{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FWEICE2OPY7DCYU4ABLNLT7X4X","short_pith_number":"pith:FWEICE2O","canonical_record":{"source":{"id":"2410.11437","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T09:40:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"61a2faa4b62134365b48f4ba535d175468c6e94bf5009ffa0ce2dcc1e190f3a9","abstract_canon_sha256":"8a9375006947cb6b13de7b8008d9b99a1cc0d959a9e6e8bb2893f794929b62c0"},"schema_version":"1.0"},"canonical_sha256":"2d8881134e7e3e31629c0056d5cff7e5cc981a8879263825d4c6aebed1ba2b75","source":{"kind":"arxiv","id":"2410.11437","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11437","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11437v1","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11437","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"pith_short_12","alias_value":"FWEICE2OPY7D","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"pith_short_16","alias_value":"FWEICE2OPY7DCYU4","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"pith_short_8","alias_value":"FWEICE2O","created_at":"2026-07-05T09:20:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FWEICE2OPY7DCYU4ABLNLT7X4X","target":"record","payload":{"canonical_record":{"source":{"id":"2410.11437","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T09:40:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"61a2faa4b62134365b48f4ba535d175468c6e94bf5009ffa0ce2dcc1e190f3a9","abstract_canon_sha256":"8a9375006947cb6b13de7b8008d9b99a1cc0d959a9e6e8bb2893f794929b62c0"},"schema_version":"1.0"},"canonical_sha256":"2d8881134e7e3e31629c0056d5cff7e5cc981a8879263825d4c6aebed1ba2b75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:53.667415Z","signature_b64":"Ea+ibRu29L+1n5Nsh9XIxifaOECjpVK2QPh9HMgC6FwyTdHFR2Bo2BNPUjONF8GZ6U5UrqREZLMOlfdtiv8zDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d8881134e7e3e31629c0056d5cff7e5cc981a8879263825d4c6aebed1ba2b75","last_reissued_at":"2026-07-05T09:20:53.666956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:53.666956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.11437","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":"2026-07-05T09:20:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/0DpacEHEOoLsDaymwhjUmndJdahN8f+UZRh/t/u/ogBV33ogsv+0lROot8ZXThmIm9i8c1Auuj7AZEJj7yBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:20:57.586301Z"},"content_sha256":"21b62117526f58f2ff67eec4029e76d6227196b5b8e16c3ed7882ac5bc12bedc","schema_version":"1.0","event_id":"sha256:21b62117526f58f2ff67eec4029e76d6227196b5b8e16c3ed7882ac5bc12bedc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FWEICE2OPY7DCYU4ABLNLT7X4X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Pinjia He, Sihang Zhao, Xiaoying Tang, Youliang Yuan","submitted_at":"2024-10-15T09:40:50Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) demonstrate a strong understanding of the real world and can even handle complex tasks. However, they still fail on some straightforward visual question-answering (VQA) problems. This paper dives deeper into this issue, revealing that models tend to err when answering easy questions (e.g. Yes/No questions) about an image, even though they can correctly describe it. We refer to this model behavior discrepancy between difficult and simple questions as model laziness. To systematically investigate model laziness, we manually construct LazyBench, a benchmar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11437","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/2410.11437/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":"2026-07-05T09:20:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KKpC9W78FQIzwygLpg0TC4e7GCFa0Fohln7sIxxfGJFB3UdVJtpo4iv4kTgffAAncYVpBOfXxsvSLdArEIVLAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:20:57.586619Z"},"content_sha256":"489c2bad628b0d4fe44035f9821dd2f21c611b9ed99d0a700b9e317a897ede51","schema_version":"1.0","event_id":"sha256:489c2bad628b0d4fe44035f9821dd2f21c611b9ed99d0a700b9e317a897ede51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWEICE2OPY7DCYU4ABLNLT7X4X/bundle.json","state_url":"https://pith.science/pith/FWEICE2OPY7DCYU4ABLNLT7X4X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWEICE2OPY7DCYU4ABLNLT7X4X/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":"2026-08-14T19:20:57Z","links":{"resolver":"https://pith.science/pith/FWEICE2OPY7DCYU4ABLNLT7X4X","bundle":"https://pith.science/pith/FWEICE2OPY7DCYU4ABLNLT7X4X/bundle.json","state":"https://pith.science/pith/FWEICE2OPY7DCYU4ABLNLT7X4X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWEICE2OPY7DCYU4ABLNLT7X4X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FWEICE2OPY7DCYU4ABLNLT7X4X","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":"8a9375006947cb6b13de7b8008d9b99a1cc0d959a9e6e8bb2893f794929b62c0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T09:40:50Z","title_canon_sha256":"61a2faa4b62134365b48f4ba535d175468c6e94bf5009ffa0ce2dcc1e190f3a9"},"schema_version":"1.0","source":{"id":"2410.11437","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11437","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11437v1","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11437","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"pith_short_12","alias_value":"FWEICE2OPY7D","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"pith_short_16","alias_value":"FWEICE2OPY7DCYU4","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"pith_short_8","alias_value":"FWEICE2O","created_at":"2026-07-05T09:20:53Z"}],"graph_snapshots":[{"event_id":"sha256:489c2bad628b0d4fe44035f9821dd2f21c611b9ed99d0a700b9e317a897ede51","target":"graph","created_at":"2026-07-05T09:20:53Z","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/2410.11437/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) demonstrate a strong understanding of the real world and can even handle complex tasks. However, they still fail on some straightforward visual question-answering (VQA) problems. This paper dives deeper into this issue, revealing that models tend to err when answering easy questions (e.g. Yes/No questions) about an image, even though they can correctly describe it. We refer to this model behavior discrepancy between difficult and simple questions as model laziness. To systematically investigate model laziness, we manually construct LazyBench, a benchmar","authors_text":"Pinjia He, Sihang Zhao, Xiaoying Tang, Youliang Yuan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T09:40:50Z","title":"Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11437","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":"sha256:21b62117526f58f2ff67eec4029e76d6227196b5b8e16c3ed7882ac5bc12bedc","target":"record","created_at":"2026-07-05T09:20:53Z","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":"8a9375006947cb6b13de7b8008d9b99a1cc0d959a9e6e8bb2893f794929b62c0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T09:40:50Z","title_canon_sha256":"61a2faa4b62134365b48f4ba535d175468c6e94bf5009ffa0ce2dcc1e190f3a9"},"schema_version":"1.0","source":{"id":"2410.11437","kind":"arxiv","version":1}},"canonical_sha256":"2d8881134e7e3e31629c0056d5cff7e5cc981a8879263825d4c6aebed1ba2b75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d8881134e7e3e31629c0056d5cff7e5cc981a8879263825d4c6aebed1ba2b75","first_computed_at":"2026-07-05T09:20:53.666956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:53.666956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ea+ibRu29L+1n5Nsh9XIxifaOECjpVK2QPh9HMgC6FwyTdHFR2Bo2BNPUjONF8GZ6U5UrqREZLMOlfdtiv8zDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:53.667415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11437","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21b62117526f58f2ff67eec4029e76d6227196b5b8e16c3ed7882ac5bc12bedc","sha256:489c2bad628b0d4fe44035f9821dd2f21c611b9ed99d0a700b9e317a897ede51"],"state_sha256":"86b33df0fe0452b56cd169bde23322c63e748fd67268762652b192155bffd36b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l8E2wAXUovFMxN6LFdbSZjwmp4MMyV3vgbVxPUVi8jr+FmVYwBOujNJwkqjJEeRYsncMxAYO/mo4gzHEFdE1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:20:57.608044Z","bundle_sha256":"b85a9345895dbd5ae726684c0bd759fbfb22caf2c310812114feaceb2d621155"}}