49230ffa971183d327d130020b7e13c92c226ccdec19972291ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5377733fbef49230ffa971183d327d130020b7e13c92c226ccdec19972291ad","first_computed_at":"2026-07-05T11:13:13.948967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:13.948967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tW3eGVFYz0RW6JftTSOmAf2UBPpMOWPjzWUIjjMvAXibLLousN4HqySxFklxEgNq9Cci0A7tFEViyuVY2XveBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:13.949532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08145","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45df2bfbbef6c1de594c350b3a1d72db8e56e727224f3377e9f15f5e32b99181","sha256:593bc4b48dce50e8be263a929f923f638ab789d92a5962ad9dc2ff63593c4cc8"],"state_sha256":"7e9448a2d536d670a86c5d9a36b6601a04b0c64460492b61c30110caa3858b00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M7yTCnT72PT6fFWc2opplcTNmCGbc01HlMXuKK7HYY4SDobB3atCRJgwOhf62kMrSl2y5XVxsP+fIK4lXJ7ZCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:58:09.793678Z","bundle_sha256":"0815cc92eec69c87bc3043bd007d79eb4af23039fc4ca0b44b2bc32cf961018b"}}