{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GHRXSEYZVRIHSPLGDAD7YQXPHZ","short_pith_number":"pith:GHRXSEYZ","schema_version":"1.0","canonical_sha256":"31e3791319ac50793d661807fc42ef3e68f486cf4f35154c27b45307c2d24c1d","source":{"kind":"arxiv","id":"2506.11006","version":1},"attestation_state":"computed","paper":{"title":"Test code generation at Ericsson using Program Analysis Augmented Fine Tuned LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Balvinder Singh, Dimitris Rentas, Giriprasad Sridhara, Jakub Gajda, Karol Sawicki, Maciej Nalepa, Magnus Sandelin, Sai Krishna, Sourav Mazumdar, Sujoy Roychowdhury","submitted_at":"2025-04-23T18:18:18Z","abstract_excerpt":"We describe test code generation using Large Language Models (LLMs) in Ericsson. Our input is a test step in natural language (English) and our output is code (Java) which accomplishes the test step. We describe how straight forward prompting does not suffice and results in LLM assuming functions and signatures which are not present in the code repository. We then show how we alleviate the problem by a combination of Retrieval Augmented Generation (RAG) along with prompt engineering that expanded the simple prompt with additional contextual information using static program analysis. We then de"},"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":"2506.11006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-23T18:18:18Z","cross_cats_sorted":[],"title_canon_sha256":"a2df5303729af28392e63c7c54c53a6c6757b3d8edf1fa36c2d1bf743cfb7c39","abstract_canon_sha256":"457b36737bb8528980ca85a4cc9c1b6cf3d40cba6b9375825a1fdbe44b9e1de7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:57.632602Z","signature_b64":"NeICBP4v0kH2umjO/6QGSIihyzdovkJPW7r8BItcSlk4t9QLitm9+vofwGpRbR7LdJU6OEcXluGWGWvt9Nw1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31e3791319ac50793d661807fc42ef3e68f486cf4f35154c27b45307c2d24c1d","last_reissued_at":"2026-07-05T11:20:57.632159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:57.632159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test code generation at Ericsson using Program Analysis Augmented Fine Tuned LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Balvinder Singh, Dimitris Rentas, Giriprasad Sridhara, Jakub Gajda, Karol Sawicki, Maciej Nalepa, Magnus Sandelin, Sai Krishna, Sourav Mazumdar, Sujoy Roychowdhury","submitted_at":"2025-04-23T18:18:18Z","abstract_excerpt":"We describe test code generation using Large Language Models (LLMs) in Ericsson. Our input is a test step in natural language (English) and our output is code (Java) which accomplishes the test step. We describe how straight forward prompting does not suffice and results in LLM assuming functions and signatures which are not present in the code repository. We then show how we alleviate the problem by a combination of Retrieval Augmented Generation (RAG) along with prompt engineering that expanded the simple prompt with additional contextual information using static program analysis. We then de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11006","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/2506.11006/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":"2506.11006","created_at":"2026-07-05T11:20:57.632213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11006v1","created_at":"2026-07-05T11:20:57.632213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11006","created_at":"2026-07-05T11:20:57.632213+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHRXSEYZVRIH","created_at":"2026-07-05T11:20:57.632213+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHRXSEYZVRIHSPLG","created_at":"2026-07-05T11:20:57.632213+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHRXSEYZ","created_at":"2026-07-05T11:20:57.632213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GHRXSEYZVRIHSPLGDAD7YQXPHZ","json":"https://pith.science/pith/GHRXSEYZVRIHSPLGDAD7YQXPHZ.json","graph_json":"https://pith.science/api/pith-number/GHRXSEYZVRIHSPLGDAD7YQXPHZ/graph.json","events_json":"https://pith.science/api/pith-number/GHRXSEYZVRIHSPLGDAD7YQXPHZ/events.json","paper":"https://pith.science/paper/GHRXSEYZ"},"agent_actions":{"view_html":"https://pith.science/pith/GHRXSEYZVRIHSPLGDAD7YQXPHZ","download_json":"https://pith.science/pith/GHRXSEYZVRIHSPLGDAD7YQXPHZ.json","view_paper":"https://pith.science/paper/GHRXSEYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11006&json=true","fetch_graph":"https://pith.science/api/pith-number/GHRXSEYZVRIHSPLGDAD7YQXPHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GHRXSEYZVRIHSPLGDAD7YQXPHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHRXSEYZVRIHSPLGDAD7YQXPHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHRXSEYZVRIHSPLGDAD7YQXPHZ/action/storage_attestation","attest_author":"https://pith.science/pith/GHRXSEYZVRIHSPLGDAD7YQXPHZ/action/author_attestation","sign_citation":"https://pith.science/pith/GHRXSEYZVRIHSPLGDAD7YQXPHZ/action/citation_signature","submit_replication":"https://pith.science/pith/GHRXSEYZVRIHSPLGDAD7YQXPHZ/action/replication_record"}},"created_at":"2026-07-05T11:20:57.632213+00:00","updated_at":"2026-07-05T11:20:57.632213+00:00"}