{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LQG2DQIMQ2Y3QEVBIZVKHJKDRW","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":"1cdf1d5fc1dd0217cd2c8bfbbb353bf2508ad3674e896ac1d410da0e2ef06b68","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T04:01:43Z","title_canon_sha256":"4a37c56268c03e9f9ab8dc6bfc7001f43ffca1f74c1c6b0effdd853c30d0d2b9"},"schema_version":"1.0","source":{"id":"2502.16428","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.16428","created_at":"2026-07-05T10:18:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.16428v1","created_at":"2026-07-05T10:18:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16428","created_at":"2026-07-05T10:18:53Z"},{"alias_kind":"pith_short_12","alias_value":"LQG2DQIMQ2Y3","created_at":"2026-07-05T10:18:53Z"},{"alias_kind":"pith_short_16","alias_value":"LQG2DQIMQ2Y3QEVB","created_at":"2026-07-05T10:18:53Z"},{"alias_kind":"pith_short_8","alias_value":"LQG2DQIM","created_at":"2026-07-05T10:18:53Z"}],"graph_snapshots":[{"event_id":"sha256:a62cd82211f31ea2a4765564845faa57fd7c0459bf3a8edcc033bc0a63372f78","target":"graph","created_at":"2026-07-05T10:18:53Z","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/2502.16428/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abdeltawab Hendawi, Marwan Abdelatti, Nidhal Jegham","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T04:01:43Z","title":"Visual Reasoning Evaluation of Grok, Deepseek Janus, Gemini, Qwen, Mistral, and ChatGPT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16428","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":"sha256:188ef0317300e3f33615ff649a3fbeef99f0e714167dd53201c1bddf88923306","target":"record","created_at":"2026-07-05T10:18:53Z","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":"1cdf1d5fc1dd0217cd2c8bfbbb353bf2508ad3674e896ac1d410da0e2ef06b68","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T04:01:43Z","title_canon_sha256":"4a37c56268c03e9f9ab8dc6bfc7001f43ffca1f74c1c6b0effdd853c30d0d2b9"},"schema_version":"1.0","source":{"id":"2502.16428","kind":"arxiv","version":1}},"canonical_sha256":"5c0da1c10c86b1b812a1466aa3a5438db99057f14bbfe86ac44650ce6f9eacae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c0da1c10c86b1b812a1466aa3a5438db99057f14bbfe86ac44650ce6f9eacae","first_computed_at":"2026-07-05T10:18:53.392723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:53.392723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"86nSUdyjn6AKhsTN4KZou5VUp0IJEriQ7HWtRrNd4UWP2SNdSZOYBOIZDDozsacBzZz6HzEfarf6dqpTxwU6DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:53.393193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.16428","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:188ef0317300e3f33615ff649a3fbeef99f0e714167dd53201c1bddf88923306","sha256:a62cd82211f31ea2a4765564845faa57fd7c0459bf3a8edcc033bc0a63372f78"],"state_sha256":"5f67d4ff565296627e86f673369cd62ca31d8008fea1e883c7bae0f60f9d3c98"}