{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KJCXGZXOU4SX2SP5EE7NQPJ2QK","short_pith_number":"pith:KJCXGZXO","schema_version":"1.0","canonical_sha256":"52457366eea7257d49fd213ed83d3a82a3ec37a9f38bb0dd2ad7e69253cca1c2","source":{"kind":"arxiv","id":"2310.16534","version":1},"attestation_state":"computed","paper":{"title":"An Early Evaluation of GPT-4V(ision)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bing Qin, Hao Yang, Hongbo Zhang, Shilong Wang, Tian Zheng, Yang Wu, Yanyan Zhao","submitted_at":"2023-10-25T10:33:17Z","abstract_excerpt":"In this paper, we evaluate different abilities of GPT-4V including visual understanding, language understanding, visual puzzle solving, and understanding of other modalities such as depth, thermal, video, and audio. To estimate GPT-4V's performance, we manually construct 656 test instances and carefully evaluate the results of GPT-4V. The highlights of our findings are as follows: (1) GPT-4V exhibits impressive performance on English visual-centric benchmarks but fails to recognize simple Chinese texts in the images; (2) GPT-4V shows inconsistent refusal behavior when answering questions relat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.16534","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T10:33:17Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9b5087c665e43c4d9f77237716d5d7477b5d45815405dc57625c2cf4250a8a85","abstract_canon_sha256":"abb4e349ec2892f74bb464dc10d94090568c6f8d75ba470718b5bd41194f4967"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:59.070689Z","signature_b64":"ycrI2orJpnrhsCTT8B4TYlTH11X4sVqLDow8UV9ryAPrW1xK+iDBqDVyajghlDLROGBlG1NUBeuH9pKM3MFHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52457366eea7257d49fd213ed83d3a82a3ec37a9f38bb0dd2ad7e69253cca1c2","last_reissued_at":"2026-07-05T07:04:59.070160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:59.070160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Early Evaluation of GPT-4V(ision)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bing Qin, Hao Yang, Hongbo Zhang, Shilong Wang, Tian Zheng, Yang Wu, Yanyan Zhao","submitted_at":"2023-10-25T10:33:17Z","abstract_excerpt":"In this paper, we evaluate different abilities of GPT-4V including visual understanding, language understanding, visual puzzle solving, and understanding of other modalities such as depth, thermal, video, and audio. To estimate GPT-4V's performance, we manually construct 656 test instances and carefully evaluate the results of GPT-4V. The highlights of our findings are as follows: (1) GPT-4V exhibits impressive performance on English visual-centric benchmarks but fails to recognize simple Chinese texts in the images; (2) GPT-4V shows inconsistent refusal behavior when answering questions relat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16534","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/2310.16534/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.16534","created_at":"2026-07-05T07:04:59.070221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16534v1","created_at":"2026-07-05T07:04:59.070221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16534","created_at":"2026-07-05T07:04:59.070221+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJCXGZXOU4SX","created_at":"2026-07-05T07:04:59.070221+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJCXGZXOU4SX2SP5","created_at":"2026-07-05T07:04:59.070221+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJCXGZXO","created_at":"2026-07-05T07:04:59.070221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2311.07397","citing_title":"AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13394","citing_title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJCXGZXOU4SX2SP5EE7NQPJ2QK","json":"https://pith.science/pith/KJCXGZXOU4SX2SP5EE7NQPJ2QK.json","graph_json":"https://pith.science/api/pith-number/KJCXGZXOU4SX2SP5EE7NQPJ2QK/graph.json","events_json":"https://pith.science/api/pith-number/KJCXGZXOU4SX2SP5EE7NQPJ2QK/events.json","paper":"https://pith.science/paper/KJCXGZXO"},"agent_actions":{"view_html":"https://pith.science/pith/KJCXGZXOU4SX2SP5EE7NQPJ2QK","download_json":"https://pith.science/pith/KJCXGZXOU4SX2SP5EE7NQPJ2QK.json","view_paper":"https://pith.science/paper/KJCXGZXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16534&json=true","fetch_graph":"https://pith.science/api/pith-number/KJCXGZXOU4SX2SP5EE7NQPJ2QK/graph.json","fetch_events":"https://pith.science/api/pith-number/KJCXGZXOU4SX2SP5EE7NQPJ2QK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJCXGZXOU4SX2SP5EE7NQPJ2QK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJCXGZXOU4SX2SP5EE7NQPJ2QK/action/storage_attestation","attest_author":"https://pith.science/pith/KJCXGZXOU4SX2SP5EE7NQPJ2QK/action/author_attestation","sign_citation":"https://pith.science/pith/KJCXGZXOU4SX2SP5EE7NQPJ2QK/action/citation_signature","submit_replication":"https://pith.science/pith/KJCXGZXOU4SX2SP5EE7NQPJ2QK/action/replication_record"}},"created_at":"2026-07-05T07:04:59.070221+00:00","updated_at":"2026-07-05T07:04:59.070221+00:00"}