{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HGLNEGE6643TJTUSBB5XKC4Q23","short_pith_number":"pith:HGLNEGE6","schema_version":"1.0","canonical_sha256":"3996d2189ef73734ce92087b750b90d6ca5dcf11ed69c1ef430e2f5fd57e4f3a","source":{"kind":"arxiv","id":"2306.08568","version":2},"attestation_state":"computed","paper":{"title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Can Xu, Chongyang Tao, Daxin Jiang, Jing Ma, Pu Zhao, Qingfeng Sun, Qingwei Lin, Wenxiang Hu, Xiubo Geng, Ziyang Luo","submitted_at":"2023-06-14T15:18:48Z","abstract_excerpt":"Code Large Language Models (Code LLMs), such as StarCoder, have demonstrated exceptional performance in code-related tasks. However, most existing models are solely pre-trained on extensive raw code data without instruction fine-tuning. In this paper, we introduce WizardCoder, which empowers Code LLMs with complex instruction fine-tuning, by adapting the Evol-Instruct method to the domain of code. Through comprehensive experiments on four prominent code generation benchmarks, namely HumanEval, HumanEval+, MBPP, and DS-1000, we unveil the exceptional capabilities of our model. It surpasses all "},"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":"2306.08568","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-14T15:18:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35981c93fff9174666b1739ac0baa0093458a862d8a9fe0b3d7d5cc527568caf","abstract_canon_sha256":"e8be5acd8df6ed1a35be3a28c36ccf304ab43932083b697e00fc641fc7cd79ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:56.889540Z","signature_b64":"ngeC7l+fDsDah8h6DFCCzdvWPxe+ddtAsSI18is/HkaaLWh/8DDgz7dpG/VRUdZ4yGAKlWDEc05WXqObi/UCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3996d2189ef73734ce92087b750b90d6ca5dcf11ed69c1ef430e2f5fd57e4f3a","last_reissued_at":"2026-07-05T11:09:56.889051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:56.889051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Can Xu, Chongyang Tao, Daxin Jiang, Jing Ma, Pu Zhao, Qingfeng Sun, Qingwei Lin, Wenxiang Hu, Xiubo Geng, Ziyang Luo","submitted_at":"2023-06-14T15:18:48Z","abstract_excerpt":"Code Large Language Models (Code LLMs), such as StarCoder, have demonstrated exceptional performance in code-related tasks. However, most existing models are solely pre-trained on extensive raw code data without instruction fine-tuning. In this paper, we introduce WizardCoder, which empowers Code LLMs with complex instruction fine-tuning, by adapting the Evol-Instruct method to the domain of code. Through comprehensive experiments on four prominent code generation benchmarks, namely HumanEval, HumanEval+, MBPP, and DS-1000, we unveil the exceptional capabilities of our model. It surpasses all "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08568","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/2306.08568/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":"2306.08568","created_at":"2026-07-05T11:09:56.889106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.08568v2","created_at":"2026-07-05T11:09:56.889106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08568","created_at":"2026-07-05T11:09:56.889106+00:00"},{"alias_kind":"pith_short_12","alias_value":"HGLNEGE6643T","created_at":"2026-07-05T11:09:56.889106+00:00"},{"alias_kind":"pith_short_16","alias_value":"HGLNEGE6643TJTUS","created_at":"2026-07-05T11:09:56.889106+00:00"},{"alias_kind":"pith_short_8","alias_value":"HGLNEGE6","created_at":"2026-07-05T11:09:56.889106+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":34,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2607.08011","citing_title":"Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2607.07480","citing_title":"Biased or Personalized? The Impact of Personal Information on AI-driven Development","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05842","citing_title":"Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24549","citing_title":"FirmCure:Towards Autonomous and Adaptive Rehosting of Linux-Based Firmware","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01789","citing_title":"EPnG: Adaptive Expert Prune-and-Grow for Parameter-Efficient MoE Fine-tuning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10385","citing_title":"Beyond Absolute Imitation: Anchored Residual Guidance for Privileged On-Policy Distillation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06826","citing_title":"SkelDPO: A Skeleton-Guided Direct Preference Optimization Framework for Efficient Code Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01286","citing_title":"BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24079","citing_title":"TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28998","citing_title":"Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29155","citing_title":"OASIF: An Efficient Obfuscation-Aware Self-Improving Framework for LLM-Based Assembly Code Instruction Following and Comprehension","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25835","citing_title":"Context-Instrumental Data Distillation for Kubernetes Manifest Generation: Method and Experimental Evaluation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26302","citing_title":"Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08676","citing_title":"Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2408.15815","citing_title":"MR-Adopt: Automatic Deduction of Input Transformation Function for Metamorphic Testing","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2411.10656","citing_title":"Precision or Peril: A PoC of Python Code Quality from Quantized Large Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08167","citing_title":"Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18829","citing_title":"Lossless Anti-Distillation Sampling","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18073","citing_title":"A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2601.00376","citing_title":"In Line with Context: Repository-Level Code Generation via Context Inlining","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02602","citing_title":"SWaRL: Safeguard Code Watermarking via Reinforcement Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2311.16867","citing_title":"The Falcon Series of Open Language Models","ref_index":182,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18449","citing_title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HGLNEGE6643TJTUSBB5XKC4Q23","json":"https://pith.science/pith/HGLNEGE6643TJTUSBB5XKC4Q23.json","graph_json":"https://pith.science/api/pith-number/HGLNEGE6643TJTUSBB5XKC4Q23/graph.json","events_json":"https://pith.science/api/pith-number/HGLNEGE6643TJTUSBB5XKC4Q23/events.json","paper":"https://pith.science/paper/HGLNEGE6"},"agent_actions":{"view_html":"https://pith.science/pith/HGLNEGE6643TJTUSBB5XKC4Q23","download_json":"https://pith.science/pith/HGLNEGE6643TJTUSBB5XKC4Q23.json","view_paper":"https://pith.science/paper/HGLNEGE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.08568&json=true","fetch_graph":"https://pith.science/api/pith-number/HGLNEGE6643TJTUSBB5XKC4Q23/graph.json","fetch_events":"https://pith.science/api/pith-number/HGLNEGE6643TJTUSBB5XKC4Q23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HGLNEGE6643TJTUSBB5XKC4Q23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HGLNEGE6643TJTUSBB5XKC4Q23/action/storage_attestation","attest_author":"https://pith.science/pith/HGLNEGE6643TJTUSBB5XKC4Q23/action/author_attestation","sign_citation":"https://pith.science/pith/HGLNEGE6643TJTUSBB5XKC4Q23/action/citation_signature","submit_replication":"https://pith.science/pith/HGLNEGE6643TJTUSBB5XKC4Q23/action/replication_record"}},"created_at":"2026-07-05T11:09:56.889106+00:00","updated_at":"2026-07-05T11:09:56.889106+00:00"}