{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XHMFQROYC74CH7Y5SKGN2QTSDZ","short_pith_number":"pith:XHMFQROY","schema_version":"1.0","canonical_sha256":"b9d85845d817f823ff1d928cdd42721e6a822a11d68482f390f5671f0d831b3e","source":{"kind":"arxiv","id":"2308.10620","version":6},"attestation_state":"computed","paper":{"title":"Large Language Models for Software Engineering: A Systematic Literature Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"David Lo, Haoyu Wang, John Grundy, Kailong Wang, Li Li, Xiapu Luo, Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang","submitted_at":"2023-08-21T10:37:49Z","abstract_excerpt":"Large Language Models (LLMs) have significantly impacted numerous domains, including Software Engineering (SE). Many recent publications have explored LLMs applied to various SE tasks. Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages. To bridge this gap, we conducted a systematic literature review (SLR) on LLM4SE, with a particular focus on understanding how LLMs can be exploited to optimize processes and outcomes. We select and analyze 395 research papers from January 2017 to January 2024 to answer fou"},"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":"2308.10620","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-08-21T10:37:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"11c24abc8b83ce51719615fd53783b2bdeecac82aa2cd63a7d67a9957dac2acf","abstract_canon_sha256":"481282f021554d8fdd5f111971226c3d6df4c169fd36d927607a97be8dac99fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:24.604463Z","signature_b64":"xNwhrXJbsXiisoEstlWtW2C8Ti7lIsfm2u3wYHJdydYLYHlRPtPXx+pdevmBzd6gMYwEF9vpjtVlRuTW2iqsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9d85845d817f823ff1d928cdd42721e6a822a11d68482f390f5671f0d831b3e","last_reissued_at":"2026-07-05T08:06:24.603955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:24.603955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models for Software Engineering: A Systematic Literature Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"David Lo, Haoyu Wang, John Grundy, Kailong Wang, Li Li, Xiapu Luo, Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang","submitted_at":"2023-08-21T10:37:49Z","abstract_excerpt":"Large Language Models (LLMs) have significantly impacted numerous domains, including Software Engineering (SE). Many recent publications have explored LLMs applied to various SE tasks. Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages. To bridge this gap, we conducted a systematic literature review (SLR) on LLM4SE, with a particular focus on understanding how LLMs can be exploited to optimize processes and outcomes. We select and analyze 395 research papers from January 2017 to January 2024 to answer fou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10620","kind":"arxiv","version":6},"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/2308.10620/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":"2308.10620","created_at":"2026-07-05T08:06:24.604014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10620v6","created_at":"2026-07-05T08:06:24.604014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10620","created_at":"2026-07-05T08:06:24.604014+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHMFQROYC74C","created_at":"2026-07-05T08:06:24.604014+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHMFQROYC74CH7Y5","created_at":"2026-07-05T08:06:24.604014+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHMFQROY","created_at":"2026-07-05T08:06:24.604014+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06337","citing_title":"TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04769","citing_title":"Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security Implications","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04273","citing_title":"Characterizing initial human-AI proof formalization workflows","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24298","citing_title":"An Empirical Evaluation of LLM-Generated Code Security Across Prompting Methods","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27601","citing_title":"Test Case Selection for Deep Neural Networks: A Replication Study on LLMs for Code","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10106","citing_title":"What makes a harness a harness: necessary and sufficient conditions for an agent harness","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20173","citing_title":"Qiskit Code Migration with LLMs","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2305.12138","citing_title":"Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2402.01411","citing_title":"CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01055","citing_title":"Towards Agentic Runtime Healing","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2505.07700","citing_title":"PatchTrack: A Comprehensive Analysis of ChatGPT's Influence on Pull Request Outcomes","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22534","citing_title":"Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2508.16771","citing_title":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04572","citing_title":"From Competition to Collaboration: Designing Sustainable Mechanisms Between LLMs and Online Forums","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08915","citing_title":"Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.06276","citing_title":"Story Point Estimation Using Large Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14362","citing_title":"Correctness-Aware Repository Filtering Under Maximum Effective Context Window Constraints","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19173","citing_title":"StarCoder 2 and The Stack v2: The Next Generation","ref_index":214,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26923","citing_title":"ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26523","citing_title":"RepoDoc: A Knowledge Graph-Based Framework to Automatic Documentation Generation and Incremental Updates","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13103","citing_title":"Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05753","citing_title":"An End-to-End Approach for Fixing Concurrency Bugs via SHB-Based Context Extractor","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14550","citing_title":"VeriGraphi: A Multi-Agent Framework of Hierarchical RTL Generation for Large Hardware Designs","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17763","citing_title":"A Quasi-Experimental Developer Study of Security Training in LLM-Assisted Web Application Development","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHMFQROYC74CH7Y5SKGN2QTSDZ","json":"https://pith.science/pith/XHMFQROYC74CH7Y5SKGN2QTSDZ.json","graph_json":"https://pith.science/api/pith-number/XHMFQROYC74CH7Y5SKGN2QTSDZ/graph.json","events_json":"https://pith.science/api/pith-number/XHMFQROYC74CH7Y5SKGN2QTSDZ/events.json","paper":"https://pith.science/paper/XHMFQROY"},"agent_actions":{"view_html":"https://pith.science/pith/XHMFQROYC74CH7Y5SKGN2QTSDZ","download_json":"https://pith.science/pith/XHMFQROYC74CH7Y5SKGN2QTSDZ.json","view_paper":"https://pith.science/paper/XHMFQROY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10620&json=true","fetch_graph":"https://pith.science/api/pith-number/XHMFQROYC74CH7Y5SKGN2QTSDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XHMFQROYC74CH7Y5SKGN2QTSDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHMFQROYC74CH7Y5SKGN2QTSDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHMFQROYC74CH7Y5SKGN2QTSDZ/action/storage_attestation","attest_author":"https://pith.science/pith/XHMFQROYC74CH7Y5SKGN2QTSDZ/action/author_attestation","sign_citation":"https://pith.science/pith/XHMFQROYC74CH7Y5SKGN2QTSDZ/action/citation_signature","submit_replication":"https://pith.science/pith/XHMFQROYC74CH7Y5SKGN2QTSDZ/action/replication_record"}},"created_at":"2026-07-05T08:06:24.604014+00:00","updated_at":"2026-07-05T08:06:24.604014+00:00"}