{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:URFJNYM6EJHCTESF35YYDTUGFD","short_pith_number":"pith:URFJNYM6","schema_version":"1.0","canonical_sha256":"a44a96e19e224e299245df7181ce8628f12d5660ccc68a52241e1005a56d2f9b","source":{"kind":"arxiv","id":"2509.07846","version":1},"attestation_state":"computed","paper":{"title":"Aligning LLMs for the Classroom with Knowledge-Based Retrieval -- A Comparative RAG Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amay Jain, Liu Cui, Si Chen","submitted_at":"2025-09-09T15:22:33Z","abstract_excerpt":"Large language models like ChatGPT are increasingly used in classrooms, but they often provide outdated or fabricated information that can mislead students. Retrieval Augmented Generation (RAG) improves reliability of LLMs by grounding responses in external resources. We investigate two accessible RAG paradigms, vector-based retrieval and graph-based retrieval to identify best practices for classroom question answering (QA). Existing comparative studies fail to account for pedagogical factors such as educational disciplines, question types, and practical deployment costs. Using a novel dataset"},"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":"2509.07846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-09T15:22:33Z","cross_cats_sorted":[],"title_canon_sha256":"d49ab6f711aa41c89701dd9f03c48a976203ffd91fd6996c9bafbb0558c46411","abstract_canon_sha256":"11e5af9ae0aa2d43ab9bfdacb359643429f21402a8dbd4c59e738ff48e76da9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:40.995183Z","signature_b64":"Y1PhHg7ikhKAxmDqVcRpm6ipimy8JQNn9u9vf1VfvHgeruXSz4K469P4xzP+zwvCLjq2Hid+whlktj2cnn0qBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a44a96e19e224e299245df7181ce8628f12d5660ccc68a52241e1005a56d2f9b","last_reissued_at":"2026-07-05T12:07:40.994683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:40.994683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning LLMs for the Classroom with Knowledge-Based Retrieval -- A Comparative RAG Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amay Jain, Liu Cui, Si Chen","submitted_at":"2025-09-09T15:22:33Z","abstract_excerpt":"Large language models like ChatGPT are increasingly used in classrooms, but they often provide outdated or fabricated information that can mislead students. Retrieval Augmented Generation (RAG) improves reliability of LLMs by grounding responses in external resources. We investigate two accessible RAG paradigms, vector-based retrieval and graph-based retrieval to identify best practices for classroom question answering (QA). Existing comparative studies fail to account for pedagogical factors such as educational disciplines, question types, and practical deployment costs. Using a novel dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07846","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/2509.07846/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":"2509.07846","created_at":"2026-07-05T12:07:40.994735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.07846v1","created_at":"2026-07-05T12:07:40.994735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07846","created_at":"2026-07-05T12:07:40.994735+00:00"},{"alias_kind":"pith_short_12","alias_value":"URFJNYM6EJHC","created_at":"2026-07-05T12:07:40.994735+00:00"},{"alias_kind":"pith_short_16","alias_value":"URFJNYM6EJHCTESF","created_at":"2026-07-05T12:07:40.994735+00:00"},{"alias_kind":"pith_short_8","alias_value":"URFJNYM6","created_at":"2026-07-05T12:07:40.994735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02452","citing_title":"Position: How can Graphs Help Large Language Models?","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/URFJNYM6EJHCTESF35YYDTUGFD","json":"https://pith.science/pith/URFJNYM6EJHCTESF35YYDTUGFD.json","graph_json":"https://pith.science/api/pith-number/URFJNYM6EJHCTESF35YYDTUGFD/graph.json","events_json":"https://pith.science/api/pith-number/URFJNYM6EJHCTESF35YYDTUGFD/events.json","paper":"https://pith.science/paper/URFJNYM6"},"agent_actions":{"view_html":"https://pith.science/pith/URFJNYM6EJHCTESF35YYDTUGFD","download_json":"https://pith.science/pith/URFJNYM6EJHCTESF35YYDTUGFD.json","view_paper":"https://pith.science/paper/URFJNYM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.07846&json=true","fetch_graph":"https://pith.science/api/pith-number/URFJNYM6EJHCTESF35YYDTUGFD/graph.json","fetch_events":"https://pith.science/api/pith-number/URFJNYM6EJHCTESF35YYDTUGFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URFJNYM6EJHCTESF35YYDTUGFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URFJNYM6EJHCTESF35YYDTUGFD/action/storage_attestation","attest_author":"https://pith.science/pith/URFJNYM6EJHCTESF35YYDTUGFD/action/author_attestation","sign_citation":"https://pith.science/pith/URFJNYM6EJHCTESF35YYDTUGFD/action/citation_signature","submit_replication":"https://pith.science/pith/URFJNYM6EJHCTESF35YYDTUGFD/action/replication_record"}},"created_at":"2026-07-05T12:07:40.994735+00:00","updated_at":"2026-07-05T12:07:40.994735+00:00"}