{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:P2DC7CTHVXI4CCPLU5UKTYMVZX","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":"77fab89cf75859b726a15ece8ba3796c86f2e6b3cbb6fe2fbe3f43b8309bc1c3","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-13T08:54:49Z","title_canon_sha256":"10fe26f5d464289c03790859042e80a0a3d6ce7127fe29be833c7c09e71d8bd4"},"schema_version":"1.0","source":{"id":"2312.11524","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11524","created_at":"2026-07-05T07:25:50Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11524v1","created_at":"2026-07-05T07:25:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11524","created_at":"2026-07-05T07:25:50Z"},{"alias_kind":"pith_short_12","alias_value":"P2DC7CTHVXI4","created_at":"2026-07-05T07:25:50Z"},{"alias_kind":"pith_short_16","alias_value":"P2DC7CTHVXI4CCPL","created_at":"2026-07-05T07:25:50Z"},{"alias_kind":"pith_short_8","alias_value":"P2DC7CTH","created_at":"2026-07-05T07:25:50Z"}],"graph_snapshots":[{"event_id":"sha256:2f39dd23c40c8d7d58cc52a8c707a2c170729b6bef5cca48fc544db1f75b654d","target":"graph","created_at":"2026-07-05T07:25:50Z","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/2312.11524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modality promises to unlock further uses for large language models. Recently, the state-of-the-art language model GPT-4 was enhanced with vision capabilities. We carry out a prompting evaluation of GPT-4V and five other baselines on structured reasoning tasks, such as mathematical reasoning, visual data analysis, and code generation. We show that visual Chain-of-Thought, an extension of Chain-of-Thought to multi-modal LLMs, yields significant improvements over the vanilla model. We also present a categorized analysis of scenarios where these models perform well and where they struggle, h","authors_text":"Gust Verbruggen, Jos\\'e Cambronero, Mukul Singh, Sumit Gulwani, Vu Le","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-13T08:54:49Z","title":"Assessing GPT4-V on Structured Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11524","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":"sha256:6a234aff200d5d82c6afe7677d3ecea1a9c358480d3fb33aa765cbb7ae43c414","target":"record","created_at":"2026-07-05T07:25:50Z","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":"77fab89cf75859b726a15ece8ba3796c86f2e6b3cbb6fe2fbe3f43b8309bc1c3","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-13T08:54:49Z","title_canon_sha256":"10fe26f5d464289c03790859042e80a0a3d6ce7127fe29be833c7c09e71d8bd4"},"schema_version":"1.0","source":{"id":"2312.11524","kind":"arxiv","version":1}},"canonical_sha256":"7e862f8a67add1c109eba768a9e195cde1fe9be2ce41f596dad3cf3f0ab5d4b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e862f8a67add1c109eba768a9e195cde1fe9be2ce41f596dad3cf3f0ab5d4b8","first_computed_at":"2026-07-05T07:25:50.819448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:50.819448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3HSRCMOZ1K7Fy0Vi+ZjFolt/+fJAcGtdLEspH12f7zHpKZUJSs65yD0LOcknIcoot9POg+XI2HZaJLseDhvMDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:50.819898Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.11524","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a234aff200d5d82c6afe7677d3ecea1a9c358480d3fb33aa765cbb7ae43c414","sha256:2f39dd23c40c8d7d58cc52a8c707a2c170729b6bef5cca48fc544db1f75b654d"],"state_sha256":"ca06a1ab835dd61a691ed90a4e10f4e4306db27885335a872333d97052795bb8"}