{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2O6RJBE2VEO5HIFU5D7XH4OITA","short_pith_number":"pith:2O6RJBE2","schema_version":"1.0","canonical_sha256":"d3bd14849aa91dd3a0b4e8ff73f1c8983a726df2576c31f5244f2e4f42eba491","source":{"kind":"arxiv","id":"2403.07506","version":1},"attestation_state":"computed","paper":{"title":"Robustness, Security, Privacy, Explainability, Efficiency, and Usability of Large Language Models for Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"David Lo, Premkumar Devanbu, Terry Zhuo Yue, Zhensu Sun, Zhou Yang","submitted_at":"2024-03-12T10:43:26Z","abstract_excerpt":"Large language models for code (LLM4Code), which demonstrate strong performance (e.g., high accuracy) in processing source code, have significantly transformed software engineering. Many studies separately investigate the non-functional properties of LM4Code, but there is no systematic review of how these properties are evaluated and enhanced. This paper fills this gap by thoroughly examining 146 relevant studies, thereby presenting the first systematic literature review to identify seven important properties beyond accuracy, including robustness, security, privacy, explainability, efficiency,"},"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":"2403.07506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-03-12T10:43:26Z","cross_cats_sorted":[],"title_canon_sha256":"4b0e56879968dd9446fe5a1a5d971bcc7b2f95fd0f0c626746ec1315815fdbe8","abstract_canon_sha256":"022444f3041e101bb7822b680f11d7176d71e72087a5ddf529111358a9ff8601"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:04.663418Z","signature_b64":"XzXfzIlNzBe7DXl8qLOAcJdd4OSvdDQvLZnRK8zyCwhidRMpoc0XmYpJKEO/VU03LMK2z1I1nKnGQO9Ivp1bBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3bd14849aa91dd3a0b4e8ff73f1c8983a726df2576c31f5244f2e4f42eba491","last_reissued_at":"2026-07-05T07:55:04.662908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:04.662908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustness, Security, Privacy, Explainability, Efficiency, and Usability of Large Language Models for Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"David Lo, Premkumar Devanbu, Terry Zhuo Yue, Zhensu Sun, Zhou Yang","submitted_at":"2024-03-12T10:43:26Z","abstract_excerpt":"Large language models for code (LLM4Code), which demonstrate strong performance (e.g., high accuracy) in processing source code, have significantly transformed software engineering. Many studies separately investigate the non-functional properties of LM4Code, but there is no systematic review of how these properties are evaluated and enhanced. This paper fills this gap by thoroughly examining 146 relevant studies, thereby presenting the first systematic literature review to identify seven important properties beyond accuracy, including robustness, security, privacy, explainability, efficiency,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07506","kind":"arxiv","version":1},"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/2403.07506/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":"2403.07506","created_at":"2026-07-05T07:55:04.662974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07506v1","created_at":"2026-07-05T07:55:04.662974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07506","created_at":"2026-07-05T07:55:04.662974+00:00"},{"alias_kind":"pith_short_12","alias_value":"2O6RJBE2VEO5","created_at":"2026-07-05T07:55:04.662974+00:00"},{"alias_kind":"pith_short_16","alias_value":"2O6RJBE2VEO5HIFU","created_at":"2026-07-05T07:55:04.662974+00:00"},{"alias_kind":"pith_short_8","alias_value":"2O6RJBE2","created_at":"2026-07-05T07:55:04.662974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10846","citing_title":"Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models","ref_index":10,"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":58,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01055","citing_title":"Towards Agentic Runtime Healing","ref_index":65,"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":112,"is_internal_anchor":false},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":300,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10611","citing_title":"DuCodeMark: Dual-Purpose Code Dataset Watermarking via Style-Aware Watermark-Poison Design","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2O6RJBE2VEO5HIFU5D7XH4OITA","json":"https://pith.science/pith/2O6RJBE2VEO5HIFU5D7XH4OITA.json","graph_json":"https://pith.science/api/pith-number/2O6RJBE2VEO5HIFU5D7XH4OITA/graph.json","events_json":"https://pith.science/api/pith-number/2O6RJBE2VEO5HIFU5D7XH4OITA/events.json","paper":"https://pith.science/paper/2O6RJBE2"},"agent_actions":{"view_html":"https://pith.science/pith/2O6RJBE2VEO5HIFU5D7XH4OITA","download_json":"https://pith.science/pith/2O6RJBE2VEO5HIFU5D7XH4OITA.json","view_paper":"https://pith.science/paper/2O6RJBE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07506&json=true","fetch_graph":"https://pith.science/api/pith-number/2O6RJBE2VEO5HIFU5D7XH4OITA/graph.json","fetch_events":"https://pith.science/api/pith-number/2O6RJBE2VEO5HIFU5D7XH4OITA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2O6RJBE2VEO5HIFU5D7XH4OITA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2O6RJBE2VEO5HIFU5D7XH4OITA/action/storage_attestation","attest_author":"https://pith.science/pith/2O6RJBE2VEO5HIFU5D7XH4OITA/action/author_attestation","sign_citation":"https://pith.science/pith/2O6RJBE2VEO5HIFU5D7XH4OITA/action/citation_signature","submit_replication":"https://pith.science/pith/2O6RJBE2VEO5HIFU5D7XH4OITA/action/replication_record"}},"created_at":"2026-07-05T07:55:04.662974+00:00","updated_at":"2026-07-05T07:55:04.662974+00:00"}