{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E4ST4TYIFZXUNH4NLCXSENDMNM","short_pith_number":"pith:E4ST4TYI","canonical_record":{"source":{"id":"2407.12772","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T17:51:53Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9304da0fd6df0a43a304bc7313fd5757487e366e8650beec5abefe326d06a3a2","abstract_canon_sha256":"4e942c277c09028045710149d7f7bf8b6da6f6a2028782aa5a1e0e123c0fb3bd"},"schema_version":"1.0"},"canonical_sha256":"27253e4f082e6f469f8d58af22346c6b1fce493d856b203c45919958e98d8fa0","source":{"kind":"arxiv","id":"2407.12772","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12772","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12772v2","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12772","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"pith_short_12","alias_value":"E4ST4TYIFZXU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"E4ST4TYIFZXUNH4N","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"E4ST4TYI","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E4ST4TYIFZXUNH4NLCXSENDMNM","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12772","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T17:51:53Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9304da0fd6df0a43a304bc7313fd5757487e366e8650beec5abefe326d06a3a2","abstract_canon_sha256":"4e942c277c09028045710149d7f7bf8b6da6f6a2028782aa5a1e0e123c0fb3bd"},"schema_version":"1.0"},"canonical_sha256":"27253e4f082e6f469f8d58af22346c6b1fce493d856b203c45919958e98d8fa0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:15.009691Z","signature_b64":"/db6vdtnPHx4hLMrb7vbrQ9PC4Zkq95eghk3UFxjcSMIYOhlgF02PRRoqsQ0DPP8ymJjHwfBDWB66JDKQCsBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27253e4f082e6f469f8d58af22346c6b1fce493d856b203c45919958e98d8fa0","last_reissued_at":"2026-05-17T23:38:15.008955Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:15.008955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12772","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":"2026-05-17T23:38:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e99RG0QMOOVnY3Gz+8X5qbMVNjgv8tuePPkLfkByUNP9Hb29jR3iNBQJGfMYB8Xf9HCa7xaEU4hwLs15sRe6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T06:35:01.944919Z"},"content_sha256":"f0b171f78f260e919f152a23537d8aae0b927a3c3288e99306f479edd02283fa","schema_version":"1.0","event_id":"sha256:f0b171f78f260e919f152a23537d8aae0b927a3c3288e99306f479edd02283fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E4ST4TYIFZXUNH4NLCXSENDMNM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Evaluating large multimodal models requires balancing wide task coverage, low computational cost, and zero data contamination in benchmarks.","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bo Li, Chunyuan Li, Fanyi Pu, Jingkang Yang, Joshua Adrian Cahyono, Kaichen Zhang, Kairui Hu, Peiyuan Zhang, Shuai Liu, Yuanhan Zhang, Ziwei Liu","submitted_at":"2024-07-17T17:51:53Z","abstract_excerpt":"The advances of large foundation models necessitate wide-coverage, low-cost, and zero-contamination benchmarks. Despite continuous exploration of language model evaluations, comprehensive studies on the evaluation of Large Multi-modal Models (LMMs) remain limited. In this work, we introduce LMMS-EVAL, a unified and standardized multimodal benchmark framework with over 50 tasks and more than 10 models to promote transparent and reproducible evaluations. Although LMMS-EVAL offers comprehensive coverage, we find it still falls short in achieving low cost and zero contamination. To approach this e"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our work highlights the importance of considering the evaluation trilemma and provides practical solutions to navigate the trade-offs in evaluating large multi-modal models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the live data sources and pruning rules in LMMS-EVAL LITE and LIVEBENCH truly deliver zero contamination and maintained coverage without introducing new selection biases or missing important capabilities.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LMMS-EVAL delivers a standardized multimodal evaluation framework with lite and live variants that target the trade-offs among coverage, cost, and zero contamination.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Evaluating large multimodal models requires balancing wide task coverage, low computational cost, and zero data contamination in benchmarks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e3d49ea222040ef472c564e264ba79f6f27b0de3ed651315426759c8b1ffb32d"},"source":{"id":"2407.12772","kind":"arxiv","version":2},"verdict":{"id":"aea1499b-8ccf-4737-bb8a-8fa3e282bc8c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T05:15:22.504049Z","strongest_claim":"Our work highlights the importance of considering the evaluation trilemma and provides practical solutions to navigate the trade-offs in evaluating large multi-modal models.","one_line_summary":"LMMS-EVAL delivers a standardized multimodal evaluation framework with lite and live variants that target the trade-offs among coverage, cost, and zero contamination.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the live data sources and pruning rules in LMMS-EVAL LITE and LIVEBENCH truly deliver zero contamination and maintained coverage without introducing new selection biases or missing important capabilities.","pith_extraction_headline":"Evaluating large multimodal models requires balancing wide task coverage, low computational cost, and zero data contamination in benchmarks."},"references":{"count":24,"sample":[{"doi":"","year":null,"title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","work_id":"f3aac728-ded0-4e55-aa9e-4a1635d4313d","ref_index":1,"cited_arxiv_id":"2305.06500","is_internal_anchor":true},{"doi":"","year":null,"title":"Internlm-xcomposer2- 4khd: A pioneering large vision-language model handling resolutions from 336 pixels to 4k hd","work_id":"799b1f12-2edc-4b09-a83b-dbd87e1404e7","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","work_id":"806d2e73-71b3-4d56-87e0-39d571cc15d6","ref_index":3,"cited_arxiv_id":"2306.13394","is_internal_anchor":true},{"doi":"","year":2023,"title":"Making llama see and draw with seed tokenizer","work_id":"9453feaf-a19d-4603-b9de-da50593c5d43","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"A diagram is worth a dozen images.ArXiv, abs/1603.07396","work_id":"3cc7177d-7f05-4d4d-8066-04b7d589017f","ref_index":5,"cited_arxiv_id":"1603.07396","is_internal_anchor":true}],"resolved_work":24,"snapshot_sha256":"8259cdf1001bbc4b76ac39e2a416d1dc500d9bc07d1609c7bd56eafeaa80ae19","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0fe42ac1f960edabb5776079e4c5fb9f1ed2d110b322762081d32bcc4709db70"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"aea1499b-8ccf-4737-bb8a-8fa3e282bc8c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yPaDQwBNhW5REMOfavKxGA/JFSHIe6mWa9lz8gBd3xeACYhwVXlBmMEVr7j1S95cY9ANcoYqraNPQgunMlukAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T06:35:01.945532Z"},"content_sha256":"12fd4ef0d69cf6a031dfe7ee4eabee1319a74f9ef479384c87b7f62f4f674b5c","schema_version":"1.0","event_id":"sha256:12fd4ef0d69cf6a031dfe7ee4eabee1319a74f9ef479384c87b7f62f4f674b5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM/bundle.json","state_url":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E4ST4TYIFZXUNH4NLCXSENDMNM/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":"2026-05-24T06:35:01Z","links":{"resolver":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM","bundle":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM/bundle.json","state":"https://pith.science/pith/E4ST4TYIFZXUNH4NLCXSENDMNM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E4ST4TYIFZXUNH4NLCXSENDMNM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E4ST4TYIFZXUNH4NLCXSENDMNM","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":"4e942c277c09028045710149d7f7bf8b6da6f6a2028782aa5a1e0e123c0fb3bd","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T17:51:53Z","title_canon_sha256":"9304da0fd6df0a43a304bc7313fd5757487e366e8650beec5abefe326d06a3a2"},"schema_version":"1.0","source":{"id":"2407.12772","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12772","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12772v2","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12772","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"pith_short_12","alias_value":"E4ST4TYIFZXU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"E4ST4TYIFZXUNH4N","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"E4ST4TYI","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:12fd4ef0d69cf6a031dfe7ee4eabee1319a74f9ef479384c87b7f62f4f674b5c","target":"graph","created_at":"2026-05-17T23:38:15Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our work highlights the importance of considering the evaluation trilemma and provides practical solutions to navigate the trade-offs in evaluating large multi-modal models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the live data sources and pruning rules in LMMS-EVAL LITE and LIVEBENCH truly deliver zero contamination and maintained coverage without introducing new selection biases or missing important capabilities."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LMMS-EVAL delivers a standardized multimodal evaluation framework with lite and live variants that target the trade-offs among coverage, cost, and zero contamination."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Evaluating large multimodal models requires balancing wide task coverage, low computational cost, and zero data contamination in benchmarks."}],"snapshot_sha256":"e3d49ea222040ef472c564e264ba79f6f27b0de3ed651315426759c8b1ffb32d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0fe42ac1f960edabb5776079e4c5fb9f1ed2d110b322762081d32bcc4709db70"},"paper":{"abstract_excerpt":"The advances of large foundation models necessitate wide-coverage, low-cost, and zero-contamination benchmarks. Despite continuous exploration of language model evaluations, comprehensive studies on the evaluation of Large Multi-modal Models (LMMs) remain limited. In this work, we introduce LMMS-EVAL, a unified and standardized multimodal benchmark framework with over 50 tasks and more than 10 models to promote transparent and reproducible evaluations. Although LMMS-EVAL offers comprehensive coverage, we find it still falls short in achieving low cost and zero contamination. To approach this e","authors_text":"Bo Li, Chunyuan Li, Fanyi Pu, Jingkang Yang, Joshua Adrian Cahyono, Kaichen Zhang, Kairui Hu, Peiyuan Zhang, Shuai Liu, Yuanhan Zhang, Ziwei Liu","cross_cats":["cs.CV"],"headline":"Evaluating large multimodal models requires balancing wide task coverage, low computational cost, and zero data contamination in benchmarks.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T17:51:53Z","title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models"},"references":{"count":24,"internal_anchors":3,"resolved_work":24,"sample":[{"cited_arxiv_id":"2305.06500","doi":"","is_internal_anchor":true,"ref_index":1,"title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","work_id":"f3aac728-ded0-4e55-aa9e-4a1635d4313d","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Internlm-xcomposer2- 4khd: A pioneering large vision-language model handling resolutions from 336 pixels to 4k hd","work_id":"799b1f12-2edc-4b09-a83b-dbd87e1404e7","year":null},{"cited_arxiv_id":"2306.13394","doi":"","is_internal_anchor":true,"ref_index":3,"title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","work_id":"806d2e73-71b3-4d56-87e0-39d571cc15d6","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Making llama see and draw with seed tokenizer","work_id":"9453feaf-a19d-4603-b9de-da50593c5d43","year":2023},{"cited_arxiv_id":"1603.07396","doi":"","is_internal_anchor":true,"ref_index":5,"title":"A diagram is worth a dozen images.ArXiv, abs/1603.07396","work_id":"3cc7177d-7f05-4d4d-8066-04b7d589017f","year":2022}],"snapshot_sha256":"8259cdf1001bbc4b76ac39e2a416d1dc500d9bc07d1609c7bd56eafeaa80ae19"},"source":{"id":"2407.12772","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T05:15:22.504049Z","id":"aea1499b-8ccf-4737-bb8a-8fa3e282bc8c","model_set":{"reader":"grok-4.3"},"one_line_summary":"LMMS-EVAL delivers a standardized multimodal evaluation framework with lite and live variants that target the trade-offs among coverage, cost, and zero contamination.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Evaluating large multimodal models requires balancing wide task coverage, low computational cost, and zero data contamination in benchmarks.","strongest_claim":"Our work highlights the importance of considering the evaluation trilemma and provides practical solutions to navigate the trade-offs in evaluating large multi-modal models.","weakest_assumption":"That the live data sources and pruning rules in LMMS-EVAL LITE and LIVEBENCH truly deliver zero contamination and maintained coverage without introducing new selection biases or missing important capabilities."}},"verdict_id":"aea1499b-8ccf-4737-bb8a-8fa3e282bc8c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f0b171f78f260e919f152a23537d8aae0b927a3c3288e99306f479edd02283fa","target":"record","created_at":"2026-05-17T23:38:15Z","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":"4e942c277c09028045710149d7f7bf8b6da6f6a2028782aa5a1e0e123c0fb3bd","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T17:51:53Z","title_canon_sha256":"9304da0fd6df0a43a304bc7313fd5757487e366e8650beec5abefe326d06a3a2"},"schema_version":"1.0","source":{"id":"2407.12772","kind":"arxiv","version":2}},"canonical_sha256":"27253e4f082e6f469f8d58af22346c6b1fce493d856b203c45919958e98d8fa0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27253e4f082e6f469f8d58af22346c6b1fce493d856b203c45919958e98d8fa0","first_computed_at":"2026-05-17T23:38:15.008955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:15.008955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/db6vdtnPHx4hLMrb7vbrQ9PC4Zkq95eghk3UFxjcSMIYOhlgF02PRRoqsQ0DPP8ymJjHwfBDWB66JDKQCsBBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:15.009691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12772","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0b171f78f260e919f152a23537d8aae0b927a3c3288e99306f479edd02283fa","sha256:12fd4ef0d69cf6a031dfe7ee4eabee1319a74f9ef479384c87b7f62f4f674b5c"],"state_sha256":"c02b56f35fd142f4a685a2fe96a5c50502fb3f395869d46380a2b73be9671711"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cwdkfCxPschoGS/IV2Gg0OKroWUHjAoKB6RZs+80WEHiChEyZ7ERQrcQr9HZtZbKu0GMZhsVXI0QPIMEkb8JDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T06:35:01.948632Z","bundle_sha256":"81621e8c51e1e9e2fac84369c4dd3a39cc73affd68a3d3a8e5d0d5166c33d997"}}