{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IUQBXN6WD2A3IRB6PJPBYYAXBV","short_pith_number":"pith:IUQBXN6W","schema_version":"1.0","canonical_sha256":"45201bb7d61e81b4443e7a5e1c60170d5087f778f07e59bb0572a646febd0689","source":{"kind":"arxiv","id":"2503.17502","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Hamed Jelodar, Mohammad Meymani, Roozbeh Razavi-Far","submitted_at":"2025-03-21T19:29:50Z","abstract_excerpt":"Large language models (LLMs) and transformer-based architectures are increasingly utilized for source code analysis. As software systems grow in complexity, integrating LLMs into code analysis workflows becomes essential for enhancing efficiency, accuracy, and automation. This paper explores the role of LLMs for different code analysis tasks, focusing on three key aspects: 1) what they can analyze and their applications, 2) what models are used and 3) what datasets are used, and the challenges they face. Regarding the goal of this research, we investigate scholarly articles that explore the us"},"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":"2503.17502","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-21T19:29:50Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5ef571f3ffaef13864cc9614aab29ba50f5998153b9edb12304e4a4d96da9bfc","abstract_canon_sha256":"609b242d41935e2a7d56552e7d87a81b7a5dcb86d35fbd8759595feb0f3b867d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:10.886924Z","signature_b64":"oVaDTYL84QL11HULEpnAldHyTJxurZzkj/yBxF6jIrQ098f6IZUxNiB3mmVZti7umsoX6iri0dAaZ0MRcR01BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45201bb7d61e81b4443e7a5e1c60170d5087f778f07e59bb0572a646febd0689","last_reissued_at":"2026-07-05T10:37:10.886452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:10.886452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Hamed Jelodar, Mohammad Meymani, Roozbeh Razavi-Far","submitted_at":"2025-03-21T19:29:50Z","abstract_excerpt":"Large language models (LLMs) and transformer-based architectures are increasingly utilized for source code analysis. As software systems grow in complexity, integrating LLMs into code analysis workflows becomes essential for enhancing efficiency, accuracy, and automation. This paper explores the role of LLMs for different code analysis tasks, focusing on three key aspects: 1) what they can analyze and their applications, 2) what models are used and 3) what datasets are used, and the challenges they face. Regarding the goal of this research, we investigate scholarly articles that explore the us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17502","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/2503.17502/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":"2503.17502","created_at":"2026-07-05T10:37:10.886505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17502v1","created_at":"2026-07-05T10:37:10.886505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17502","created_at":"2026-07-05T10:37:10.886505+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUQBXN6WD2A3","created_at":"2026-07-05T10:37:10.886505+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUQBXN6WD2A3IRB6","created_at":"2026-07-05T10:37:10.886505+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUQBXN6W","created_at":"2026-07-05T10:37:10.886505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06125","citing_title":"Evaluating Fine-Tuning and Metrics for Neural Decompilation of Dart AOT Binaries","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09852","citing_title":"LLM-Based Code Documentation Generation and Multi-Judge Evaluation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2505.10708","citing_title":"SafeTrans: LLM-assisted Transpilation from C to Rust","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2505.13766","citing_title":"A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19201","citing_title":"Cascaded Code Editing: Large-Small Model Collaboration for Effective and Efficient Code Editing","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12048","citing_title":"ORBIT: Guided Agentic Orchestration for Autonomous C-to-Rust Transpilation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06095","citing_title":"LLM4CodeRE: Generative AI for Code Decompilation Analysis and Reverse Engineering","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21765","citing_title":"PrismaDV: Automated Task-Aware Data Unit Test Generation","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUQBXN6WD2A3IRB6PJPBYYAXBV","json":"https://pith.science/pith/IUQBXN6WD2A3IRB6PJPBYYAXBV.json","graph_json":"https://pith.science/api/pith-number/IUQBXN6WD2A3IRB6PJPBYYAXBV/graph.json","events_json":"https://pith.science/api/pith-number/IUQBXN6WD2A3IRB6PJPBYYAXBV/events.json","paper":"https://pith.science/paper/IUQBXN6W"},"agent_actions":{"view_html":"https://pith.science/pith/IUQBXN6WD2A3IRB6PJPBYYAXBV","download_json":"https://pith.science/pith/IUQBXN6WD2A3IRB6PJPBYYAXBV.json","view_paper":"https://pith.science/paper/IUQBXN6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17502&json=true","fetch_graph":"https://pith.science/api/pith-number/IUQBXN6WD2A3IRB6PJPBYYAXBV/graph.json","fetch_events":"https://pith.science/api/pith-number/IUQBXN6WD2A3IRB6PJPBYYAXBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUQBXN6WD2A3IRB6PJPBYYAXBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUQBXN6WD2A3IRB6PJPBYYAXBV/action/storage_attestation","attest_author":"https://pith.science/pith/IUQBXN6WD2A3IRB6PJPBYYAXBV/action/author_attestation","sign_citation":"https://pith.science/pith/IUQBXN6WD2A3IRB6PJPBYYAXBV/action/citation_signature","submit_replication":"https://pith.science/pith/IUQBXN6WD2A3IRB6PJPBYYAXBV/action/replication_record"}},"created_at":"2026-07-05T10:37:10.886505+00:00","updated_at":"2026-07-05T10:37:10.886505+00:00"}