{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ESTADSFEHUUPF6CVMSQQ7F4HVH","short_pith_number":"pith:ESTADSFE","canonical_record":{"source":{"id":"2502.13059","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T17:04:26Z","cross_cats_sorted":[],"title_canon_sha256":"b965ed9425e5324155eca364329897ec4a985c8aba15ccdb3e658f7b7d9ad2d7","abstract_canon_sha256":"88708a20b79b7a37b28fc3cbbcbe5443d4692025b9c1034a4ab584dcc748c4fb"},"schema_version":"1.0"},"canonical_sha256":"24a601c8a43d28f2f85564a10f9787a9fad7c7d50227220f7789f94c1ed71bf2","source":{"kind":"arxiv","id":"2502.13059","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13059","created_at":"2026-07-05T10:16:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13059v1","created_at":"2026-07-05T10:16:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13059","created_at":"2026-07-05T10:16:28Z"},{"alias_kind":"pith_short_12","alias_value":"ESTADSFEHUUP","created_at":"2026-07-05T10:16:28Z"},{"alias_kind":"pith_short_16","alias_value":"ESTADSFEHUUPF6CV","created_at":"2026-07-05T10:16:28Z"},{"alias_kind":"pith_short_8","alias_value":"ESTADSFE","created_at":"2026-07-05T10:16:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ESTADSFEHUUPF6CVMSQQ7F4HVH","target":"record","payload":{"canonical_record":{"source":{"id":"2502.13059","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T17:04:26Z","cross_cats_sorted":[],"title_canon_sha256":"b965ed9425e5324155eca364329897ec4a985c8aba15ccdb3e658f7b7d9ad2d7","abstract_canon_sha256":"88708a20b79b7a37b28fc3cbbcbe5443d4692025b9c1034a4ab584dcc748c4fb"},"schema_version":"1.0"},"canonical_sha256":"24a601c8a43d28f2f85564a10f9787a9fad7c7d50227220f7789f94c1ed71bf2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:28.667605Z","signature_b64":"r8vUAvBijHz9MuD1WvJu2lmx1cyQzb8gl4fHcD92JFa8We6EbiBQXtDr/WXdM3RLIrsoOom20bds1EPJMN6RBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24a601c8a43d28f2f85564a10f9787a9fad7c7d50227220f7789f94c1ed71bf2","last_reissued_at":"2026-07-05T10:16:28.667116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:28.667116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.13059","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":"2026-07-05T10:16:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c8omVmraehC271BygGBWor1mRnZZsvfXzKU1rDEQHPOg2YeX6adTHRS58cMvTbVFg3Kwe5wcNTT7XgOyQ3cEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T00:12:30.206351Z"},"content_sha256":"57ceda6924012288d4822b7b6d9b9892ffda4332405d614666f806838e177b28","schema_version":"1.0","event_id":"sha256:57ceda6924012288d4822b7b6d9b9892ffda4332405d614666f806838e177b28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ESTADSFEHUUPF6CVMSQQ7F4HVH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baorui Wang, Ge Zhang, Jiaheng Liu, Jian Yang, Ke Jin, Shiwei Zhang, Tongliang Li, Weixiao Zhou, Wei Zhang, Wenhao Huang, Xianfu Cheng, Xiang Li, Xiangyuan Guan, Xianjie Wu, Yunhong Lu, Yutao Zeng, Yuying Mai, Zhoufutu Wen, Zhoujun Li","submitted_at":"2025-02-18T17:04:26Z","abstract_excerpt":"The increasing application of multi-modal large language models (MLLMs) across various sectors have spotlighted the essence of their output reliability and accuracy, particularly their ability to produce content grounded in factual information (e.g. common and domain-specific knowledge). In this work, we introduce SimpleVQA, the first comprehensive multi-modal benchmark to evaluate the factuality ability of MLLMs to answer natural language short questions. SimpleVQA is characterized by six key features: it covers multiple tasks and multiple scenarios, ensures high quality and challenging queri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13059","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/2502.13059/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":"2026-07-05T10:16:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1JAwgvKubLzVFLCHyTYZJMvDWLkWSv82mevUiKT/VEGEGMm0VxyULebYTWcnB8rorh+wN9JjPT4le1X47RdTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T00:12:30.206832Z"},"content_sha256":"54e06708922c31beb32c378a3384e20ebe499be874d454a3673304025dfd4ef2","schema_version":"1.0","event_id":"sha256:54e06708922c31beb32c378a3384e20ebe499be874d454a3673304025dfd4ef2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ESTADSFEHUUPF6CVMSQQ7F4HVH/bundle.json","state_url":"https://pith.science/pith/ESTADSFEHUUPF6CVMSQQ7F4HVH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ESTADSFEHUUPF6CVMSQQ7F4HVH/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":"2026-07-09T00:12:30Z","links":{"resolver":"https://pith.science/pith/ESTADSFEHUUPF6CVMSQQ7F4HVH","bundle":"https://pith.science/pith/ESTADSFEHUUPF6CVMSQQ7F4HVH/bundle.json","state":"https://pith.science/pith/ESTADSFEHUUPF6CVMSQQ7F4HVH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ESTADSFEHUUPF6CVMSQQ7F4HVH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ESTADSFEHUUPF6CVMSQQ7F4HVH","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":"88708a20b79b7a37b28fc3cbbcbe5443d4692025b9c1034a4ab584dcc748c4fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T17:04:26Z","title_canon_sha256":"b965ed9425e5324155eca364329897ec4a985c8aba15ccdb3e658f7b7d9ad2d7"},"schema_version":"1.0","source":{"id":"2502.13059","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13059","created_at":"2026-07-05T10:16:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13059v1","created_at":"2026-07-05T10:16:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13059","created_at":"2026-07-05T10:16:28Z"},{"alias_kind":"pith_short_12","alias_value":"ESTADSFEHUUP","created_at":"2026-07-05T10:16:28Z"},{"alias_kind":"pith_short_16","alias_value":"ESTADSFEHUUPF6CV","created_at":"2026-07-05T10:16:28Z"},{"alias_kind":"pith_short_8","alias_value":"ESTADSFE","created_at":"2026-07-05T10:16:28Z"}],"graph_snapshots":[{"event_id":"sha256:54e06708922c31beb32c378a3384e20ebe499be874d454a3673304025dfd4ef2","target":"graph","created_at":"2026-07-05T10:16:28Z","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/2502.13059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing application of multi-modal large language models (MLLMs) across various sectors have spotlighted the essence of their output reliability and accuracy, particularly their ability to produce content grounded in factual information (e.g. common and domain-specific knowledge). In this work, we introduce SimpleVQA, the first comprehensive multi-modal benchmark to evaluate the factuality ability of MLLMs to answer natural language short questions. SimpleVQA is characterized by six key features: it covers multiple tasks and multiple scenarios, ensures high quality and challenging queri","authors_text":"Baorui Wang, Ge Zhang, Jiaheng Liu, Jian Yang, Ke Jin, Shiwei Zhang, Tongliang Li, Weixiao Zhou, Wei Zhang, Wenhao Huang, Xianfu Cheng, Xiang Li, Xiangyuan Guan, Xianjie Wu, Yunhong Lu, Yutao Zeng, Yuying Mai, Zhoufutu Wen, Zhoujun Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T17:04:26Z","title":"SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13059","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":"sha256:57ceda6924012288d4822b7b6d9b9892ffda4332405d614666f806838e177b28","target":"record","created_at":"2026-07-05T10:16:28Z","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":"88708a20b79b7a37b28fc3cbbcbe5443d4692025b9c1034a4ab584dcc748c4fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T17:04:26Z","title_canon_sha256":"b965ed9425e5324155eca364329897ec4a985c8aba15ccdb3e658f7b7d9ad2d7"},"schema_version":"1.0","source":{"id":"2502.13059","kind":"arxiv","version":1}},"canonical_sha256":"24a601c8a43d28f2f85564a10f9787a9fad7c7d50227220f7789f94c1ed71bf2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24a601c8a43d28f2f85564a10f9787a9fad7c7d50227220f7789f94c1ed71bf2","first_computed_at":"2026-07-05T10:16:28.667116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:28.667116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r8vUAvBijHz9MuD1WvJu2lmx1cyQzb8gl4fHcD92JFa8We6EbiBQXtDr/WXdM3RLIrsoOom20bds1EPJMN6RBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:28.667605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13059","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57ceda6924012288d4822b7b6d9b9892ffda4332405d614666f806838e177b28","sha256:54e06708922c31beb32c378a3384e20ebe499be874d454a3673304025dfd4ef2"],"state_sha256":"ccae3f2b99c338114096f00537abf0a919d53a8481d5b59d4e646b73153bcb7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NuYrk6jjnJYsOIMGb4RjFZ+JvzSNjRs2pL+H5YyuyK+8lXqKo4S2WUSklKgUDbn2YO24mElc1tCcnCgd39YNBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T00:12:30.209275Z","bundle_sha256":"bcdfa0165f1b6274ede7ae3f52a385515955fa6571d11cc315acdbc1fe04cdd2"}}