{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2IYX42NE2KOVPZG6E3VFIQE4AX","short_pith_number":"pith:2IYX42NE","schema_version":"1.0","canonical_sha256":"d2317e69a4d29d57e4de26ea54409c05ee300ed5f71c56cafdedb0755f7083d2","source":{"kind":"arxiv","id":"2503.01245","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Beiyu Lin, Nam Huynh","submitted_at":"2025-03-03T07:17:30Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated their remarkable capabilities in numerous fields. This survey focuses on how LLMs empower users, regardless of their technical background, to use human languages to automatically generate executable code. We begin with understanding LLMs' limitations and challenges in automated code generation. Subsequently, we review various fine-tuning techniques designed to enhance both the performance and adaptability of LLMs in code generation tasks. We then review the existing metrics and benchmarks for evaluations to assess model performance based on fine-t"},"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":"2503.01245","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-03T07:17:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ab51102960b88c147b5ba60f352431f5873b084137f652345d1256031b8bcf86","abstract_canon_sha256":"30a7d762feaa21e3d6591d921ea949a7b8e62955233cbf5910ba0f66459a427e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:26.529898Z","signature_b64":"b2psuFOp+/kZE40xg4yw/2M9XeEp25AFYonv2CgNg/8KU7TxcymvIqV/WbnPNre4vlkAZYF4q7RRQdgSGNgFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2317e69a4d29d57e4de26ea54409c05ee300ed5f71c56cafdedb0755f7083d2","last_reissued_at":"2026-07-05T10:43:26.529439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:26.529439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Beiyu Lin, Nam Huynh","submitted_at":"2025-03-03T07:17:30Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated their remarkable capabilities in numerous fields. This survey focuses on how LLMs empower users, regardless of their technical background, to use human languages to automatically generate executable code. We begin with understanding LLMs' limitations and challenges in automated code generation. Subsequently, we review various fine-tuning techniques designed to enhance both the performance and adaptability of LLMs in code generation tasks. We then review the existing metrics and benchmarks for evaluations to assess model performance based on fine-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01245","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/2503.01245/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":"2503.01245","created_at":"2026-07-05T10:43:26.529496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01245v2","created_at":"2026-07-05T10:43:26.529496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01245","created_at":"2026-07-05T10:43:26.529496+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IYX42NE2KOV","created_at":"2026-07-05T10:43:26.529496+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IYX42NE2KOVPZG6","created_at":"2026-07-05T10:43:26.529496+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IYX42NE","created_at":"2026-07-05T10:43:26.529496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24300","citing_title":"Enhancing Reliability in LLM-Based Secure Code Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26851","citing_title":"LLM-based Mockless Unit Test Generation for Java","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2601.05106","citing_title":"Token-Level LLM Collaboration via FusionRoute","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16299","citing_title":"ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16299","citing_title":"ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19353","citing_title":"Architectures of Error: A Philosophical Inquiry into AI and Human Code Generation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08980","citing_title":"AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22151","citing_title":"MultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14967","citing_title":"MermaidSeqBench: An Evaluation Benchmark for NL-to-Mermaid Sequence Diagram Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12794","citing_title":"A Rule-Aware Prompt Framework for Structured Numeric Reasoning in Cyber-Physical Systems","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16321","citing_title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2603.00989","citing_title":"Sustainable Code Generation Using Large Language Models: A Systematic Literature Review","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08553","citing_title":"VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00043","citing_title":"SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platforms","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2IYX42NE2KOVPZG6E3VFIQE4AX","json":"https://pith.science/pith/2IYX42NE2KOVPZG6E3VFIQE4AX.json","graph_json":"https://pith.science/api/pith-number/2IYX42NE2KOVPZG6E3VFIQE4AX/graph.json","events_json":"https://pith.science/api/pith-number/2IYX42NE2KOVPZG6E3VFIQE4AX/events.json","paper":"https://pith.science/paper/2IYX42NE"},"agent_actions":{"view_html":"https://pith.science/pith/2IYX42NE2KOVPZG6E3VFIQE4AX","download_json":"https://pith.science/pith/2IYX42NE2KOVPZG6E3VFIQE4AX.json","view_paper":"https://pith.science/paper/2IYX42NE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01245&json=true","fetch_graph":"https://pith.science/api/pith-number/2IYX42NE2KOVPZG6E3VFIQE4AX/graph.json","fetch_events":"https://pith.science/api/pith-number/2IYX42NE2KOVPZG6E3VFIQE4AX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IYX42NE2KOVPZG6E3VFIQE4AX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IYX42NE2KOVPZG6E3VFIQE4AX/action/storage_attestation","attest_author":"https://pith.science/pith/2IYX42NE2KOVPZG6E3VFIQE4AX/action/author_attestation","sign_citation":"https://pith.science/pith/2IYX42NE2KOVPZG6E3VFIQE4AX/action/citation_signature","submit_replication":"https://pith.science/pith/2IYX42NE2KOVPZG6E3VFIQE4AX/action/replication_record"}},"created_at":"2026-07-05T10:43:26.529496+00:00","updated_at":"2026-07-05T10:43:26.529496+00:00"}