{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RU2YHXYV3WXTANXGAMGM7O7KGU","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":"93f9d67238d23937538561cfb267da3c486bc8f5f9981f6bc6760cc38ce5ef1d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-28T11:25:38Z","title_canon_sha256":"5557e461b03afe5abc63612c13c3aa65c0376e237da826e3adb0fb7e7ccf04cd"},"schema_version":"1.0","source":{"id":"2502.20964","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20964","created_at":"2026-07-05T11:33:20Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20964v3","created_at":"2026-07-05T11:33:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20964","created_at":"2026-07-05T11:33:20Z"},{"alias_kind":"pith_short_12","alias_value":"RU2YHXYV3WXT","created_at":"2026-07-05T11:33:20Z"},{"alias_kind":"pith_short_16","alias_value":"RU2YHXYV3WXTANXG","created_at":"2026-07-05T11:33:20Z"},{"alias_kind":"pith_short_8","alias_value":"RU2YHXYV","created_at":"2026-07-05T11:33:20Z"}],"graph_snapshots":[{"event_id":"sha256:ff4e8e35e8443bd677a47e6c1730a113a98cafaf3099265b53395b84572d0d5f","target":"graph","created_at":"2026-07-05T11:33:20Z","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/2502.20964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Question Answering (VQA) focuses on providing answers to natural language questions by utilizing information from images. Although cutting-edge multimodal large language models (MLLMs) such as GPT-4o achieve strong performance on VQA tasks, they frequently fall short in accessing domain-specific or the latest knowledge. To mitigate this issue, retrieval-augmented generation (RAG) leveraging external knowledge bases (KBs), referred to as KB-VQA, emerges as a promising approach. Nevertheless, conventional unimodal retrieval techniques, which translate images into textual descriptions, oft","authors_text":"Nan Tang, Yin Wu, Yuyu Luo, Zhengxuan Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-28T11:25:38Z","title":"Fine-Grained Knowledge Structuring and Retrieval for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20964","kind":"arxiv","version":3},"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":"sha256:40e5d2c8506d783c03977d770ee039f2217d2e0cf20e6f0cabf274ef886496ec","target":"record","created_at":"2026-07-05T11:33:20Z","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":"93f9d67238d23937538561cfb267da3c486bc8f5f9981f6bc6760cc38ce5ef1d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-28T11:25:38Z","title_canon_sha256":"5557e461b03afe5abc63612c13c3aa65c0376e237da826e3adb0fb7e7ccf04cd"},"schema_version":"1.0","source":{"id":"2502.20964","kind":"arxiv","version":3}},"canonical_sha256":"8d3583df15ddaf3036e6030ccfbbea3511ed55c272e10ef5f91e1f90f56dc8c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d3583df15ddaf3036e6030ccfbbea3511ed55c272e10ef5f91e1f90f56dc8c3","first_computed_at":"2026-07-05T11:33:20.837024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:20.837024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"evbOcBKaJZhqsIC55KMZD2DIu5hLvxaH+cd6BD9lA1KMSL3aIyq//l57Izmhy9LbzG0rvHvUU/KA2pWUl+txDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:20.837518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20964","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40e5d2c8506d783c03977d770ee039f2217d2e0cf20e6f0cabf274ef886496ec","sha256:ff4e8e35e8443bd677a47e6c1730a113a98cafaf3099265b53395b84572d0d5f"],"state_sha256":"877f7731c41141ad1f40c93b9aeb5573e650d62324307b887a7a06ab2ebd6cd8"}