{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SSI44MJSXBGKFQCP5GXNHWSKNM","short_pith_number":"pith:SSI44MJS","schema_version":"1.0","canonical_sha256":"9491ce3132b84ca2c04fe9aed3da4a6b3e8a666f141d6044c931e05aacdb7172","source":{"kind":"arxiv","id":"2408.04645","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Impact of Advanced LLM Techniques on AI-Lecture Tutors for a Robotics Course","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.RO"],"primary_cat":"cs.CL","authors_text":"Christopher Burgahn, Fabian Ridder, Felix L\\\"offler, Jennifer Spanagel, Jens Wienkamp, Malte Schilling, Marius Schmitz, Martin Maciol, Sebastian Kahl","submitted_at":"2024-08-02T19:49:19Z","abstract_excerpt":"This study evaluates the performance of Large Language Models (LLMs) as an Artificial Intelligence-based tutor for a university course. In particular, different advanced techniques are utilized, such as prompt engineering, Retrieval-Augmented-Generation (RAG), and fine-tuning. We assessed the different models and applied techniques using common similarity metrics like BLEU-4, ROUGE, and BERTScore, complemented by a small human evaluation of helpfulness and trustworthiness. Our findings indicate that RAG combined with prompt engineering significantly enhances model responses and produces better"},"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":"2408.04645","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-02T19:49:19Z","cross_cats_sorted":["cs.AI","cs.CY","cs.RO"],"title_canon_sha256":"c9e0214a305f049622846e970846ba74986f22929e39a2830ab35b1a0feb0b0f","abstract_canon_sha256":"41ab16a1e2ed8bc084285cc7fee70a9ca00e7fa77c1cbd52d1170ffd014b75f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:41.820160Z","signature_b64":"7ki8TiUCu2K61WIQsb3AgsILOv0HjUBbXToYCTs/a3FsZJiZQSkIgntAqxR7lhaSqAPdddiTw40QeOianeDFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9491ce3132b84ca2c04fe9aed3da4a6b3e8a666f141d6044c931e05aacdb7172","last_reissued_at":"2026-07-05T08:53:41.819724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:41.819724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Impact of Advanced LLM Techniques on AI-Lecture Tutors for a Robotics Course","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.RO"],"primary_cat":"cs.CL","authors_text":"Christopher Burgahn, Fabian Ridder, Felix L\\\"offler, Jennifer Spanagel, Jens Wienkamp, Malte Schilling, Marius Schmitz, Martin Maciol, Sebastian Kahl","submitted_at":"2024-08-02T19:49:19Z","abstract_excerpt":"This study evaluates the performance of Large Language Models (LLMs) as an Artificial Intelligence-based tutor for a university course. In particular, different advanced techniques are utilized, such as prompt engineering, Retrieval-Augmented-Generation (RAG), and fine-tuning. We assessed the different models and applied techniques using common similarity metrics like BLEU-4, ROUGE, and BERTScore, complemented by a small human evaluation of helpfulness and trustworthiness. Our findings indicate that RAG combined with prompt engineering significantly enhances model responses and produces better"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04645","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/2408.04645/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":"2408.04645","created_at":"2026-07-05T08:53:41.819793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04645v1","created_at":"2026-07-05T08:53:41.819793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04645","created_at":"2026-07-05T08:53:41.819793+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSI44MJSXBGK","created_at":"2026-07-05T08:53:41.819793+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSI44MJSXBGKFQCP","created_at":"2026-07-05T08:53:41.819793+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSI44MJS","created_at":"2026-07-05T08:53:41.819793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17056","citing_title":"The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SSI44MJSXBGKFQCP5GXNHWSKNM","json":"https://pith.science/pith/SSI44MJSXBGKFQCP5GXNHWSKNM.json","graph_json":"https://pith.science/api/pith-number/SSI44MJSXBGKFQCP5GXNHWSKNM/graph.json","events_json":"https://pith.science/api/pith-number/SSI44MJSXBGKFQCP5GXNHWSKNM/events.json","paper":"https://pith.science/paper/SSI44MJS"},"agent_actions":{"view_html":"https://pith.science/pith/SSI44MJSXBGKFQCP5GXNHWSKNM","download_json":"https://pith.science/pith/SSI44MJSXBGKFQCP5GXNHWSKNM.json","view_paper":"https://pith.science/paper/SSI44MJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04645&json=true","fetch_graph":"https://pith.science/api/pith-number/SSI44MJSXBGKFQCP5GXNHWSKNM/graph.json","fetch_events":"https://pith.science/api/pith-number/SSI44MJSXBGKFQCP5GXNHWSKNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSI44MJSXBGKFQCP5GXNHWSKNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSI44MJSXBGKFQCP5GXNHWSKNM/action/storage_attestation","attest_author":"https://pith.science/pith/SSI44MJSXBGKFQCP5GXNHWSKNM/action/author_attestation","sign_citation":"https://pith.science/pith/SSI44MJSXBGKFQCP5GXNHWSKNM/action/citation_signature","submit_replication":"https://pith.science/pith/SSI44MJSXBGKFQCP5GXNHWSKNM/action/replication_record"}},"created_at":"2026-07-05T08:53:41.819793+00:00","updated_at":"2026-07-05T08:53:41.819793+00:00"}