{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L2JTGLQIR23SOXPQWAQU6UHMTY","short_pith_number":"pith:L2JTGLQI","schema_version":"1.0","canonical_sha256":"5e93332e088eb7275df0b0214f50ec9e395ebbfd893ed73051d6eeb5253f6366","source":{"kind":"arxiv","id":"2311.10372","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Dewu Zheng, Jiachi Chen, Jingwen Zhang, Kaiwen Ning, Mingxi Ye, Yanlin Wang, Zibin Zheng","submitted_at":"2023-11-17T07:55:16Z","abstract_excerpt":"General large language models (LLMs), represented by ChatGPT, have demonstrated significant potential in tasks such as code generation in software engineering. This has led to the development of specialized LLMs for software engineering, known as Code LLMs. A considerable portion of Code LLMs is derived from general LLMs through model fine-tuning. As a result, Code LLMs are often updated frequently and their performance can be influenced by the base LLMs. However, there is currently a lack of systematic investigation into Code LLMs and their performance. In this study, we conduct a comprehensi"},"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":"2311.10372","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-11-17T07:55:16Z","cross_cats_sorted":[],"title_canon_sha256":"660466775c0fe4b036c55c1b9ada0367b99ab8072fa6a3fb9c97acdb83666530","abstract_canon_sha256":"c1cbb2931666431970832c9d3a380509c94d381c117b7c2c5607103d5d0b2885"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:56.762467Z","signature_b64":"W5iWSYKnPtcHmrBZYNxXDECfoM3HQhS8iD+EYsSQLv4DK0PY0SAPKJSTrlVxMQJ4+Wfg9/4OLcLCBbj3Xx1cCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e93332e088eb7275df0b0214f50ec9e395ebbfd893ed73051d6eeb5253f6366","last_reissued_at":"2026-07-05T07:30:56.762104Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:56.762104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Dewu Zheng, Jiachi Chen, Jingwen Zhang, Kaiwen Ning, Mingxi Ye, Yanlin Wang, Zibin Zheng","submitted_at":"2023-11-17T07:55:16Z","abstract_excerpt":"General large language models (LLMs), represented by ChatGPT, have demonstrated significant potential in tasks such as code generation in software engineering. This has led to the development of specialized LLMs for software engineering, known as Code LLMs. A considerable portion of Code LLMs is derived from general LLMs through model fine-tuning. As a result, Code LLMs are often updated frequently and their performance can be influenced by the base LLMs. However, there is currently a lack of systematic investigation into Code LLMs and their performance. In this study, we conduct a comprehensi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10372","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/2311.10372/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":"2311.10372","created_at":"2026-07-05T07:30:56.762159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10372v2","created_at":"2026-07-05T07:30:56.762159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10372","created_at":"2026-07-05T07:30:56.762159+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2JTGLQIR23S","created_at":"2026-07-05T07:30:56.762159+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2JTGLQIR23SOXPQ","created_at":"2026-07-05T07:30:56.762159+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2JTGLQI","created_at":"2026-07-05T07:30:56.762159+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05717","citing_title":"Plainbook: Data Science, in Plain Language","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.24138","citing_title":"Understanding Conversational Patterns in Multi-agent Programming: A Case Study on Fibonacci Game Development","ref_index":28,"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":111,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28148","citing_title":"DeltaMCP: Incremental Regeneration via Spec-Aware Transformation for MCP servers","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29357","citing_title":"PassNet: Scaling Large Language Models for Graph Compiler Pass Generation","ref_index":5,"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":75,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20173","citing_title":"Qiskit Code Migration with LLMs","ref_index":107,"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":57,"is_internal_anchor":false},{"citing_arxiv_id":"2410.22240","citing_title":"Are Decoder-Only Large Language Models the Silver Bullet for Code Search?","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18684","citing_title":"Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents","ref_index":44,"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":70,"is_internal_anchor":false},{"citing_arxiv_id":"2404.13501","citing_title":"A Survey on the Memory Mechanism of Large Language Model based Agents","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2603.29813","citing_title":"Compiling Code LLMs into Lightweight Executables","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03048","citing_title":"Combining Static Code Analysis and Large Language Models Improves Correctness and Performance of Algorithm Recognition","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10387","citing_title":"Leveraging Mathematical Reasoning of LLMs for Efficient GPU Thread Mapping","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08083","citing_title":"Can LLMs Deobfuscate Binary Code? A Systematic Analysis of Large Language Models into Pseudocode Deobfuscation","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02741","citing_title":"AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L2JTGLQIR23SOXPQWAQU6UHMTY","json":"https://pith.science/pith/L2JTGLQIR23SOXPQWAQU6UHMTY.json","graph_json":"https://pith.science/api/pith-number/L2JTGLQIR23SOXPQWAQU6UHMTY/graph.json","events_json":"https://pith.science/api/pith-number/L2JTGLQIR23SOXPQWAQU6UHMTY/events.json","paper":"https://pith.science/paper/L2JTGLQI"},"agent_actions":{"view_html":"https://pith.science/pith/L2JTGLQIR23SOXPQWAQU6UHMTY","download_json":"https://pith.science/pith/L2JTGLQIR23SOXPQWAQU6UHMTY.json","view_paper":"https://pith.science/paper/L2JTGLQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10372&json=true","fetch_graph":"https://pith.science/api/pith-number/L2JTGLQIR23SOXPQWAQU6UHMTY/graph.json","fetch_events":"https://pith.science/api/pith-number/L2JTGLQIR23SOXPQWAQU6UHMTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2JTGLQIR23SOXPQWAQU6UHMTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2JTGLQIR23SOXPQWAQU6UHMTY/action/storage_attestation","attest_author":"https://pith.science/pith/L2JTGLQIR23SOXPQWAQU6UHMTY/action/author_attestation","sign_citation":"https://pith.science/pith/L2JTGLQIR23SOXPQWAQU6UHMTY/action/citation_signature","submit_replication":"https://pith.science/pith/L2JTGLQIR23SOXPQWAQU6UHMTY/action/replication_record"}},"created_at":"2026-07-05T07:30:56.762159+00:00","updated_at":"2026-07-05T07:30:56.762159+00:00"}