{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AV7JYU66SWLQ5QR7LUBD6T5EJN","short_pith_number":"pith:AV7JYU66","schema_version":"1.0","canonical_sha256":"057e9c53de95970ec23f5d023f4fa44b5216b3c72dcccec6aff711444e7a1abc","source":{"kind":"arxiv","id":"2501.01588","version":1},"attestation_state":"computed","paper":{"title":"(WhyPHI) Fine-Tuning PHI-3 for Multiple-Choice Question Answering: Methodology, Results, and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mohamed Hisham Abdellatif","submitted_at":"2025-01-03T00:56:46Z","abstract_excerpt":"Large Language Models (LLMs) have become essential tools across various domains due to their impressive capabilities in understanding and generating human-like text. The ability to accurately answer multiple-choice questions (MCQs) holds significant value in education, particularly in automated tutoring systems and assessment platforms. However, adapting LLMs to handle MCQ tasks effectively remains challenging due to the hallucinations and unclear prompts. This work explores the potential of Microsoft's PHI-3\\cite{Abdin2024}, a compact yet efficient LLM, for MCQ answering. Our contributions in"},"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":"2501.01588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-03T00:56:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0585a0d5eab0fc03c963970b8e840637f140e20fe740a0a21354d11256e39083","abstract_canon_sha256":"caa78b5e0d0356ef68f8bd2088260b7e712be27d9e31e665da12d0033281ebf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:27.182888Z","signature_b64":"kDdfsRD9dwOgdsZ6KY+HyG8s31+2bH0Qyb0VY0v6K/wgSKj6KXcxbQZMBK3Fr95o5mJiLT6H1pvPYb7W3ra4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"057e9c53de95970ec23f5d023f4fa44b5216b3c72dcccec6aff711444e7a1abc","last_reissued_at":"2026-07-05T09:56:27.182521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:27.182521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"(WhyPHI) Fine-Tuning PHI-3 for Multiple-Choice Question Answering: Methodology, Results, and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mohamed Hisham Abdellatif","submitted_at":"2025-01-03T00:56:46Z","abstract_excerpt":"Large Language Models (LLMs) have become essential tools across various domains due to their impressive capabilities in understanding and generating human-like text. The ability to accurately answer multiple-choice questions (MCQs) holds significant value in education, particularly in automated tutoring systems and assessment platforms. However, adapting LLMs to handle MCQ tasks effectively remains challenging due to the hallucinations and unclear prompts. This work explores the potential of Microsoft's PHI-3\\cite{Abdin2024}, a compact yet efficient LLM, for MCQ answering. Our contributions in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01588","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/2501.01588/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":"2501.01588","created_at":"2026-07-05T09:56:27.182576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01588v1","created_at":"2026-07-05T09:56:27.182576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01588","created_at":"2026-07-05T09:56:27.182576+00:00"},{"alias_kind":"pith_short_12","alias_value":"AV7JYU66SWLQ","created_at":"2026-07-05T09:56:27.182576+00:00"},{"alias_kind":"pith_short_16","alias_value":"AV7JYU66SWLQ5QR7","created_at":"2026-07-05T09:56:27.182576+00:00"},{"alias_kind":"pith_short_8","alias_value":"AV7JYU66","created_at":"2026-07-05T09:56:27.182576+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/AV7JYU66SWLQ5QR7LUBD6T5EJN","json":"https://pith.science/pith/AV7JYU66SWLQ5QR7LUBD6T5EJN.json","graph_json":"https://pith.science/api/pith-number/AV7JYU66SWLQ5QR7LUBD6T5EJN/graph.json","events_json":"https://pith.science/api/pith-number/AV7JYU66SWLQ5QR7LUBD6T5EJN/events.json","paper":"https://pith.science/paper/AV7JYU66"},"agent_actions":{"view_html":"https://pith.science/pith/AV7JYU66SWLQ5QR7LUBD6T5EJN","download_json":"https://pith.science/pith/AV7JYU66SWLQ5QR7LUBD6T5EJN.json","view_paper":"https://pith.science/paper/AV7JYU66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01588&json=true","fetch_graph":"https://pith.science/api/pith-number/AV7JYU66SWLQ5QR7LUBD6T5EJN/graph.json","fetch_events":"https://pith.science/api/pith-number/AV7JYU66SWLQ5QR7LUBD6T5EJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AV7JYU66SWLQ5QR7LUBD6T5EJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AV7JYU66SWLQ5QR7LUBD6T5EJN/action/storage_attestation","attest_author":"https://pith.science/pith/AV7JYU66SWLQ5QR7LUBD6T5EJN/action/author_attestation","sign_citation":"https://pith.science/pith/AV7JYU66SWLQ5QR7LUBD6T5EJN/action/citation_signature","submit_replication":"https://pith.science/pith/AV7JYU66SWLQ5QR7LUBD6T5EJN/action/replication_record"}},"created_at":"2026-07-05T09:56:27.182576+00:00","updated_at":"2026-07-05T09:56:27.182576+00:00"}