{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UNP6HTOB45Q23XVSG6QPLMKQEN","short_pith_number":"pith:UNP6HTOB","schema_version":"1.0","canonical_sha256":"a35fe3cdc1e761addeb237a0f5b15023514396deb82070abd6d21ebe8b762edf","source":{"kind":"arxiv","id":"2506.20008","version":2},"attestation_state":"computed","paper":{"title":"QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL","cs.SE"],"primary_cat":"cs.AI","authors_text":"Abdul Basit, Alberto Marchisio, Minghao Shao, Muhammad Haider Asif, Muhammad Kashif, Muhammad Shafique, Nouhaila Innan","submitted_at":"2025-06-24T20:54:56Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have demonstrated strong potential in code generation, yet their effectiveness in quantum computing remains underexplored. This paper benchmarks LLMs for PennyLane-based quantum code generation using real-world challenges from the Quantum Hackathon (QHack). We introduce QHackBench, a novel benchmark dataset derived from QHack competitions, and evaluate model performance under vanilla prompting and Retrieval-Augmented Generation (RAG). Our structured evaluation framework assesses functional correctness, syntactic validity, and execution success ac"},"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":"2506.20008","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-24T20:54:56Z","cross_cats_sorted":["cs.PL","cs.SE"],"title_canon_sha256":"ced76dc3529673379bf22a4d2cf3d729774ddec7975909f77b1a5e4249de4416","abstract_canon_sha256":"e6ec50284fb61e9200021dfd2da9532cb6459e0a209771ace7479c082335c40d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:24.313091Z","signature_b64":"Ga7uJdoWM1H7gpkfEMVLGk48xzcPUvWPPuypk3WGAkFwGuSSChxiwvRvyz4HGqt0rMr4IHt/9pfIND1YiRYTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a35fe3cdc1e761addeb237a0f5b15023514396deb82070abd6d21ebe8b762edf","last_reissued_at":"2026-07-05T12:01:24.312587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:24.312587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL","cs.SE"],"primary_cat":"cs.AI","authors_text":"Abdul Basit, Alberto Marchisio, Minghao Shao, Muhammad Haider Asif, Muhammad Kashif, Muhammad Shafique, Nouhaila Innan","submitted_at":"2025-06-24T20:54:56Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have demonstrated strong potential in code generation, yet their effectiveness in quantum computing remains underexplored. This paper benchmarks LLMs for PennyLane-based quantum code generation using real-world challenges from the Quantum Hackathon (QHack). We introduce QHackBench, a novel benchmark dataset derived from QHack competitions, and evaluate model performance under vanilla prompting and Retrieval-Augmented Generation (RAG). Our structured evaluation framework assesses functional correctness, syntactic validity, and execution success ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20008","kind":"arxiv","version":2},"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/2506.20008/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":"2506.20008","created_at":"2026-07-05T12:01:24.312646+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20008v2","created_at":"2026-07-05T12:01:24.312646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20008","created_at":"2026-07-05T12:01:24.312646+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNP6HTOB45Q2","created_at":"2026-07-05T12:01:24.312646+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNP6HTOB45Q23XVS","created_at":"2026-07-05T12:01:24.312646+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNP6HTOB","created_at":"2026-07-05T12:01:24.312646+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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21287","citing_title":"StabilizerBench: A Benchmark for AI-Assisted Quantum Error Correction Circuit Synthesis","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNP6HTOB45Q23XVSG6QPLMKQEN","json":"https://pith.science/pith/UNP6HTOB45Q23XVSG6QPLMKQEN.json","graph_json":"https://pith.science/api/pith-number/UNP6HTOB45Q23XVSG6QPLMKQEN/graph.json","events_json":"https://pith.science/api/pith-number/UNP6HTOB45Q23XVSG6QPLMKQEN/events.json","paper":"https://pith.science/paper/UNP6HTOB"},"agent_actions":{"view_html":"https://pith.science/pith/UNP6HTOB45Q23XVSG6QPLMKQEN","download_json":"https://pith.science/pith/UNP6HTOB45Q23XVSG6QPLMKQEN.json","view_paper":"https://pith.science/paper/UNP6HTOB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20008&json=true","fetch_graph":"https://pith.science/api/pith-number/UNP6HTOB45Q23XVSG6QPLMKQEN/graph.json","fetch_events":"https://pith.science/api/pith-number/UNP6HTOB45Q23XVSG6QPLMKQEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNP6HTOB45Q23XVSG6QPLMKQEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNP6HTOB45Q23XVSG6QPLMKQEN/action/storage_attestation","attest_author":"https://pith.science/pith/UNP6HTOB45Q23XVSG6QPLMKQEN/action/author_attestation","sign_citation":"https://pith.science/pith/UNP6HTOB45Q23XVSG6QPLMKQEN/action/citation_signature","submit_replication":"https://pith.science/pith/UNP6HTOB45Q23XVSG6QPLMKQEN/action/replication_record"}},"created_at":"2026-07-05T12:01:24.312646+00:00","updated_at":"2026-07-05T12:01:24.312646+00:00"}