{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:P6GXCB25Q55TSK3KVMFFSDAHKV","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":"c53b2ca065b446d90a7fa475194d19a8b3c5d7e4719c8977b9ebcceb8639573e","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-29T15:57:49Z","title_canon_sha256":"596752597a8530ffa3df9d72d843776b8a8610aab09f2b2be818bfc5ff44ae91"},"schema_version":"1.0","source":{"id":"2312.17661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.17661","created_at":"2026-07-05T07:28:55Z"},{"alias_kind":"arxiv_version","alias_value":"2312.17661v1","created_at":"2026-07-05T07:28:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17661","created_at":"2026-07-05T07:28:55Z"},{"alias_kind":"pith_short_12","alias_value":"P6GXCB25Q55T","created_at":"2026-07-05T07:28:55Z"},{"alias_kind":"pith_short_16","alias_value":"P6GXCB25Q55TSK3K","created_at":"2026-07-05T07:28:55Z"},{"alias_kind":"pith_short_8","alias_value":"P6GXCB25","created_at":"2026-07-05T07:28:55Z"}],"graph_snapshots":[{"event_id":"sha256:aaefbb2a967ce9de3db7ee03f63e02595dea53c7d9d8e7e471bb74e503b17483","target":"graph","created_at":"2026-07-05T07:28:55Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.17661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The burgeoning interest in Multimodal Large Language Models (MLLMs), such as OpenAI's GPT-4V(ision), has significantly impacted both academic and industrial realms. These models enhance Large Language Models (LLMs) with advanced visual understanding capabilities, facilitating their application in a variety of multimodal tasks. Recently, Google introduced Gemini, a cutting-edge MLLM designed specifically for multimodal integration. Despite its advancements, preliminary benchmarks indicate that Gemini lags behind GPT models in commonsense reasoning tasks. However, this assessment, based on a lim","authors_text":"Yun Zhao, Yuqing Wang","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-29T15:57:49Z","title":"Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17661","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":"sha256:1a75799e11995023b9dcffbea591ea81c694825df301dbbac1a275120db4bfb4","target":"record","created_at":"2026-07-05T07:28:55Z","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":"c53b2ca065b446d90a7fa475194d19a8b3c5d7e4719c8977b9ebcceb8639573e","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-29T15:57:49Z","title_canon_sha256":"596752597a8530ffa3df9d72d843776b8a8610aab09f2b2be818bfc5ff44ae91"},"schema_version":"1.0","source":{"id":"2312.17661","kind":"arxiv","version":1}},"canonical_sha256":"7f8d71075d877b392b6aab0a590c07555a9ce461bd45229233eedaa6fb940e40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f8d71075d877b392b6aab0a590c07555a9ce461bd45229233eedaa6fb940e40","first_computed_at":"2026-07-05T07:28:55.048053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:55.048053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RSpr1GC6ISbJ9+C9om3gYQXio/yIEReB74+wgVZjR/Sh4lT/n/p8N38/duVwBThGlpA2Aik20i3F/Izz6vG5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:55.048609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.17661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a75799e11995023b9dcffbea591ea81c694825df301dbbac1a275120db4bfb4","sha256:aaefbb2a967ce9de3db7ee03f63e02595dea53c7d9d8e7e471bb74e503b17483"],"state_sha256":"72f18e96ed141c169a9a0c37c01ca55a01f5cf76ce724307ea6748b6c066fca3"}