{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2MD3PLBMT6QKU3XL2GAJZJJ6B7","short_pith_number":"pith:2MD3PLBM","canonical_record":{"source":{"id":"2307.16125","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-30T04:25:16Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3cfa260a255e77b76cec5139aa572843eb9b952de93949abd296a45d044f1902","abstract_canon_sha256":"8b5fdc45f6d246ff05679d76140b94cc8ef1bd3b82a6eaf00c67fead7297a2a5"},"schema_version":"1.0"},"canonical_sha256":"d307b7ac2c9fa0aa6eebd1809ca53e0fc7d15b6e9b301c0acabd365aab3b8676","source":{"kind":"arxiv","id":"2307.16125","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16125","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16125v2","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16125","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"pith_short_12","alias_value":"2MD3PLBMT6QK","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"pith_short_16","alias_value":"2MD3PLBMT6QKU3XL","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"pith_short_8","alias_value":"2MD3PLBM","created_at":"2026-07-05T06:36:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2MD3PLBMT6QKU3XL2GAJZJJ6B7","target":"record","payload":{"canonical_record":{"source":{"id":"2307.16125","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-30T04:25:16Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3cfa260a255e77b76cec5139aa572843eb9b952de93949abd296a45d044f1902","abstract_canon_sha256":"8b5fdc45f6d246ff05679d76140b94cc8ef1bd3b82a6eaf00c67fead7297a2a5"},"schema_version":"1.0"},"canonical_sha256":"d307b7ac2c9fa0aa6eebd1809ca53e0fc7d15b6e9b301c0acabd365aab3b8676","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:55.687271Z","signature_b64":"uoAcFJCiwiu9RDlRt6NhTysVs49Xko05wetSnKt/qZVR09miGC6JEKeBiJxgyL4CYD2g6YN4aT2/XyU+c9eoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d307b7ac2c9fa0aa6eebd1809ca53e0fc7d15b6e9b301c0acabd365aab3b8676","last_reissued_at":"2026-07-05T06:36:55.686764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:55.686764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.16125","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":"2026-07-05T06:36:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jyQk6ELns1YXdt9PslO7iQPA4sbron5rPl3+nYHx+Hbf/FMWUoaqY4ur2w1xHIa27uofDcvhlHdt0F+Z1DRdDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:11:30.872842Z"},"content_sha256":"8afc525728495fa344a5d305da599ba5a7dbc93c24e3e1e593c0ff52c8e59ea0","schema_version":"1.0","event_id":"sha256:8afc525728495fa344a5d305da599ba5a7dbc93c24e3e1e593c0ff52c8e59ea0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2MD3PLBMT6QKU3XL2GAJZJJ6B7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"SEED-Bench supplies 19K human-verified multiple-choice questions to measure multimodal LLMs on image and video comprehension across 12 dimensions.","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bohao Li, Guangzhi Wang, Rui Wang, Ying Shan, Yixiao Ge, Yuying Ge","submitted_at":"2023-07-30T04:25:16Z","abstract_excerpt":"Based on powerful Large Language Models (LLMs), recent generative Multimodal Large Language Models (MLLMs) have gained prominence as a pivotal research area, exhibiting remarkable capability for both comprehension and generation. In this work, we address the evaluation of generative comprehension in MLLMs as a preliminary step towards a comprehensive assessment of generative models, by introducing a benchmark named SEED-Bench. SEED-Bench consists of 19K multiple choice questions with accurate human annotations (x 6 larger than existing benchmarks), which spans 12 evaluation dimensions includin"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SEED-Bench consists of 19K multiple choice questions with accurate human annotations (x 6 larger than existing benchmarks), which spans 12 evaluation dimensions including the comprehension of both the image and video modality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the pipeline of automatic question generation plus manual verification produces questions that genuinely measure generative comprehension rather than artifacts of the generation process itself.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SEED-Bench is a new benchmark of 19K multiple-choice questions for evaluating generative comprehension in multimodal LLMs across 12 image and video dimensions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SEED-Bench supplies 19K human-verified multiple-choice questions to measure multimodal LLMs on image and video comprehension across 12 dimensions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"446d3742bfce8b2df877ed41886b90a9833d90d6939bcd7a74319525b99f20e2"},"source":{"id":"2307.16125","kind":"arxiv","version":2},"verdict":{"id":"dede37a3-26a2-4e9a-870a-4cc4cef5795b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T16:55:12.675278Z","strongest_claim":"SEED-Bench consists of 19K multiple choice questions with accurate human annotations (x 6 larger than existing benchmarks), which spans 12 evaluation dimensions including the comprehension of both the image and video modality.","one_line_summary":"SEED-Bench is a new benchmark of 19K multiple-choice questions for evaluating generative comprehension in multimodal LLMs across 12 image and video dimensions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the pipeline of automatic question generation plus manual verification produces questions that genuinely measure generative comprehension rather than artifacts of the generation process itself.","pith_extraction_headline":"SEED-Bench supplies 19K human-verified multiple-choice questions to measure multimodal LLMs on image and video comprehension across 12 dimensions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.16125/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":42,"sample":[{"doi":"","year":2022,"title":"Scaling Instruction-Finetuned Language Models","work_id":"8405abb1-7558-4fdf-af24-f4c52fa77a06","ref_index":1,"cited_arxiv_id":"2210.11416","is_internal_anchor":true},{"doi":"","year":2023,"title":"Gpt-4 technical report","work_id":"388f534c-855a-4366-b933-f07bf3e2db5f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Introducing chatgpt","work_id":"1b840f0b-fb6b-43d7-bc36-05b0a98a171e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"FastChat. Vicuna. https://github.com/lm-sys/FastChat, 2023","work_id":"ee2e3957-facb-454c-b74c-07fdc354f73e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","ref_index":5,"cited_arxiv_id":"2302.13971","is_internal_anchor":true}],"resolved_work":42,"snapshot_sha256":"b967801c3b760b0eff858d80d9e18d6823f2cfd7743a7f5011bd81be2bf3f7e3","internal_anchors":16},"formal_canon":{"evidence_count":2,"snapshot_sha256":"488a2e33743f22e32483cda8e09b1b26e774339717002e8ebfc44bb5f09d6748"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"dede37a3-26a2-4e9a-870a-4cc4cef5795b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:36:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lWAlzT/HKOKnlMr6AhVanZK7Z8iIf38fbPdjCk5UgqtfPPAdE0pbfXMEXavAS31fkTotK8L3dFWOkkDzhYEPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:11:30.873873Z"},"content_sha256":"fc00873123b823ad76d09765c7108480619db9e3825469f3816817307e0f6eb7","schema_version":"1.0","event_id":"sha256:fc00873123b823ad76d09765c7108480619db9e3825469f3816817307e0f6eb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2MD3PLBMT6QKU3XL2GAJZJJ6B7/bundle.json","state_url":"https://pith.science/pith/2MD3PLBMT6QKU3XL2GAJZJJ6B7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2MD3PLBMT6QKU3XL2GAJZJJ6B7/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":"2026-08-04T01:11:30Z","links":{"resolver":"https://pith.science/pith/2MD3PLBMT6QKU3XL2GAJZJJ6B7","bundle":"https://pith.science/pith/2MD3PLBMT6QKU3XL2GAJZJJ6B7/bundle.json","state":"https://pith.science/pith/2MD3PLBMT6QKU3XL2GAJZJJ6B7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2MD3PLBMT6QKU3XL2GAJZJJ6B7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2MD3PLBMT6QKU3XL2GAJZJJ6B7","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":"8b5fdc45f6d246ff05679d76140b94cc8ef1bd3b82a6eaf00c67fead7297a2a5","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-30T04:25:16Z","title_canon_sha256":"3cfa260a255e77b76cec5139aa572843eb9b952de93949abd296a45d044f1902"},"schema_version":"1.0","source":{"id":"2307.16125","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16125","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16125v2","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16125","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"pith_short_12","alias_value":"2MD3PLBMT6QK","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"pith_short_16","alias_value":"2MD3PLBMT6QKU3XL","created_at":"2026-07-05T06:36:55Z"},{"alias_kind":"pith_short_8","alias_value":"2MD3PLBM","created_at":"2026-07-05T06:36:55Z"}],"graph_snapshots":[{"event_id":"sha256:fc00873123b823ad76d09765c7108480619db9e3825469f3816817307e0f6eb7","target":"graph","created_at":"2026-07-05T06:36:55Z","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":"SEED-Bench consists of 19K multiple choice questions with accurate human annotations (x 6 larger than existing benchmarks), which spans 12 evaluation dimensions including the comprehension of both the image and video modality."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the pipeline of automatic question generation plus manual verification produces questions that genuinely measure generative comprehension rather than artifacts of the generation process itself."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SEED-Bench is a new benchmark of 19K multiple-choice questions for evaluating generative comprehension in multimodal LLMs across 12 image and video dimensions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SEED-Bench supplies 19K human-verified multiple-choice questions to measure multimodal LLMs on image and video comprehension across 12 dimensions."}],"snapshot_sha256":"446d3742bfce8b2df877ed41886b90a9833d90d6939bcd7a74319525b99f20e2"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"488a2e33743f22e32483cda8e09b1b26e774339717002e8ebfc44bb5f09d6748"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2307.16125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Based on powerful Large Language Models (LLMs), recent generative Multimodal Large Language Models (MLLMs) have gained prominence as a pivotal research area, exhibiting remarkable capability for both comprehension and generation. In this work, we address the evaluation of generative comprehension in MLLMs as a preliminary step towards a comprehensive assessment of generative models, by introducing a benchmark named SEED-Bench. SEED-Bench consists of 19K multiple choice questions with accurate human annotations (x 6 larger than existing benchmarks), which spans 12 evaluation dimensions includin","authors_text":"Bohao Li, Guangzhi Wang, Rui Wang, Ying Shan, Yixiao Ge, Yuying Ge","cross_cats":["cs.CV"],"headline":"SEED-Bench supplies 19K human-verified multiple-choice questions to measure multimodal LLMs on image and video comprehension across 12 dimensions.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-30T04:25:16Z","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension"},"references":{"count":42,"internal_anchors":16,"resolved_work":42,"sample":[{"cited_arxiv_id":"2210.11416","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Scaling Instruction-Finetuned Language Models","work_id":"8405abb1-7558-4fdf-af24-f4c52fa77a06","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Gpt-4 technical report","work_id":"388f534c-855a-4366-b933-f07bf3e2db5f","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Introducing chatgpt","work_id":"1b840f0b-fb6b-43d7-bc36-05b0a98a171e","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"FastChat. Vicuna. https://github.com/lm-sys/FastChat, 2023","work_id":"ee2e3957-facb-454c-b74c-07fdc354f73e","year":2023},{"cited_arxiv_id":"2302.13971","doi":"","is_internal_anchor":true,"ref_index":5,"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","year":2023}],"snapshot_sha256":"b967801c3b760b0eff858d80d9e18d6823f2cfd7743a7f5011bd81be2bf3f7e3"},"source":{"id":"2307.16125","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T16:55:12.675278Z","id":"dede37a3-26a2-4e9a-870a-4cc4cef5795b","model_set":{"reader":"grok-4.3"},"one_line_summary":"SEED-Bench is a new benchmark of 19K multiple-choice questions for evaluating generative comprehension in multimodal LLMs across 12 image and video dimensions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"SEED-Bench supplies 19K human-verified multiple-choice questions to measure multimodal LLMs on image and video comprehension across 12 dimensions.","strongest_claim":"SEED-Bench consists of 19K multiple choice questions with accurate human annotations (x 6 larger than existing benchmarks), which spans 12 evaluation dimensions including the comprehension of both the image and video modality.","weakest_assumption":"That the pipeline of automatic question generation plus manual verification produces questions that genuinely measure generative comprehension rather than artifacts of the generation process itself."}},"verdict_id":"dede37a3-26a2-4e9a-870a-4cc4cef5795b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8afc525728495fa344a5d305da599ba5a7dbc93c24e3e1e593c0ff52c8e59ea0","target":"record","created_at":"2026-07-05T06:36:55Z","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":"8b5fdc45f6d246ff05679d76140b94cc8ef1bd3b82a6eaf00c67fead7297a2a5","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-30T04:25:16Z","title_canon_sha256":"3cfa260a255e77b76cec5139aa572843eb9b952de93949abd296a45d044f1902"},"schema_version":"1.0","source":{"id":"2307.16125","kind":"arxiv","version":2}},"canonical_sha256":"d307b7ac2c9fa0aa6eebd1809ca53e0fc7d15b6e9b301c0acabd365aab3b8676","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d307b7ac2c9fa0aa6eebd1809ca53e0fc7d15b6e9b301c0acabd365aab3b8676","first_computed_at":"2026-07-05T06:36:55.686764Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:36:55.686764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uoAcFJCiwiu9RDlRt6NhTysVs49Xko05wetSnKt/qZVR09miGC6JEKeBiJxgyL4CYD2g6YN4aT2/XyU+c9eoAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:36:55.687271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.16125","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8afc525728495fa344a5d305da599ba5a7dbc93c24e3e1e593c0ff52c8e59ea0","sha256:fc00873123b823ad76d09765c7108480619db9e3825469f3816817307e0f6eb7"],"state_sha256":"65b2729a1c544e5ae43ab4ac3cd309bce50f7d049ca4d1190fd114a1ab71d95d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"srcc1rG/NJvZ2o7Y6Vc82iVG0dqQj/x1mZ8bxXL72cA8gNOcBpQqYGnce5UY0A16CYZUfqDd0Z321qNhmbemBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T01:11:30.880685Z","bundle_sha256":"d9aeb649338ab97a2a7ec415b67a44322dddfef27f347c90720a7b6e04f51a17"}}