{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MYQXNQOV5H5G3CMHSXR4RURSSR","short_pith_number":"pith:MYQXNQOV","schema_version":"1.0","canonical_sha256":"662176c1d5e9fa6d898795e3c8d23294607ae9eebb9b50ece4df9bb905025b88","source":{"kind":"arxiv","id":"2508.16148","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Vision-Language Reasoning for Multimodal Multiple-Choice Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.IR","authors_text":"Ao Zhou, Jiawen Chen, Mingsheng Tu, Qing Gu, Tenghao Sun, Yafeng Yin, Zebo Gu, Zhiwei Jiang, Zifeng Cheng","submitted_at":"2025-08-22T07:17:16Z","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"},"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":"2508.16148","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-22T07:17:16Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"079f2ec3ff693fe834b3d2f7d807906271b9574576f613d8af5fce6469d54535","abstract_canon_sha256":"3a2c43bf48660d7fa9305b4e2884dcb550ff521db9aae31362604ced1e2eba5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:42.915709Z","signature_b64":"wDWphkQ9FxnxiUinFLPCsQ+NgSapej1lHrGNvQBoUW8c5JrIXsJQT4nviW67MHBANQ5KHT+HQUY9iINc7ZgLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"662176c1d5e9fa6d898795e3c8d23294607ae9eebb9b50ece4df9bb905025b88","last_reissued_at":"2026-07-05T11:57:42.915196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:42.915196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Vision-Language Reasoning for Multimodal Multiple-Choice Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.IR","authors_text":"Ao Zhou, Jiawen Chen, Mingsheng Tu, Qing Gu, Tenghao Sun, Yafeng Yin, Zebo Gu, Zhiwei Jiang, Zifeng Cheng","submitted_at":"2025-08-22T07:17:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16148","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/2508.16148/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":"2508.16148","created_at":"2026-07-05T11:57:42.915259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16148v1","created_at":"2026-07-05T11:57:42.915259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16148","created_at":"2026-07-05T11:57:42.915259+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYQXNQOV5H5G","created_at":"2026-07-05T11:57:42.915259+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYQXNQOV5H5G3CMH","created_at":"2026-07-05T11:57:42.915259+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYQXNQOV","created_at":"2026-07-05T11:57:42.915259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYQXNQOV5H5G3CMHSXR4RURSSR","json":"https://pith.science/pith/MYQXNQOV5H5G3CMHSXR4RURSSR.json","graph_json":"https://pith.science/api/pith-number/MYQXNQOV5H5G3CMHSXR4RURSSR/graph.json","events_json":"https://pith.science/api/pith-number/MYQXNQOV5H5G3CMHSXR4RURSSR/events.json","paper":"https://pith.science/paper/MYQXNQOV"},"agent_actions":{"view_html":"https://pith.science/pith/MYQXNQOV5H5G3CMHSXR4RURSSR","download_json":"https://pith.science/pith/MYQXNQOV5H5G3CMHSXR4RURSSR.json","view_paper":"https://pith.science/paper/MYQXNQOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16148&json=true","fetch_graph":"https://pith.science/api/pith-number/MYQXNQOV5H5G3CMHSXR4RURSSR/graph.json","fetch_events":"https://pith.science/api/pith-number/MYQXNQOV5H5G3CMHSXR4RURSSR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYQXNQOV5H5G3CMHSXR4RURSSR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYQXNQOV5H5G3CMHSXR4RURSSR/action/storage_attestation","attest_author":"https://pith.science/pith/MYQXNQOV5H5G3CMHSXR4RURSSR/action/author_attestation","sign_citation":"https://pith.science/pith/MYQXNQOV5H5G3CMHSXR4RURSSR/action/citation_signature","submit_replication":"https://pith.science/pith/MYQXNQOV5H5G3CMHSXR4RURSSR/action/replication_record"}},"created_at":"2026-07-05T11:57:42.915259+00:00","updated_at":"2026-07-05T11:57:42.915259+00:00"}