{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P6GXCB25Q55TSK3KVMFFSDAHKV","short_pith_number":"pith:P6GXCB25","schema_version":"1.0","canonical_sha256":"7f8d71075d877b392b6aab0a590c07555a9ce461bd45229233eedaa6fb940e40","source":{"kind":"arxiv","id":"2312.17661","version":1},"attestation_state":"computed","paper":{"title":"Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Yun Zhao, Yuqing Wang","submitted_at":"2023-12-29T15:57:49Z","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"},"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":"2312.17661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-29T15:57:49Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"596752597a8530ffa3df9d72d843776b8a8610aab09f2b2be818bfc5ff44ae91","abstract_canon_sha256":"c53b2ca065b446d90a7fa475194d19a8b3c5d7e4719c8977b9ebcceb8639573e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:55.048609Z","signature_b64":"RSpr1GC6ISbJ9+C9om3gYQXio/yIEReB74+wgVZjR/Sh4lT/n/p8N38/duVwBThGlpA2Aik20i3F/Izz6vG5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f8d71075d877b392b6aab0a590c07555a9ce461bd45229233eedaa6fb940e40","last_reissued_at":"2026-07-05T07:28:55.048053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:55.048053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Yun Zhao, Yuqing Wang","submitted_at":"2023-12-29T15:57:49Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17661","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/2312.17661/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":"2312.17661","created_at":"2026-07-05T07:28:55.048114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17661v1","created_at":"2026-07-05T07:28:55.048114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17661","created_at":"2026-07-05T07:28:55.048114+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6GXCB25Q55T","created_at":"2026-07-05T07:28:55.048114+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6GXCB25Q55TSK3K","created_at":"2026-07-05T07:28:55.048114+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6GXCB25","created_at":"2026-07-05T07:28:55.048114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":249,"is_internal_anchor":false},{"citing_arxiv_id":"2405.19088","citing_title":"Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2503.23137","citing_title":"When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6GXCB25Q55TSK3KVMFFSDAHKV","json":"https://pith.science/pith/P6GXCB25Q55TSK3KVMFFSDAHKV.json","graph_json":"https://pith.science/api/pith-number/P6GXCB25Q55TSK3KVMFFSDAHKV/graph.json","events_json":"https://pith.science/api/pith-number/P6GXCB25Q55TSK3KVMFFSDAHKV/events.json","paper":"https://pith.science/paper/P6GXCB25"},"agent_actions":{"view_html":"https://pith.science/pith/P6GXCB25Q55TSK3KVMFFSDAHKV","download_json":"https://pith.science/pith/P6GXCB25Q55TSK3KVMFFSDAHKV.json","view_paper":"https://pith.science/paper/P6GXCB25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17661&json=true","fetch_graph":"https://pith.science/api/pith-number/P6GXCB25Q55TSK3KVMFFSDAHKV/graph.json","fetch_events":"https://pith.science/api/pith-number/P6GXCB25Q55TSK3KVMFFSDAHKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6GXCB25Q55TSK3KVMFFSDAHKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6GXCB25Q55TSK3KVMFFSDAHKV/action/storage_attestation","attest_author":"https://pith.science/pith/P6GXCB25Q55TSK3KVMFFSDAHKV/action/author_attestation","sign_citation":"https://pith.science/pith/P6GXCB25Q55TSK3KVMFFSDAHKV/action/citation_signature","submit_replication":"https://pith.science/pith/P6GXCB25Q55TSK3KVMFFSDAHKV/action/replication_record"}},"created_at":"2026-07-05T07:28:55.048114+00:00","updated_at":"2026-07-05T07:28:55.048114+00:00"}