{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MYQXNQOV5H5G3CMHSXR4RURSSR","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":"3a2c43bf48660d7fa9305b4e2884dcb550ff521db9aae31362604ced1e2eba5d","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-22T07:17:16Z","title_canon_sha256":"079f2ec3ff693fe834b3d2f7d807906271b9574576f613d8af5fce6469d54535"},"schema_version":"1.0","source":{"id":"2508.16148","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.16148","created_at":"2026-07-05T11:57:42Z"},{"alias_kind":"arxiv_version","alias_value":"2508.16148v1","created_at":"2026-07-05T11:57:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16148","created_at":"2026-07-05T11:57:42Z"},{"alias_kind":"pith_short_12","alias_value":"MYQXNQOV5H5G","created_at":"2026-07-05T11:57:42Z"},{"alias_kind":"pith_short_16","alias_value":"MYQXNQOV5H5G3CMH","created_at":"2026-07-05T11:57:42Z"},{"alias_kind":"pith_short_8","alias_value":"MYQXNQOV","created_at":"2026-07-05T11:57:42Z"}],"graph_snapshots":[{"event_id":"sha256:93207a391dbdffe8ddcc8e1b423cfab5cb98167e5b8e04c159dc58c0ccbf7049","target":"graph","created_at":"2026-07-05T11:57:42Z","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/2508.16148/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable multimodal understanding capabilities in Visual Question Answering (VQA) tasks by integrating visual and textual features. However, under the challenging ten-choice question evaluation paradigm, existing methods still exhibit significant limitations when processing PDF documents with complex layouts and lengthy content. Notably, current mainstream models suffer from a strong bias toward English training data, resulting in suboptimal performance for Japanese and other language scenarios. To address these challenges, this pape","authors_text":"Ao Zhou, Jiawen Chen, Mingsheng Tu, Qing Gu, Tenghao Sun, Yafeng Yin, Zebo Gu, Zhiwei Jiang, Zifeng Cheng","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-22T07:17:16Z","title":"Hierarchical Vision-Language Reasoning for Multimodal Multiple-Choice Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16148","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":"sha256:0e5859e3b9c85c0f5c2ff697700f92fa4cb6bd71cb607dbe7762734aed8a7099","target":"record","created_at":"2026-07-05T11:57:42Z","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":"3a2c43bf48660d7fa9305b4e2884dcb550ff521db9aae31362604ced1e2eba5d","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-22T07:17:16Z","title_canon_sha256":"079f2ec3ff693fe834b3d2f7d807906271b9574576f613d8af5fce6469d54535"},"schema_version":"1.0","source":{"id":"2508.16148","kind":"arxiv","version":1}},"canonical_sha256":"662176c1d5e9fa6d898795e3c8d23294607ae9eebb9b50ece4df9bb905025b88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"662176c1d5e9fa6d898795e3c8d23294607ae9eebb9b50ece4df9bb905025b88","first_computed_at":"2026-07-05T11:57:42.915196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:42.915196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wDWphkQ9FxnxiUinFLPCsQ+NgSapej1lHrGNvQBoUW8c5JrIXsJQT4nviW67MHBANQ5KHT+HQUY9iINc7ZgLDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:42.915709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.16148","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e5859e3b9c85c0f5c2ff697700f92fa4cb6bd71cb607dbe7762734aed8a7099","sha256:93207a391dbdffe8ddcc8e1b423cfab5cb98167e5b8e04c159dc58c0ccbf7049"],"state_sha256":"9d9be8b2c30a338b0f1824bb2626e9bb05a82a2c755d2ccc09c30efc8782f620"}