{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6S5MQX62SD26LRFUNUIWLCHRD5","short_pith_number":"pith:6S5MQX62","schema_version":"1.0","canonical_sha256":"f4bac85fda90f5e5c4b46d116588f11f69cf289b8e291475d81b1f4009bcefb7","source":{"kind":"arxiv","id":"2411.08438","version":1},"attestation_state":"computed","paper":{"title":"Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andrei Staradubets, Anum Afzal, Florian Matthes, Gentrit Fazlija, Juraj Vladika","submitted_at":"2024-11-13T08:43:37Z","abstract_excerpt":"Given the growing trend of many organizations integrating Retrieval Augmented Generation (RAG) into their operations, we assess RAG on domain-specific data and test state-of-the-art models across various optimization techniques. We incorporate four optimizations; Multi-Query, Child-Parent-Retriever, Ensemble Retriever, and In-Context-Learning, to enhance the functionality and performance in the academic domain. We focus on data retrieval, specifically targeting various study programs at a large technical university. We additionally introduce a novel evaluation approach, the RAG Confusion Matri"},"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":"2411.08438","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-13T08:43:37Z","cross_cats_sorted":[],"title_canon_sha256":"229ad4844b8a6587b4e39021de46ccf01c3aaa9339cfb8e386a8584f384ce60e","abstract_canon_sha256":"2edefb564000d35fd46fd7aa303babbaa73193c98473bbf0287375c7827fea6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:47.565031Z","signature_b64":"vX1vUbQuPyRD3fn520EMRSiFHnDTl2cqOzdulNEqhBqwQTr4dzzOxHW0Go8y5IbVI884iqTT6JhFHWoX1ZCkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4bac85fda90f5e5c4b46d116588f11f69cf289b8e291475d81b1f4009bcefb7","last_reissued_at":"2026-07-05T09:34:47.564554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:47.564554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andrei Staradubets, Anum Afzal, Florian Matthes, Gentrit Fazlija, Juraj Vladika","submitted_at":"2024-11-13T08:43:37Z","abstract_excerpt":"Given the growing trend of many organizations integrating Retrieval Augmented Generation (RAG) into their operations, we assess RAG on domain-specific data and test state-of-the-art models across various optimization techniques. We incorporate four optimizations; Multi-Query, Child-Parent-Retriever, Ensemble Retriever, and In-Context-Learning, to enhance the functionality and performance in the academic domain. We focus on data retrieval, specifically targeting various study programs at a large technical university. We additionally introduce a novel evaluation approach, the RAG Confusion Matri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08438","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/2411.08438/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":"2411.08438","created_at":"2026-07-05T09:34:47.564619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.08438v1","created_at":"2026-07-05T09:34:47.564619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08438","created_at":"2026-07-05T09:34:47.564619+00:00"},{"alias_kind":"pith_short_12","alias_value":"6S5MQX62SD26","created_at":"2026-07-05T09:34:47.564619+00:00"},{"alias_kind":"pith_short_16","alias_value":"6S5MQX62SD26LRFU","created_at":"2026-07-05T09:34:47.564619+00:00"},{"alias_kind":"pith_short_8","alias_value":"6S5MQX62","created_at":"2026-07-05T09:34:47.564619+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/6S5MQX62SD26LRFUNUIWLCHRD5","json":"https://pith.science/pith/6S5MQX62SD26LRFUNUIWLCHRD5.json","graph_json":"https://pith.science/api/pith-number/6S5MQX62SD26LRFUNUIWLCHRD5/graph.json","events_json":"https://pith.science/api/pith-number/6S5MQX62SD26LRFUNUIWLCHRD5/events.json","paper":"https://pith.science/paper/6S5MQX62"},"agent_actions":{"view_html":"https://pith.science/pith/6S5MQX62SD26LRFUNUIWLCHRD5","download_json":"https://pith.science/pith/6S5MQX62SD26LRFUNUIWLCHRD5.json","view_paper":"https://pith.science/paper/6S5MQX62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.08438&json=true","fetch_graph":"https://pith.science/api/pith-number/6S5MQX62SD26LRFUNUIWLCHRD5/graph.json","fetch_events":"https://pith.science/api/pith-number/6S5MQX62SD26LRFUNUIWLCHRD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6S5MQX62SD26LRFUNUIWLCHRD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6S5MQX62SD26LRFUNUIWLCHRD5/action/storage_attestation","attest_author":"https://pith.science/pith/6S5MQX62SD26LRFUNUIWLCHRD5/action/author_attestation","sign_citation":"https://pith.science/pith/6S5MQX62SD26LRFUNUIWLCHRD5/action/citation_signature","submit_replication":"https://pith.science/pith/6S5MQX62SD26LRFUNUIWLCHRD5/action/replication_record"}},"created_at":"2026-07-05T09:34:47.564619+00:00","updated_at":"2026-07-05T09:34:47.564619+00:00"}