{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZKZ5O6AOUOAHA323IQ5TQEZICX","short_pith_number":"pith:ZKZ5O6AO","schema_version":"1.0","canonical_sha256":"cab3d7780ea380706f5b443b38132815ca44aa95683f339c9263071d7b203a80","source":{"kind":"arxiv","id":"2502.15604","version":1},"attestation_state":"computed","paper":{"title":"Cross-Format Retrieval-Augmented Generation in XR with LLMs for Context-Aware Maintenance Assistance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.IR","authors_text":"Akos Nagy, Vasileios Argyriou, Yannis Spyridis","submitted_at":"2025-02-21T17:19:39Z","abstract_excerpt":"This paper presents a detailed evaluation of a Retrieval-Augmented Generation (RAG) system that integrates large language models (LLMs) to enhance information retrieval and instruction generation for maintenance personnel across diverse data formats. We assessed the performance of eight LLMs, emphasizing key metrics such as response speed and accuracy, which were quantified using BLEU and METEOR scores. Our findings reveal that advanced models like GPT-4 and GPT-4o-mini significantly outperform their counterparts, particularly when addressing complex queries requiring multi-format data integra"},"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":"2502.15604","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-21T17:19:39Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"995b2f1c18f2bd1ac131bf11a6296c093eeac424eacc277fd79eca552ac8196e","abstract_canon_sha256":"2a8303c38a310cbfd8128f1b28c11ab705b314e5ecba8e4ca44c59f93dde2729"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:07.259340Z","signature_b64":"4rQgFJDWv5JWMiSzJEqeRNtQrnhkFe8vIc9enFDFfqYndMpLQf+cwFN7ZdOA5CHTBr42CkdiQauxv++evcRxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cab3d7780ea380706f5b443b38132815ca44aa95683f339c9263071d7b203a80","last_reissued_at":"2026-07-05T10:21:07.258702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:07.258702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Format Retrieval-Augmented Generation in XR with LLMs for Context-Aware Maintenance Assistance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.IR","authors_text":"Akos Nagy, Vasileios Argyriou, Yannis Spyridis","submitted_at":"2025-02-21T17:19:39Z","abstract_excerpt":"This paper presents a detailed evaluation of a Retrieval-Augmented Generation (RAG) system that integrates large language models (LLMs) to enhance information retrieval and instruction generation for maintenance personnel across diverse data formats. We assessed the performance of eight LLMs, emphasizing key metrics such as response speed and accuracy, which were quantified using BLEU and METEOR scores. Our findings reveal that advanced models like GPT-4 and GPT-4o-mini significantly outperform their counterparts, particularly when addressing complex queries requiring multi-format data integra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15604","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/2502.15604/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":"2502.15604","created_at":"2026-07-05T10:21:07.258778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15604v1","created_at":"2026-07-05T10:21:07.258778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15604","created_at":"2026-07-05T10:21:07.258778+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKZ5O6AOUOAH","created_at":"2026-07-05T10:21:07.258778+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKZ5O6AOUOAHA323","created_at":"2026-07-05T10:21:07.258778+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKZ5O6AO","created_at":"2026-07-05T10:21:07.258778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.07861","citing_title":"How Much Does It Cost to Answer My Question? Benchmarking Cloud VLM-based VQA Systems","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKZ5O6AOUOAHA323IQ5TQEZICX","json":"https://pith.science/pith/ZKZ5O6AOUOAHA323IQ5TQEZICX.json","graph_json":"https://pith.science/api/pith-number/ZKZ5O6AOUOAHA323IQ5TQEZICX/graph.json","events_json":"https://pith.science/api/pith-number/ZKZ5O6AOUOAHA323IQ5TQEZICX/events.json","paper":"https://pith.science/paper/ZKZ5O6AO"},"agent_actions":{"view_html":"https://pith.science/pith/ZKZ5O6AOUOAHA323IQ5TQEZICX","download_json":"https://pith.science/pith/ZKZ5O6AOUOAHA323IQ5TQEZICX.json","view_paper":"https://pith.science/paper/ZKZ5O6AO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15604&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKZ5O6AOUOAHA323IQ5TQEZICX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKZ5O6AOUOAHA323IQ5TQEZICX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKZ5O6AOUOAHA323IQ5TQEZICX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKZ5O6AOUOAHA323IQ5TQEZICX/action/storage_attestation","attest_author":"https://pith.science/pith/ZKZ5O6AOUOAHA323IQ5TQEZICX/action/author_attestation","sign_citation":"https://pith.science/pith/ZKZ5O6AOUOAHA323IQ5TQEZICX/action/citation_signature","submit_replication":"https://pith.science/pith/ZKZ5O6AOUOAHA323IQ5TQEZICX/action/replication_record"}},"created_at":"2026-07-05T10:21:07.258778+00:00","updated_at":"2026-07-05T10:21:07.258778+00:00"}