{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AWHMKWFPAYOXDYNPUZ55LCG43E","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":"c982183890c92d01e4c293e80c2d60a78f86a5ff2dfbe7aaa9d4604ed35a1e0f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-29T06:07:59Z","title_canon_sha256":"e331e2786438509755ad53fe8cc32a3decbfdc0928a497f0fd884dfb59b10838"},"schema_version":"1.0","source":{"id":"2507.21520","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21520","created_at":"2026-07-05T11:45:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21520v1","created_at":"2026-07-05T11:45:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21520","created_at":"2026-07-05T11:45:01Z"},{"alias_kind":"pith_short_12","alias_value":"AWHMKWFPAYOX","created_at":"2026-07-05T11:45:01Z"},{"alias_kind":"pith_short_16","alias_value":"AWHMKWFPAYOXDYNP","created_at":"2026-07-05T11:45:01Z"},{"alias_kind":"pith_short_8","alias_value":"AWHMKWFP","created_at":"2026-07-05T11:45:01Z"}],"graph_snapshots":[{"event_id":"sha256:1d8b0173ddd4fee868729e5fb9624a318ba2f70b88cd970d31ed43375ca67c2b","target":"graph","created_at":"2026-07-05T11:45:01Z","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/2507.21520/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Large Language Models (VLLMs) have improved multi-modal understanding and visual question answering (VQA), but still suffer from hallucinated answers. Multi-modal Retrieval-Augmented Generation (RAG) helps address these issues by incorporating external information, yet challenges remain in visual context comprehension, multi-source retrieval, and multi-turn interactions. To address these challenges, Meta constructed the CRAG-MM benchmark and launched the CRAG-MM Challenge at KDD Cup 2025, which consists of three tasks. This paper describes the solutions of all tasks in Meta KDD Cup'25 f","authors_text":"Peng Yan, Xiaocheng Zhang, Yang Zhou, Zhimin Lin, Zijian Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-29T06:07:59Z","title":"Solution for Meta KDD Cup'25: A Comprehensive Three-Step Framework for Vision Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21520","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":"sha256:569508fbd7dc9028558e95fb87851322d53ede062c250c9934801c63c18fdfe0","target":"record","created_at":"2026-07-05T11:45:01Z","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":"c982183890c92d01e4c293e80c2d60a78f86a5ff2dfbe7aaa9d4604ed35a1e0f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-29T06:07:59Z","title_canon_sha256":"e331e2786438509755ad53fe8cc32a3decbfdc0928a497f0fd884dfb59b10838"},"schema_version":"1.0","source":{"id":"2507.21520","kind":"arxiv","version":1}},"canonical_sha256":"058ec558af061d71e1afa67bd588dcd91d22fad4a2727cef5af9569a9734926c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"058ec558af061d71e1afa67bd588dcd91d22fad4a2727cef5af9569a9734926c","first_computed_at":"2026-07-05T11:45:01.649729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:01.649729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jy+lKO07TAm+r5ilihUSWGodVTXnaSqGQcvkoDUrSB7tnYDOCGNrjxyEiowJPAnKRy3stb5Je3Unj6Xq4H7wBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:01.650303Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21520","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:569508fbd7dc9028558e95fb87851322d53ede062c250c9934801c63c18fdfe0","sha256:1d8b0173ddd4fee868729e5fb9624a318ba2f70b88cd970d31ed43375ca67c2b"],"state_sha256":"c9c47eb557ad290e90f2c5485a14c633a86a16681bf6cf6c4d484d6fe712f6f8"}