{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LQG2DQIMQ2Y3QEVBIZVKHJKDRW","short_pith_number":"pith:LQG2DQIM","schema_version":"1.0","canonical_sha256":"5c0da1c10c86b1b812a1466aa3a5438db99057f14bbfe86ac44650ce6f9eacae","source":{"kind":"arxiv","id":"2502.16428","version":1},"attestation_state":"computed","paper":{"title":"Visual Reasoning Evaluation of Grok, Deepseek Janus, Gemini, Qwen, Mistral, and ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abdeltawab Hendawi, Marwan Abdelatti, Nidhal Jegham","submitted_at":"2025-02-23T04:01:43Z","abstract_excerpt":"Traditional evaluations of multimodal large language models (LLMs) have been limited by their focus on single-image reasoning, failing to assess crucial aspects like contextual understanding, reasoning stability, and uncertainty calibration. This study addresses these limitations by introducing a novel benchmark that integrates multi-image reasoning tasks with rejection-based evaluation and positional bias detection. To evaluate these dimensions, we further introduce entropy as a novel metric for quantifying reasoning consistency across reordered answer variants. We applied this benchmark to a"},"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":"2502.16428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T04:01:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4a37c56268c03e9f9ab8dc6bfc7001f43ffca1f74c1c6b0effdd853c30d0d2b9","abstract_canon_sha256":"1cdf1d5fc1dd0217cd2c8bfbbb353bf2508ad3674e896ac1d410da0e2ef06b68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:53.393193Z","signature_b64":"86nSUdyjn6AKhsTN4KZou5VUp0IJEriQ7HWtRrNd4UWP2SNdSZOYBOIZDDozsacBzZz6HzEfarf6dqpTxwU6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c0da1c10c86b1b812a1466aa3a5438db99057f14bbfe86ac44650ce6f9eacae","last_reissued_at":"2026-07-05T10:18:53.392723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:53.392723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Reasoning Evaluation of Grok, Deepseek Janus, Gemini, Qwen, Mistral, and ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abdeltawab Hendawi, Marwan Abdelatti, Nidhal Jegham","submitted_at":"2025-02-23T04:01:43Z","abstract_excerpt":"Traditional evaluations of multimodal large language models (LLMs) have been limited by their focus on single-image reasoning, failing to assess crucial aspects like contextual understanding, reasoning stability, and uncertainty calibration. This study addresses these limitations by introducing a novel benchmark that integrates multi-image reasoning tasks with rejection-based evaluation and positional bias detection. To evaluate these dimensions, we further introduce entropy as a novel metric for quantifying reasoning consistency across reordered answer variants. We applied this benchmark to a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16428","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/2502.16428/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":"2502.16428","created_at":"2026-07-05T10:18:53.392775+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16428v1","created_at":"2026-07-05T10:18:53.392775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16428","created_at":"2026-07-05T10:18:53.392775+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQG2DQIMQ2Y3","created_at":"2026-07-05T10:18:53.392775+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQG2DQIMQ2Y3QEVB","created_at":"2026-07-05T10:18:53.392775+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQG2DQIM","created_at":"2026-07-05T10:18:53.392775+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.06907","citing_title":"A Survey on Foundation Models for Personalized Federated Intelligence","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20646","citing_title":"DisImpact: Quantifying the Physi-Social Impact of Natural Disasters Through Social Media","ref_index":133,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQG2DQIMQ2Y3QEVBIZVKHJKDRW","json":"https://pith.science/pith/LQG2DQIMQ2Y3QEVBIZVKHJKDRW.json","graph_json":"https://pith.science/api/pith-number/LQG2DQIMQ2Y3QEVBIZVKHJKDRW/graph.json","events_json":"https://pith.science/api/pith-number/LQG2DQIMQ2Y3QEVBIZVKHJKDRW/events.json","paper":"https://pith.science/paper/LQG2DQIM"},"agent_actions":{"view_html":"https://pith.science/pith/LQG2DQIMQ2Y3QEVBIZVKHJKDRW","download_json":"https://pith.science/pith/LQG2DQIMQ2Y3QEVBIZVKHJKDRW.json","view_paper":"https://pith.science/paper/LQG2DQIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16428&json=true","fetch_graph":"https://pith.science/api/pith-number/LQG2DQIMQ2Y3QEVBIZVKHJKDRW/graph.json","fetch_events":"https://pith.science/api/pith-number/LQG2DQIMQ2Y3QEVBIZVKHJKDRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQG2DQIMQ2Y3QEVBIZVKHJKDRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQG2DQIMQ2Y3QEVBIZVKHJKDRW/action/storage_attestation","attest_author":"https://pith.science/pith/LQG2DQIMQ2Y3QEVBIZVKHJKDRW/action/author_attestation","sign_citation":"https://pith.science/pith/LQG2DQIMQ2Y3QEVBIZVKHJKDRW/action/citation_signature","submit_replication":"https://pith.science/pith/LQG2DQIMQ2Y3QEVBIZVKHJKDRW/action/replication_record"}},"created_at":"2026-07-05T10:18:53.392775+00:00","updated_at":"2026-07-05T10:18:53.392775+00:00"}