{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GWFFKZG7DS3CD5XI7IDO2MV35H","short_pith_number":"pith:GWFFKZG7","schema_version":"1.0","canonical_sha256":"358a5564df1cb621f6e8fa06ed32bbe9c11020641011213dd4f01a425a1d942e","source":{"kind":"arxiv","id":"2312.15223","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Large Language Models for Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chunrong Fang, Quanjun Zhang, Shengcheng Yu, Weisong Sun, Yang Xie, Yaxin Zhang, Yun Yang, Zhenyu Chen","submitted_at":"2023-12-23T11:09:40Z","abstract_excerpt":"Software Engineering (SE) is the systematic design, development, maintenance, and management of software applications underpinning the digital infrastructure of our modern world. Very recently, the SE community has seen a rapidly increasing number of techniques employing Large Language Models (LLMs) to automate a broad range of SE tasks. Nevertheless, existing information of the applications, effects, and possible limitations of LLMs within SE is still not well-studied.\n  In this paper, we provide a systematic survey to summarize the current state-of-the-art research in the LLM-based SE commun"},"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":"2312.15223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-12-23T11:09:40Z","cross_cats_sorted":[],"title_canon_sha256":"2fe85bef1845f62c8cca8a43dd333b4ab37eddefa1afb436d668e3ad953f07c5","abstract_canon_sha256":"9df36501dbff690dd98e6a61b5b21442b1965b2c0837b5d4915e637013a15205"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:31.106169Z","signature_b64":"ac1WUvfKZE5AONbQFgsGu5ReinhvYHoyq6nUSCoy7rRE37Sl8WAfUQbPf7jCjAq81mxi+NqHWRDjOyHScBzdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"358a5564df1cb621f6e8fa06ed32bbe9c11020641011213dd4f01a425a1d942e","last_reissued_at":"2026-07-05T09:04:31.105669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:31.105669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Large Language Models for Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chunrong Fang, Quanjun Zhang, Shengcheng Yu, Weisong Sun, Yang Xie, Yaxin Zhang, Yun Yang, Zhenyu Chen","submitted_at":"2023-12-23T11:09:40Z","abstract_excerpt":"Software Engineering (SE) is the systematic design, development, maintenance, and management of software applications underpinning the digital infrastructure of our modern world. Very recently, the SE community has seen a rapidly increasing number of techniques employing Large Language Models (LLMs) to automate a broad range of SE tasks. Nevertheless, existing information of the applications, effects, and possible limitations of LLMs within SE is still not well-studied.\n  In this paper, we provide a systematic survey to summarize the current state-of-the-art research in the LLM-based SE commun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15223","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/2312.15223/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":"2312.15223","created_at":"2026-07-05T09:04:31.105733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.15223v2","created_at":"2026-07-05T09:04:31.105733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15223","created_at":"2026-07-05T09:04:31.105733+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWFFKZG7DS3C","created_at":"2026-07-05T09:04:31.105733+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWFFKZG7DS3CD5XI","created_at":"2026-07-05T09:04:31.105733+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWFFKZG7","created_at":"2026-07-05T09:04:31.105733+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24834","citing_title":"Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07341","citing_title":"Empirical Evaluation of Large Language Models for Migration of Code Fragments to Post-Quantum Cryptography","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31368","citing_title":"MOA: A Profiling-Guided LLM Framework for Memory-Optimization Automation at Codebase Scale","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25536","citing_title":"A Tertiary Review of Large Language Model-Based Code Generating Tasks: Trends, Challenges, and Future Directions","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30054","citing_title":"Projectional Decoding: Towards Semantic-Aware LLM Generation","ref_index":42,"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":74,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25402","citing_title":"LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23091","citing_title":"Security of LLM-generated Code: A Comparative Analysis","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2410.01026","citing_title":"Understanding the Human-LLM Dynamic: A Literature Survey of LLM Use in Programming Tasks","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2410.20791","citing_title":"From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap","ref_index":120,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17957","citing_title":"Contextualized Code Pretraining for Code Generation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19627","citing_title":"How Helpful is LLM Assistance in Network Operations? A Case Study at a Large Demonstration Network","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15411","citing_title":"Foundational Design Principles and Patterns for Building Robust and Adaptive GenAI-Native Systems","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2510.24428","citing_title":"CodeWiki: Evaluating AI's Ability to Generate Holistic Documentation for Large-Scale Codebases","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2511.07458","citing_title":"REFLEX: Reference-Free Evaluation of Log Summarization via Large Language Model Judgment","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2512.18470","citing_title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2601.11848","citing_title":"Compass vs Railway Tracks: Unpacking User Mental Models for Communicating Long-Horizon Work to Humans vs. AI","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2601.16456","citing_title":"RubberDuckBench: A Benchmark for AI Coding Assistants","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2603.06276","citing_title":"Story Point Estimation Using Large Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22018","citing_title":"Do Papers Tell the Whole Story? A Benchmark and Framework for Uncovering Hidden Implementation Gaps in Bioinformatics","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.29813","citing_title":"Compiling Code LLMs into Lightweight Executables","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24621","citing_title":"Evaluation of LLM-Based Software Engineering Tools: Practices, Challenges, and Future Directions","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23816","citing_title":"Query2Diagram: Answering Developer Queries with UML Diagrams","ref_index":46,"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":149,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13934","citing_title":"Towards Enabling An Artificial Self-Construction Software Life-cycle via Autopoietic Architectures","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GWFFKZG7DS3CD5XI7IDO2MV35H","json":"https://pith.science/pith/GWFFKZG7DS3CD5XI7IDO2MV35H.json","graph_json":"https://pith.science/api/pith-number/GWFFKZG7DS3CD5XI7IDO2MV35H/graph.json","events_json":"https://pith.science/api/pith-number/GWFFKZG7DS3CD5XI7IDO2MV35H/events.json","paper":"https://pith.science/paper/GWFFKZG7"},"agent_actions":{"view_html":"https://pith.science/pith/GWFFKZG7DS3CD5XI7IDO2MV35H","download_json":"https://pith.science/pith/GWFFKZG7DS3CD5XI7IDO2MV35H.json","view_paper":"https://pith.science/paper/GWFFKZG7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.15223&json=true","fetch_graph":"https://pith.science/api/pith-number/GWFFKZG7DS3CD5XI7IDO2MV35H/graph.json","fetch_events":"https://pith.science/api/pith-number/GWFFKZG7DS3CD5XI7IDO2MV35H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWFFKZG7DS3CD5XI7IDO2MV35H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWFFKZG7DS3CD5XI7IDO2MV35H/action/storage_attestation","attest_author":"https://pith.science/pith/GWFFKZG7DS3CD5XI7IDO2MV35H/action/author_attestation","sign_citation":"https://pith.science/pith/GWFFKZG7DS3CD5XI7IDO2MV35H/action/citation_signature","submit_replication":"https://pith.science/pith/GWFFKZG7DS3CD5XI7IDO2MV35H/action/replication_record"}},"created_at":"2026-07-05T09:04:31.105733+00:00","updated_at":"2026-07-05T09:04:31.105733+00:00"}