{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TVJWWNNIP5OYLFSQGSULWJVAIE","short_pith_number":"pith:TVJWWNNI","canonical_record":{"source":{"id":"2408.00765","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:59:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"89c12e4cba9bcce28519f7d07dd11ba63e7581a262f37291824d3b4a963a2a2e","abstract_canon_sha256":"f96eb4cfc88f1a04c86d7caea3154022c4609c407c81c796bd3eb909e2e8674b"},"schema_version":"1.0"},"canonical_sha256":"9d536b35a87f5d85965034a8bb26a04102614cfa10d7d3a2a78bd867d07bd1a7","source":{"kind":"arxiv","id":"2408.00765","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.00765","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.00765v2","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00765","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_12","alias_value":"TVJWWNNIP5OY","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_16","alias_value":"TVJWWNNIP5OYLFSQ","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_8","alias_value":"TVJWWNNI","created_at":"2026-07-05T09:42:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TVJWWNNIP5OYLFSQGSULWJVAIE","target":"record","payload":{"canonical_record":{"source":{"id":"2408.00765","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:59:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"89c12e4cba9bcce28519f7d07dd11ba63e7581a262f37291824d3b4a963a2a2e","abstract_canon_sha256":"f96eb4cfc88f1a04c86d7caea3154022c4609c407c81c796bd3eb909e2e8674b"},"schema_version":"1.0"},"canonical_sha256":"9d536b35a87f5d85965034a8bb26a04102614cfa10d7d3a2a78bd867d07bd1a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:28.561532Z","signature_b64":"UaRVlVqWvytJKzI2hzTY4fjuXoXb3jJVFKv8ddn06z8UjBWN4hRaJIiAqx1pMT7/wVg/NR0nlV1eGtb5RXSpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d536b35a87f5d85965034a8bb26a04102614cfa10d7d3a2a78bd867d07bd1a7","last_reissued_at":"2026-07-05T09:42:28.560986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:28.560986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.00765","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":"2026-07-05T09:42:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KD0KGgEycK3+Y02FWsb1JJvumqaLWa1gf+0XzMNs4waVTcy0VkevPCTrExM+NxODaJmcGhE+kMR+pnfq3c7oBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T19:44:12.999911Z"},"content_sha256":"aa8739fa7134a4aa6ddd8da858bcbbf450ee7a70d45ee26cc01e0e4801374a5e","schema_version":"1.0","event_id":"sha256:aa8739fa7134a4aa6ddd8da858bcbbf450ee7a70d45ee26cc01e0e4801374a5e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TVJWWNNIP5OYLFSQGSULWJVAIE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Jianfeng Wang, Kevin Lin, Lijuan Wang, Lingfeng Ren, Linjie Li, Weihao Yu, Xinchao Wang, Zhengyuan Yang, Zicheng Liu","submitted_at":"2024-08-01T17:59:54Z","abstract_excerpt":"MM-Vet, with open-ended vision-language questions targeting at evaluating integrated capabilities, has become one of the most popular benchmarks for large multimodal model evaluation. MM-Vet assesses six core vision-language (VL) capabilities: recognition, knowledge, spatial awareness, language generation, OCR, and math. However, its question format is restricted to single image-text pairs, lacking the interleaved image and text sequences prevalent in real-world scenarios. To address this limitation, we introduce MM-Vet v2, which includes a new VL capability called \"image-text sequence underst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00765","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/2408.00765/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":"2026-07-05T09:42:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2/lw4FQyy8vAkT758KdewiVS74YplLjWexvukCmFC/lifONqZL5Pr8FzNtMKwCicWCqYjfBRwonCb28SHwRHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T19:44:13.000445Z"},"content_sha256":"0ccc6af4cd7c660e0741f8abf55ec06d6b1c114e6d7334b7d3c175aa63d9e2b9","schema_version":"1.0","event_id":"sha256:0ccc6af4cd7c660e0741f8abf55ec06d6b1c114e6d7334b7d3c175aa63d9e2b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE/bundle.json","state_url":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TVJWWNNIP5OYLFSQGSULWJVAIE/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":"2026-08-02T19:44:13Z","links":{"resolver":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE","bundle":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE/bundle.json","state":"https://pith.science/pith/TVJWWNNIP5OYLFSQGSULWJVAIE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TVJWWNNIP5OYLFSQGSULWJVAIE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TVJWWNNIP5OYLFSQGSULWJVAIE","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":"f96eb4cfc88f1a04c86d7caea3154022c4609c407c81c796bd3eb909e2e8674b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:59:54Z","title_canon_sha256":"89c12e4cba9bcce28519f7d07dd11ba63e7581a262f37291824d3b4a963a2a2e"},"schema_version":"1.0","source":{"id":"2408.00765","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.00765","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.00765v2","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00765","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_12","alias_value":"TVJWWNNIP5OY","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_16","alias_value":"TVJWWNNIP5OYLFSQ","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_8","alias_value":"TVJWWNNI","created_at":"2026-07-05T09:42:28Z"}],"graph_snapshots":[{"event_id":"sha256:0ccc6af4cd7c660e0741f8abf55ec06d6b1c114e6d7334b7d3c175aa63d9e2b9","target":"graph","created_at":"2026-07-05T09:42:28Z","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/2408.00765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"MM-Vet, with open-ended vision-language questions targeting at evaluating integrated capabilities, has become one of the most popular benchmarks for large multimodal model evaluation. MM-Vet assesses six core vision-language (VL) capabilities: recognition, knowledge, spatial awareness, language generation, OCR, and math. However, its question format is restricted to single image-text pairs, lacking the interleaved image and text sequences prevalent in real-world scenarios. To address this limitation, we introduce MM-Vet v2, which includes a new VL capability called \"image-text sequence underst","authors_text":"Chung-Ching Lin, Jianfeng Wang, Kevin Lin, Lijuan Wang, Lingfeng Ren, Linjie Li, Weihao Yu, Xinchao Wang, Zhengyuan Yang, Zicheng Liu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:59:54Z","title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00765","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:aa8739fa7134a4aa6ddd8da858bcbbf450ee7a70d45ee26cc01e0e4801374a5e","target":"record","created_at":"2026-07-05T09:42:28Z","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":"f96eb4cfc88f1a04c86d7caea3154022c4609c407c81c796bd3eb909e2e8674b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:59:54Z","title_canon_sha256":"89c12e4cba9bcce28519f7d07dd11ba63e7581a262f37291824d3b4a963a2a2e"},"schema_version":"1.0","source":{"id":"2408.00765","kind":"arxiv","version":2}},"canonical_sha256":"9d536b35a87f5d85965034a8bb26a04102614cfa10d7d3a2a78bd867d07bd1a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d536b35a87f5d85965034a8bb26a04102614cfa10d7d3a2a78bd867d07bd1a7","first_computed_at":"2026-07-05T09:42:28.560986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:28.560986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UaRVlVqWvytJKzI2hzTY4fjuXoXb3jJVFKv8ddn06z8UjBWN4hRaJIiAqx1pMT7/wVg/NR0nlV1eGtb5RXSpAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:28.561532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.00765","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa8739fa7134a4aa6ddd8da858bcbbf450ee7a70d45ee26cc01e0e4801374a5e","sha256:0ccc6af4cd7c660e0741f8abf55ec06d6b1c114e6d7334b7d3c175aa63d9e2b9"],"state_sha256":"02d9af34be893a3bbdcae418d031d6ab26331a576292be1057f44478f1cff18f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4LAiJhv9cedfPEgkMSwLPw26ApzQimYNZ94IfKoO2T0u11+lzc0SseJcAJtfCgOHLHelAsHP/rdznsi2PKL6Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T19:44:13.006069Z","bundle_sha256":"70b522bde65249194a0c7a688b900de19837ea7466df50a2794df9e9e90e2ea2"}}