{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VQR6P5EDNVYE5ZQVP7MVQ4UGPJ","short_pith_number":"pith:VQR6P5ED","canonical_record":{"source":{"id":"2505.10541","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T17:52:40Z","cross_cats_sorted":[],"title_canon_sha256":"cf10c22e163010c22ea9a62862f3bc3496db4b33fa38980f1bb3a0882745e44e","abstract_canon_sha256":"5c759e26c1df8130c83ed1fdf37b287e6fdfc1e0b4e2187e27c5f380badf81d4"},"schema_version":"1.0"},"canonical_sha256":"ac23e7f4836d704ee6157fd95872867a6ab75cc04ec8d104aef33debd4f31553","source":{"kind":"arxiv","id":"2505.10541","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10541","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10541v2","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10541","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"VQR6P5EDNVYE","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"VQR6P5EDNVYE5ZQV","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"VQR6P5ED","created_at":"2026-07-05T11:08:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VQR6P5EDNVYE5ZQVP7MVQ4UGPJ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.10541","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T17:52:40Z","cross_cats_sorted":[],"title_canon_sha256":"cf10c22e163010c22ea9a62862f3bc3496db4b33fa38980f1bb3a0882745e44e","abstract_canon_sha256":"5c759e26c1df8130c83ed1fdf37b287e6fdfc1e0b4e2187e27c5f380badf81d4"},"schema_version":"1.0"},"canonical_sha256":"ac23e7f4836d704ee6157fd95872867a6ab75cc04ec8d104aef33debd4f31553","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:20.535102Z","signature_b64":"McpV6NiQj9tzbCYueeshHrawTFfAuuqHo7tbpIKqy9/ZjEqUoB7qMgSbX1GN9tIw8sysK/iz0C004G5B2C9cDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac23e7f4836d704ee6157fd95872867a6ab75cc04ec8d104aef33debd4f31553","last_reissued_at":"2026-07-05T11:08:20.534602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:20.534602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.10541","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":"2026-07-05T11:08:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2xVV0dLgrEeyQMGWa4lECNNLmkWrUAX0uTWQXOhcXABddxMUu9C+NdBkuWZlZHCEsw1RQ+7D83oBYxFVL88YAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:53:28.524039Z"},"content_sha256":"a1a1a3c6f302c15918bc482402a2c2737e8c082d9dcd52c8d9b45b331ed4ea54","schema_version":"1.0","event_id":"sha256:a1a1a3c6f302c15918bc482402a2c2737e8c082d9dcd52c8d9b45b331ed4ea54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VQR6P5EDNVYE5ZQVP7MVQ4UGPJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Implicit Visual Misunderstandings in Multimodal Large Language Models through Attention Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guohai Xu, Jie Lou, Junjie Yang, Pengfei Wang, Weinong Wang, Yunhua Xue","submitted_at":"2025-05-15T17:52:40Z","abstract_excerpt":"Recent advancements have enhanced the capability of Multimodal Large Language Models (MLLMs) to comprehend multi-image information. However, existing benchmarks primarily evaluate answer correctness, overlooking whether models genuinely comprehend the visual input. To address this, we define implicit visual misunderstanding (IVM), where MLLMs provide correct answers without fully comprehending the visual input. Through our analysis, we decouple the visual and textual modalities within the causal attention module, revealing that attention distribution increasingly converges on the image associa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10541","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/2505.10541/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":"2026-07-05T11:08:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N02xtj4P1i3eTK5oXgqBZI9DlJX3IrhMdL7jSfB9OB6CSZcDkDLE5Id2xcbbVp1PjSU4Cn5AbWAaMCHEcxdKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:53:28.524546Z"},"content_sha256":"614da88c78881614be5b142f5dd86d93e61ca21e760e935f137a3a0918a4a9c6","schema_version":"1.0","event_id":"sha256:614da88c78881614be5b142f5dd86d93e61ca21e760e935f137a3a0918a4a9c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQR6P5EDNVYE5ZQVP7MVQ4UGPJ/bundle.json","state_url":"https://pith.science/pith/VQR6P5EDNVYE5ZQVP7MVQ4UGPJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQR6P5EDNVYE5ZQVP7MVQ4UGPJ/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":"2026-08-22T12:53:28Z","links":{"resolver":"https://pith.science/pith/VQR6P5EDNVYE5ZQVP7MVQ4UGPJ","bundle":"https://pith.science/pith/VQR6P5EDNVYE5ZQVP7MVQ4UGPJ/bundle.json","state":"https://pith.science/pith/VQR6P5EDNVYE5ZQVP7MVQ4UGPJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQR6P5EDNVYE5ZQVP7MVQ4UGPJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VQR6P5EDNVYE5ZQVP7MVQ4UGPJ","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":"5c759e26c1df8130c83ed1fdf37b287e6fdfc1e0b4e2187e27c5f380badf81d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T17:52:40Z","title_canon_sha256":"cf10c22e163010c22ea9a62862f3bc3496db4b33fa38980f1bb3a0882745e44e"},"schema_version":"1.0","source":{"id":"2505.10541","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10541","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10541v2","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10541","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"VQR6P5EDNVYE","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"VQR6P5EDNVYE5ZQV","created_at":"2026-07-05T11:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"VQR6P5ED","created_at":"2026-07-05T11:08:20Z"}],"graph_snapshots":[{"event_id":"sha256:614da88c78881614be5b142f5dd86d93e61ca21e760e935f137a3a0918a4a9c6","target":"graph","created_at":"2026-07-05T11:08:20Z","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/2505.10541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements have enhanced the capability of Multimodal Large Language Models (MLLMs) to comprehend multi-image information. However, existing benchmarks primarily evaluate answer correctness, overlooking whether models genuinely comprehend the visual input. To address this, we define implicit visual misunderstanding (IVM), where MLLMs provide correct answers without fully comprehending the visual input. Through our analysis, we decouple the visual and textual modalities within the causal attention module, revealing that attention distribution increasingly converges on the image associa","authors_text":"Guohai Xu, Jie Lou, Junjie Yang, Pengfei Wang, Weinong Wang, Yunhua Xue","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T17:52:40Z","title":"Exploring Implicit Visual Misunderstandings in Multimodal Large Language Models through Attention Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10541","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:a1a1a3c6f302c15918bc482402a2c2737e8c082d9dcd52c8d9b45b331ed4ea54","target":"record","created_at":"2026-07-05T11:08:20Z","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":"5c759e26c1df8130c83ed1fdf37b287e6fdfc1e0b4e2187e27c5f380badf81d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T17:52:40Z","title_canon_sha256":"cf10c22e163010c22ea9a62862f3bc3496db4b33fa38980f1bb3a0882745e44e"},"schema_version":"1.0","source":{"id":"2505.10541","kind":"arxiv","version":2}},"canonical_sha256":"ac23e7f4836d704ee6157fd95872867a6ab75cc04ec8d104aef33debd4f31553","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac23e7f4836d704ee6157fd95872867a6ab75cc04ec8d104aef33debd4f31553","first_computed_at":"2026-07-05T11:08:20.534602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:20.534602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"McpV6NiQj9tzbCYueeshHrawTFfAuuqHo7tbpIKqy9/ZjEqUoB7qMgSbX1GN9tIw8sysK/iz0C004G5B2C9cDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:20.535102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10541","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1a1a3c6f302c15918bc482402a2c2737e8c082d9dcd52c8d9b45b331ed4ea54","sha256:614da88c78881614be5b142f5dd86d93e61ca21e760e935f137a3a0918a4a9c6"],"state_sha256":"37f1c187e82d056be28f56f5d59662d3ebe781fa4f870a61d6d13ca93324d348"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+UVG+fPYGxVI6QIR19+OkNWlvNgUW3H7ALcyfn0JY8yViNoBEVBm6iXtNw7Mtz50iaHb8ficyxVlo2z5USg+Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T12:53:28.528388Z","bundle_sha256":"243523bc33f46ce6cabd46c4b920461c33926695eb082cfb48c57e71cc263a86"}}