{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FAQQWUN2CLZJNHS7CHMAFPI2GS","short_pith_number":"pith:FAQQWUN2","schema_version":"1.0","canonical_sha256":"28210b51ba12f2969e5f11d802bd1a34aa9243f354172cca008b621243d41b77","source":{"kind":"arxiv","id":"2412.20956","version":1},"attestation_state":"computed","paper":{"title":"QuantumLLMInstruct: A 500k LLM Instruction-Tuning Dataset with Problem-Solution Pairs for Quantum Computing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"Shlomo Kashani","submitted_at":"2024-12-30T13:53:51Z","abstract_excerpt":"We present QuantumLLMInstruct (QLMMI), an innovative dataset featuring over 500,000 meticulously curated instruction-following problem-solution pairs designed specifically for quantum computing - the largest and most comprehensive dataset of its kind. Originating from over 90 primary seed domains and encompassing hundreds of subdomains autonomously generated by LLMs, QLMMI marks a transformative step in the diversity and richness of quantum computing datasets.\n  Designed for instruction fine-tuning, QLMMI seeks to significantly improve LLM performance in addressing complex quantum computing ch"},"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":"2412.20956","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2024-12-30T13:53:51Z","cross_cats_sorted":[],"title_canon_sha256":"7aa49f6f95bb2f681c1ff228b9ff63bb434c6baf790f0b30a94060747ce9c522","abstract_canon_sha256":"7029cb73b5e932bbf24a83930e44950e299cd7acabf0adb62b7895040c25b5e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:25.320561Z","signature_b64":"AZpY+sklQvDqkgY+1P22VSB6TDYA6yz0HrBLkEBH/Q63D+LOYxrfHmoEER19KK2zJfyrreY5chAStTU9VWw6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28210b51ba12f2969e5f11d802bd1a34aa9243f354172cca008b621243d41b77","last_reissued_at":"2026-07-05T09:55:25.319851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:25.319851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QuantumLLMInstruct: A 500k LLM Instruction-Tuning Dataset with Problem-Solution Pairs for Quantum Computing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"Shlomo Kashani","submitted_at":"2024-12-30T13:53:51Z","abstract_excerpt":"We present QuantumLLMInstruct (QLMMI), an innovative dataset featuring over 500,000 meticulously curated instruction-following problem-solution pairs designed specifically for quantum computing - the largest and most comprehensive dataset of its kind. Originating from over 90 primary seed domains and encompassing hundreds of subdomains autonomously generated by LLMs, QLMMI marks a transformative step in the diversity and richness of quantum computing datasets.\n  Designed for instruction fine-tuning, QLMMI seeks to significantly improve LLM performance in addressing complex quantum computing ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20956","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/2412.20956/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":"2412.20956","created_at":"2026-07-05T09:55:25.319932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20956v1","created_at":"2026-07-05T09:55:25.319932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20956","created_at":"2026-07-05T09:55:25.319932+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAQQWUN2CLZJ","created_at":"2026-07-05T09:55:25.319932+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAQQWUN2CLZJNHS7","created_at":"2026-07-05T09:55:25.319932+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAQQWUN2","created_at":"2026-07-05T09:55:25.319932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27210","citing_title":"Qiskit QuantumKatas: Adapting Microsoft's Quantum Computing exercises for LLM evaluation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18176","citing_title":"QuantumQA: Enhancing Scientific Reasoning via Physics-Consistent Dataset and Verification-Aware Reinforcement Learning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAQQWUN2CLZJNHS7CHMAFPI2GS","json":"https://pith.science/pith/FAQQWUN2CLZJNHS7CHMAFPI2GS.json","graph_json":"https://pith.science/api/pith-number/FAQQWUN2CLZJNHS7CHMAFPI2GS/graph.json","events_json":"https://pith.science/api/pith-number/FAQQWUN2CLZJNHS7CHMAFPI2GS/events.json","paper":"https://pith.science/paper/FAQQWUN2"},"agent_actions":{"view_html":"https://pith.science/pith/FAQQWUN2CLZJNHS7CHMAFPI2GS","download_json":"https://pith.science/pith/FAQQWUN2CLZJNHS7CHMAFPI2GS.json","view_paper":"https://pith.science/paper/FAQQWUN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20956&json=true","fetch_graph":"https://pith.science/api/pith-number/FAQQWUN2CLZJNHS7CHMAFPI2GS/graph.json","fetch_events":"https://pith.science/api/pith-number/FAQQWUN2CLZJNHS7CHMAFPI2GS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAQQWUN2CLZJNHS7CHMAFPI2GS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAQQWUN2CLZJNHS7CHMAFPI2GS/action/storage_attestation","attest_author":"https://pith.science/pith/FAQQWUN2CLZJNHS7CHMAFPI2GS/action/author_attestation","sign_citation":"https://pith.science/pith/FAQQWUN2CLZJNHS7CHMAFPI2GS/action/citation_signature","submit_replication":"https://pith.science/pith/FAQQWUN2CLZJNHS7CHMAFPI2GS/action/replication_record"}},"created_at":"2026-07-05T09:55:25.319932+00:00","updated_at":"2026-07-05T09:55:25.319932+00:00"}