{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U2VSZRDSZVULEMDJFOHYMB7ZNF","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":"cd31453986c3518b1ca4c94ec0b11a908918b018714f33e1c9710182d709a75d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T07:29:03Z","title_canon_sha256":"a8f9542d9b516ab208204f97fb8b445fe0f857fb02c8f849164d9524d0cbb715"},"schema_version":"1.0","source":{"id":"2503.02358","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02358","created_at":"2026-07-05T10:23:42Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02358v1","created_at":"2026-07-05T10:23:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02358","created_at":"2026-07-05T10:23:42Z"},{"alias_kind":"pith_short_12","alias_value":"U2VSZRDSZVUL","created_at":"2026-07-05T10:23:42Z"},{"alias_kind":"pith_short_16","alias_value":"U2VSZRDSZVULEMDJ","created_at":"2026-07-05T10:23:42Z"},{"alias_kind":"pith_short_8","alias_value":"U2VSZRDS","created_at":"2026-07-05T10:23:42Z"}],"graph_snapshots":[{"event_id":"sha256:10650680eb518ef2159b9322231b2dd1fc60b4447503615d95d099bcf19f7441","target":"graph","created_at":"2026-07-05T10:23:42Z","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/2503.02358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision Language Models (LVLMs) have demonstrated remarkable abilities in understanding and reasoning about both visual and textual information. However, existing evaluation methods for LVLMs, primarily based on benchmarks like Visual Question Answering and image captioning, often fail to capture the full scope of LVLMs' capabilities. These benchmarks are limited by issues such as inadequate assessment of detailed visual perception, data contamination, and a lack of focus on multi-turn reasoning. To address these challenges, we propose \\method{}, a game-based evaluation framework designed","authors_text":"Bohan Zhuang, Qi Wu, Xinyu Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T07:29:03Z","title":"Are Large Vision Language Models Good Game Players?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02358","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":"sha256:407aa11a8e4b20660348e805007f7b5cbd18d15a4241cd1fbb80df6f9265b532","target":"record","created_at":"2026-07-05T10:23:42Z","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":"cd31453986c3518b1ca4c94ec0b11a908918b018714f33e1c9710182d709a75d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T07:29:03Z","title_canon_sha256":"a8f9542d9b516ab208204f97fb8b445fe0f857fb02c8f849164d9524d0cbb715"},"schema_version":"1.0","source":{"id":"2503.02358","kind":"arxiv","version":1}},"canonical_sha256":"a6ab2cc472cd68b230692b8f8607f9695af7576cde90357862fd71c1740eabbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6ab2cc472cd68b230692b8f8607f9695af7576cde90357862fd71c1740eabbb","first_computed_at":"2026-07-05T10:23:42.185498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:42.185498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZvQQM9DdS3VeM+N79OrkXVGKxTClNDtlKjhCrmDUNmd/T9oFhY87/2W8MWdmk7JopHYAxGzN5anGJMHmjAHHBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:42.186008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.02358","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:407aa11a8e4b20660348e805007f7b5cbd18d15a4241cd1fbb80df6f9265b532","sha256:10650680eb518ef2159b9322231b2dd1fc60b4447503615d95d099bcf19f7441"],"state_sha256":"7b72843def857b43f49724e9d2879d0c16e18b676047b6f17cc866d649b8d40b"}