{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q4KBVO4KBMRJE555JFRFBKZAQN","short_pith_number":"pith:Q4KBVO4K","schema_version":"1.0","canonical_sha256":"87141abb8a0b229277bd496250ab208360f47990508be76ead1b43c82f66bf32","source":{"kind":"arxiv","id":"2607.05139","version":1},"attestation_state":"computed","paper":{"title":"On the risk of coding before testing: An empirical study on LLM-based test generation workflow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Florian Tambon, Michael Konstantinou, Mike Papadakis","submitted_at":"2026-07-06T14:23:30Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used in software engineering workflows to generate both source code and test suites. This dual capability has enabled emerging development paradigms, including test-first and agentic workflows, where a single model is producing and validating implementations. However, these approaches assume that generated tests act as independent and reliable oracles - a fundamental requirement for effective software testing. In this paper, we challenge this assumption and investigate whether LLM-generated code biases the generation of subsequent tests. We introdu"},"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":"2607.05139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-06T14:23:30Z","cross_cats_sorted":[],"title_canon_sha256":"73dc05c1bb219aedae520d7931fa6ea099e07a7b374b483c13a58e56be3b0758","abstract_canon_sha256":"0b35e8c113d8aea55e44a3097a027e09c3f327623312a8e7f54e72e4b58d8984"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T03:19:17.383800Z","signature_b64":"4tw4NM0BRgGfkF2wrXWyKLRt7r8EjXbjuOXnIsu3sSR1TGnnfvs58tuXlBTvqZSafgdV9jnh2AqQfmAjWNtHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87141abb8a0b229277bd496250ab208360f47990508be76ead1b43c82f66bf32","last_reissued_at":"2026-07-07T03:19:17.383369Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T03:19:17.383369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the risk of coding before testing: An empirical study on LLM-based test generation workflow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Florian Tambon, Michael Konstantinou, Mike Papadakis","submitted_at":"2026-07-06T14:23:30Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used in software engineering workflows to generate both source code and test suites. This dual capability has enabled emerging development paradigms, including test-first and agentic workflows, where a single model is producing and validating implementations. However, these approaches assume that generated tests act as independent and reliable oracles - a fundamental requirement for effective software testing. In this paper, we challenge this assumption and investigate whether LLM-generated code biases the generation of subsequent tests. We introdu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05139","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/2607.05139/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":"2607.05139","created_at":"2026-07-07T03:19:17.383429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.05139v1","created_at":"2026-07-07T03:19:17.383429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05139","created_at":"2026-07-07T03:19:17.383429+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4KBVO4KBMRJ","created_at":"2026-07-07T03:19:17.383429+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4KBVO4KBMRJE555","created_at":"2026-07-07T03:19:17.383429+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4KBVO4K","created_at":"2026-07-07T03:19:17.383429+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/Q4KBVO4KBMRJE555JFRFBKZAQN","json":"https://pith.science/pith/Q4KBVO4KBMRJE555JFRFBKZAQN.json","graph_json":"https://pith.science/api/pith-number/Q4KBVO4KBMRJE555JFRFBKZAQN/graph.json","events_json":"https://pith.science/api/pith-number/Q4KBVO4KBMRJE555JFRFBKZAQN/events.json","paper":"https://pith.science/paper/Q4KBVO4K"},"agent_actions":{"view_html":"https://pith.science/pith/Q4KBVO4KBMRJE555JFRFBKZAQN","download_json":"https://pith.science/pith/Q4KBVO4KBMRJE555JFRFBKZAQN.json","view_paper":"https://pith.science/paper/Q4KBVO4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.05139&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4KBVO4KBMRJE555JFRFBKZAQN/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4KBVO4KBMRJE555JFRFBKZAQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4KBVO4KBMRJE555JFRFBKZAQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4KBVO4KBMRJE555JFRFBKZAQN/action/storage_attestation","attest_author":"https://pith.science/pith/Q4KBVO4KBMRJE555JFRFBKZAQN/action/author_attestation","sign_citation":"https://pith.science/pith/Q4KBVO4KBMRJE555JFRFBKZAQN/action/citation_signature","submit_replication":"https://pith.science/pith/Q4KBVO4KBMRJE555JFRFBKZAQN/action/replication_record"}},"created_at":"2026-07-07T03:19:17.383429+00:00","updated_at":"2026-07-07T03:19:17.383429+00:00"}