{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GQNJSKUQGRZZFLEUSRON75PWKR","short_pith_number":"pith:GQNJSKUQ","schema_version":"1.0","canonical_sha256":"341a992a90347392ac94945cdff5f65456a90d2e304a980385552a2a8cca69c8","source":{"kind":"arxiv","id":"2501.13880","version":1},"attestation_state":"computed","paper":{"title":"A RAG-Based Institutional Assistant","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fabio G. Cozman, Gustavo Kuratomi, Paulo Pirozelli, Sarajane M. Peres","submitted_at":"2025-01-23T17:54:19Z","abstract_excerpt":"Although large language models (LLMs) demonstrate strong text generation capabilities, they struggle in scenarios requiring access to structured knowledge bases or specific documents, limiting their effectiveness in knowledge-intensive tasks. To address this limitation, retrieval-augmented generation (RAG) models have been developed, enabling generative models to incorporate relevant document fragments into their inputs. In this paper, we design and evaluate a RAG-based virtual assistant specifically tailored for the University of S\\~ao Paulo. Our system architecture comprises two key modules:"},"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":"2501.13880","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T17:54:19Z","cross_cats_sorted":[],"title_canon_sha256":"7e19245251477b714b2968758b1075d96c9bead9377d90934940f96449b3628f","abstract_canon_sha256":"d8e347f555990705756798c87b384a2820f5ec574a8a0b7d0ee7986ad3e15519"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:35.613620Z","signature_b64":"ShOBNzP0hGVwEZ7Y9+3k6cKtstkQnySO1DXp95N7kyrqIRYTtS2NNXiTZjBAfE2DIp57xyrBNk58u6YCYfRPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"341a992a90347392ac94945cdff5f65456a90d2e304a980385552a2a8cca69c8","last_reissued_at":"2026-07-05T10:04:35.613266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:35.613266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A RAG-Based Institutional Assistant","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fabio G. Cozman, Gustavo Kuratomi, Paulo Pirozelli, Sarajane M. Peres","submitted_at":"2025-01-23T17:54:19Z","abstract_excerpt":"Although large language models (LLMs) demonstrate strong text generation capabilities, they struggle in scenarios requiring access to structured knowledge bases or specific documents, limiting their effectiveness in knowledge-intensive tasks. To address this limitation, retrieval-augmented generation (RAG) models have been developed, enabling generative models to incorporate relevant document fragments into their inputs. In this paper, we design and evaluate a RAG-based virtual assistant specifically tailored for the University of S\\~ao Paulo. Our system architecture comprises two key modules:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13880","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/2501.13880/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":"2501.13880","created_at":"2026-07-05T10:04:35.613324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13880v1","created_at":"2026-07-05T10:04:35.613324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13880","created_at":"2026-07-05T10:04:35.613324+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQNJSKUQGRZZ","created_at":"2026-07-05T10:04:35.613324+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQNJSKUQGRZZFLEU","created_at":"2026-07-05T10:04:35.613324+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQNJSKUQ","created_at":"2026-07-05T10:04:35.613324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21024","citing_title":"An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEs","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR","json":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR.json","graph_json":"https://pith.science/api/pith-number/GQNJSKUQGRZZFLEUSRON75PWKR/graph.json","events_json":"https://pith.science/api/pith-number/GQNJSKUQGRZZFLEUSRON75PWKR/events.json","paper":"https://pith.science/paper/GQNJSKUQ"},"agent_actions":{"view_html":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR","download_json":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR.json","view_paper":"https://pith.science/paper/GQNJSKUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13880&json=true","fetch_graph":"https://pith.science/api/pith-number/GQNJSKUQGRZZFLEUSRON75PWKR/graph.json","fetch_events":"https://pith.science/api/pith-number/GQNJSKUQGRZZFLEUSRON75PWKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR/action/storage_attestation","attest_author":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR/action/author_attestation","sign_citation":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR/action/citation_signature","submit_replication":"https://pith.science/pith/GQNJSKUQGRZZFLEUSRON75PWKR/action/replication_record"}},"created_at":"2026-07-05T10:04:35.613324+00:00","updated_at":"2026-07-05T10:04:35.613324+00:00"}