{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AWHMKWFPAYOXDYNPUZ55LCG43E","short_pith_number":"pith:AWHMKWFP","schema_version":"1.0","canonical_sha256":"058ec558af061d71e1afa67bd588dcd91d22fad4a2727cef5af9569a9734926c","source":{"kind":"arxiv","id":"2507.21520","version":1},"attestation_state":"computed","paper":{"title":"Solution for Meta KDD Cup'25: A Comprehensive Three-Step Framework for Vision Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Peng Yan, Xiaocheng Zhang, Yang Zhou, Zhimin Lin, Zijian Zhang","submitted_at":"2025-07-29T06:07:59Z","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"},"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":"2507.21520","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-29T06:07:59Z","cross_cats_sorted":[],"title_canon_sha256":"e331e2786438509755ad53fe8cc32a3decbfdc0928a497f0fd884dfb59b10838","abstract_canon_sha256":"c982183890c92d01e4c293e80c2d60a78f86a5ff2dfbe7aaa9d4604ed35a1e0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:01.650303Z","signature_b64":"jy+lKO07TAm+r5ilihUSWGodVTXnaSqGQcvkoDUrSB7tnYDOCGNrjxyEiowJPAnKRy3stb5Je3Unj6Xq4H7wBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"058ec558af061d71e1afa67bd588dcd91d22fad4a2727cef5af9569a9734926c","last_reissued_at":"2026-07-05T11:45:01.649729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:01.649729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solution for Meta KDD Cup'25: A Comprehensive Three-Step Framework for Vision Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Peng Yan, Xiaocheng Zhang, Yang Zhou, Zhimin Lin, Zijian Zhang","submitted_at":"2025-07-29T06:07:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21520","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/2507.21520/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":"2507.21520","created_at":"2026-07-05T11:45:01.649801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21520v1","created_at":"2026-07-05T11:45:01.649801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21520","created_at":"2026-07-05T11:45:01.649801+00:00"},{"alias_kind":"pith_short_12","alias_value":"AWHMKWFPAYOX","created_at":"2026-07-05T11:45:01.649801+00:00"},{"alias_kind":"pith_short_16","alias_value":"AWHMKWFPAYOXDYNP","created_at":"2026-07-05T11:45:01.649801+00:00"},{"alias_kind":"pith_short_8","alias_value":"AWHMKWFP","created_at":"2026-07-05T11:45:01.649801+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/AWHMKWFPAYOXDYNPUZ55LCG43E","json":"https://pith.science/pith/AWHMKWFPAYOXDYNPUZ55LCG43E.json","graph_json":"https://pith.science/api/pith-number/AWHMKWFPAYOXDYNPUZ55LCG43E/graph.json","events_json":"https://pith.science/api/pith-number/AWHMKWFPAYOXDYNPUZ55LCG43E/events.json","paper":"https://pith.science/paper/AWHMKWFP"},"agent_actions":{"view_html":"https://pith.science/pith/AWHMKWFPAYOXDYNPUZ55LCG43E","download_json":"https://pith.science/pith/AWHMKWFPAYOXDYNPUZ55LCG43E.json","view_paper":"https://pith.science/paper/AWHMKWFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21520&json=true","fetch_graph":"https://pith.science/api/pith-number/AWHMKWFPAYOXDYNPUZ55LCG43E/graph.json","fetch_events":"https://pith.science/api/pith-number/AWHMKWFPAYOXDYNPUZ55LCG43E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AWHMKWFPAYOXDYNPUZ55LCG43E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AWHMKWFPAYOXDYNPUZ55LCG43E/action/storage_attestation","attest_author":"https://pith.science/pith/AWHMKWFPAYOXDYNPUZ55LCG43E/action/author_attestation","sign_citation":"https://pith.science/pith/AWHMKWFPAYOXDYNPUZ55LCG43E/action/citation_signature","submit_replication":"https://pith.science/pith/AWHMKWFPAYOXDYNPUZ55LCG43E/action/replication_record"}},"created_at":"2026-07-05T11:45:01.649801+00:00","updated_at":"2026-07-05T11:45:01.649801+00:00"}