{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BA4A4R3LSASUR23WFXUANXTB3X","short_pith_number":"pith:BA4A4R3L","schema_version":"1.0","canonical_sha256":"08380e476b902548eb762de806de61ddd79e53972602f001fda424dc699662d7","source":{"kind":"arxiv","id":"2307.12626","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bihui Yu, Cheng Tan, Jingxuan Wei, Linzhuang Sun, Ruifeng Guo, Siyuan Li, Stan Z. Li, Zhangyang Gao","submitted_at":"2023-07-24T08:58:25Z","abstract_excerpt":"Multimodal reasoning is a critical component in the pursuit of artificial intelligence systems that exhibit human-like intelligence, especially when tackling complex tasks. While the chain-of-thought (CoT) technique has gained considerable attention, the existing ScienceQA dataset, which focuses on multimodal scientific questions and explanations from elementary and high school textbooks, lacks a comprehensive evaluation of diverse approaches. To address this gap, we present COCO Multi-Modal Reasoning(COCO-MMR) dataset, a novel dataset that encompasses an extensive collection of open-ended que"},"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":"2307.12626","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-24T08:58:25Z","cross_cats_sorted":[],"title_canon_sha256":"26af31d71a87e6cbfd26feabcaaac18bc3f94d66a4c84d9cdd8eea4ab896fbbe","abstract_canon_sha256":"eb467bab1272d01b60a50edced96d9ab225aab49e2f20353fcc924e88997b407"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:42.359175Z","signature_b64":"u3AtQm4Z6+grOimky9ESsWrvlbMhAQQBGo+Tcg2B+zCMx+Up0tNv6l83emnn/d2aBiSwaAPrf5N23+eNx0wFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08380e476b902548eb762de806de61ddd79e53972602f001fda424dc699662d7","last_reissued_at":"2026-07-05T06:53:42.358704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:42.358704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bihui Yu, Cheng Tan, Jingxuan Wei, Linzhuang Sun, Ruifeng Guo, Siyuan Li, Stan Z. Li, Zhangyang Gao","submitted_at":"2023-07-24T08:58:25Z","abstract_excerpt":"Multimodal reasoning is a critical component in the pursuit of artificial intelligence systems that exhibit human-like intelligence, especially when tackling complex tasks. While the chain-of-thought (CoT) technique has gained considerable attention, the existing ScienceQA dataset, which focuses on multimodal scientific questions and explanations from elementary and high school textbooks, lacks a comprehensive evaluation of diverse approaches. To address this gap, we present COCO Multi-Modal Reasoning(COCO-MMR) dataset, a novel dataset that encompasses an extensive collection of open-ended que"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12626","kind":"arxiv","version":2},"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/2307.12626/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":"2307.12626","created_at":"2026-07-05T06:53:42.358763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12626v2","created_at":"2026-07-05T06:53:42.358763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12626","created_at":"2026-07-05T06:53:42.358763+00:00"},{"alias_kind":"pith_short_12","alias_value":"BA4A4R3LSASU","created_at":"2026-07-05T06:53:42.358763+00:00"},{"alias_kind":"pith_short_16","alias_value":"BA4A4R3LSASUR23W","created_at":"2026-07-05T06:53:42.358763+00:00"},{"alias_kind":"pith_short_8","alias_value":"BA4A4R3L","created_at":"2026-07-05T06:53:42.358763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00846","citing_title":"Improving Multimodal LLMs Ability In Geometry Problem Solving, Reasoning, And Multistep Scoring","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BA4A4R3LSASUR23WFXUANXTB3X","json":"https://pith.science/pith/BA4A4R3LSASUR23WFXUANXTB3X.json","graph_json":"https://pith.science/api/pith-number/BA4A4R3LSASUR23WFXUANXTB3X/graph.json","events_json":"https://pith.science/api/pith-number/BA4A4R3LSASUR23WFXUANXTB3X/events.json","paper":"https://pith.science/paper/BA4A4R3L"},"agent_actions":{"view_html":"https://pith.science/pith/BA4A4R3LSASUR23WFXUANXTB3X","download_json":"https://pith.science/pith/BA4A4R3LSASUR23WFXUANXTB3X.json","view_paper":"https://pith.science/paper/BA4A4R3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12626&json=true","fetch_graph":"https://pith.science/api/pith-number/BA4A4R3LSASUR23WFXUANXTB3X/graph.json","fetch_events":"https://pith.science/api/pith-number/BA4A4R3LSASUR23WFXUANXTB3X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BA4A4R3LSASUR23WFXUANXTB3X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BA4A4R3LSASUR23WFXUANXTB3X/action/storage_attestation","attest_author":"https://pith.science/pith/BA4A4R3LSASUR23WFXUANXTB3X/action/author_attestation","sign_citation":"https://pith.science/pith/BA4A4R3LSASUR23WFXUANXTB3X/action/citation_signature","submit_replication":"https://pith.science/pith/BA4A4R3LSASUR23WFXUANXTB3X/action/replication_record"}},"created_at":"2026-07-05T06:53:42.358763+00:00","updated_at":"2026-07-05T06:53:42.358763+00:00"}