{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YL4KFMLD6BJQSKMZDRZJJ5XHG5","short_pith_number":"pith:YL4KFMLD","schema_version":"1.0","canonical_sha256":"c2f8a2b163f0530929991c7294f6e7377cab04108a50c573967f30da3ba3d5cb","source":{"kind":"arxiv","id":"2504.18985","version":1},"attestation_state":"computed","paper":{"title":"Tracking the Moving Target: A Framework for Continuous Evaluation of LLM Test Generation in Industry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Beatriz P\\'erez Lamancha, Eneko Pizarro, Maider Azanza","submitted_at":"2025-04-26T18:08:13Z","abstract_excerpt":"Large Language Models (LLMs) have shown great potential in automating software testing tasks, including test generation. However, their rapid evolution poses a critical challenge for companies implementing DevSecOps - evaluations of their effectiveness quickly become outdated, making it difficult to assess their reliability for production use. While academic research has extensively studied LLM-based test generation, evaluations typically provide point-in-time analyses using academic benchmarks. Such evaluations do not address the practical needs of companies who must continuously assess tool "},"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":"2504.18985","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-26T18:08:13Z","cross_cats_sorted":[],"title_canon_sha256":"fbcf56a19faf0d067b02aca24a32e7ec2e73b087cb446b3a7bc10780408a9c81","abstract_canon_sha256":"db91f5277dae9249c8ac5ae957b8f0c5639f032bb08fa821b7837ef6b43d151c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:50.023172Z","signature_b64":"H0/ZMoaAo23SJKnLXJfbrzYWoEcY2XKjcZ2SbrFaUeNJhYDOKtoHMF+AQIT0gKfpAxuOyok8qsLU19+uM3AfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2f8a2b163f0530929991c7294f6e7377cab04108a50c573967f30da3ba3d5cb","last_reissued_at":"2026-07-05T10:54:50.022686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:50.022686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tracking the Moving Target: A Framework for Continuous Evaluation of LLM Test Generation in Industry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Beatriz P\\'erez Lamancha, Eneko Pizarro, Maider Azanza","submitted_at":"2025-04-26T18:08:13Z","abstract_excerpt":"Large Language Models (LLMs) have shown great potential in automating software testing tasks, including test generation. However, their rapid evolution poses a critical challenge for companies implementing DevSecOps - evaluations of their effectiveness quickly become outdated, making it difficult to assess their reliability for production use. While academic research has extensively studied LLM-based test generation, evaluations typically provide point-in-time analyses using academic benchmarks. Such evaluations do not address the practical needs of companies who must continuously assess tool "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18985","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/2504.18985/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":"2504.18985","created_at":"2026-07-05T10:54:50.022744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18985v1","created_at":"2026-07-05T10:54:50.022744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18985","created_at":"2026-07-05T10:54:50.022744+00:00"},{"alias_kind":"pith_short_12","alias_value":"YL4KFMLD6BJQ","created_at":"2026-07-05T10:54:50.022744+00:00"},{"alias_kind":"pith_short_16","alias_value":"YL4KFMLD6BJQSKMZ","created_at":"2026-07-05T10:54:50.022744+00:00"},{"alias_kind":"pith_short_8","alias_value":"YL4KFMLD","created_at":"2026-07-05T10:54:50.022744+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22475","citing_title":"All Green, Still Broken: Real-Flow Verification Lessons from an LLM-Integrated, Multi-Market Web Application","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YL4KFMLD6BJQSKMZDRZJJ5XHG5","json":"https://pith.science/pith/YL4KFMLD6BJQSKMZDRZJJ5XHG5.json","graph_json":"https://pith.science/api/pith-number/YL4KFMLD6BJQSKMZDRZJJ5XHG5/graph.json","events_json":"https://pith.science/api/pith-number/YL4KFMLD6BJQSKMZDRZJJ5XHG5/events.json","paper":"https://pith.science/paper/YL4KFMLD"},"agent_actions":{"view_html":"https://pith.science/pith/YL4KFMLD6BJQSKMZDRZJJ5XHG5","download_json":"https://pith.science/pith/YL4KFMLD6BJQSKMZDRZJJ5XHG5.json","view_paper":"https://pith.science/paper/YL4KFMLD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18985&json=true","fetch_graph":"https://pith.science/api/pith-number/YL4KFMLD6BJQSKMZDRZJJ5XHG5/graph.json","fetch_events":"https://pith.science/api/pith-number/YL4KFMLD6BJQSKMZDRZJJ5XHG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YL4KFMLD6BJQSKMZDRZJJ5XHG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YL4KFMLD6BJQSKMZDRZJJ5XHG5/action/storage_attestation","attest_author":"https://pith.science/pith/YL4KFMLD6BJQSKMZDRZJJ5XHG5/action/author_attestation","sign_citation":"https://pith.science/pith/YL4KFMLD6BJQSKMZDRZJJ5XHG5/action/citation_signature","submit_replication":"https://pith.science/pith/YL4KFMLD6BJQSKMZDRZJJ5XHG5/action/replication_record"}},"created_at":"2026-07-05T10:54:50.022744+00:00","updated_at":"2026-07-05T10:54:50.022744+00:00"}