{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TANBMCUPHF64EDEWN7NAHYSVRY","short_pith_number":"pith:TANBMCUP","schema_version":"1.0","canonical_sha256":"981a160a8f397dc20c966fda03e2558e02071b4ef2b04457abca11c1eaa859de","source":{"kind":"arxiv","id":"2503.14713","version":1},"attestation_state":"computed","paper":{"title":"TestForge: Feedback-Driven, Agentic Test Suite Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Claire Le Goues, Kush Jain","submitted_at":"2025-03-18T20:21:44Z","abstract_excerpt":"Automated test generation holds great promise for alleviating the burdens of manual test creation. However, existing search-based techniques compromise on test readability, while LLM-based approaches are prohibitively expensive in practice. We present TestForge, an agentic unit testing framework designed to cost-effectively generate high-quality test suites for real-world code. Our key insight is to reframe LLM-based test generation as an iterative process. TestForge thus begins with tests generated via zero-shot prompting, and then continuously refines those tests based on feedback from test "},"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":"2503.14713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-18T20:21:44Z","cross_cats_sorted":[],"title_canon_sha256":"ee9c91d19c3c7bc556b99b9895aadc617c8072bc0242e3a6bba0fefbc3190fc4","abstract_canon_sha256":"179774c4749984874668e9f3820eba741946bdf60891cbef10e8826a86c8fbe6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:22.876909Z","signature_b64":"ux7fBdGfPICSndj3CWEu+JFkQRVfYEVyAxdXaTAUpifhZsuN04wiUjcgkDwc1Cuf5aFLuZgHDa8im4T/dobhCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"981a160a8f397dc20c966fda03e2558e02071b4ef2b04457abca11c1eaa859de","last_reissued_at":"2026-07-05T10:34:22.876356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:22.876356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TestForge: Feedback-Driven, Agentic Test Suite Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Claire Le Goues, Kush Jain","submitted_at":"2025-03-18T20:21:44Z","abstract_excerpt":"Automated test generation holds great promise for alleviating the burdens of manual test creation. However, existing search-based techniques compromise on test readability, while LLM-based approaches are prohibitively expensive in practice. We present TestForge, an agentic unit testing framework designed to cost-effectively generate high-quality test suites for real-world code. Our key insight is to reframe LLM-based test generation as an iterative process. TestForge thus begins with tests generated via zero-shot prompting, and then continuously refines those tests based on feedback from test "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14713","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/2503.14713/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":"2503.14713","created_at":"2026-07-05T10:34:22.876426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.14713v1","created_at":"2026-07-05T10:34:22.876426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14713","created_at":"2026-07-05T10:34:22.876426+00:00"},{"alias_kind":"pith_short_12","alias_value":"TANBMCUPHF64","created_at":"2026-07-05T10:34:22.876426+00:00"},{"alias_kind":"pith_short_16","alias_value":"TANBMCUPHF64EDEW","created_at":"2026-07-05T10:34:22.876426+00:00"},{"alias_kind":"pith_short_8","alias_value":"TANBMCUP","created_at":"2026-07-05T10:34:22.876426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06747","citing_title":"Tensor Algebraic Property Skeletons: Amplifying Property-Based Testing for AI Compilers","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25285","citing_title":"PR-Aware Automated Unit Test Generation: Challenges and Opportunities","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05159","citing_title":"Planning to Explore: Curiosity-Driven Planning for LLM Test Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17508","citing_title":"Augmenting unit test suites from integration tests","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TANBMCUPHF64EDEWN7NAHYSVRY","json":"https://pith.science/pith/TANBMCUPHF64EDEWN7NAHYSVRY.json","graph_json":"https://pith.science/api/pith-number/TANBMCUPHF64EDEWN7NAHYSVRY/graph.json","events_json":"https://pith.science/api/pith-number/TANBMCUPHF64EDEWN7NAHYSVRY/events.json","paper":"https://pith.science/paper/TANBMCUP"},"agent_actions":{"view_html":"https://pith.science/pith/TANBMCUPHF64EDEWN7NAHYSVRY","download_json":"https://pith.science/pith/TANBMCUPHF64EDEWN7NAHYSVRY.json","view_paper":"https://pith.science/paper/TANBMCUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.14713&json=true","fetch_graph":"https://pith.science/api/pith-number/TANBMCUPHF64EDEWN7NAHYSVRY/graph.json","fetch_events":"https://pith.science/api/pith-number/TANBMCUPHF64EDEWN7NAHYSVRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TANBMCUPHF64EDEWN7NAHYSVRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TANBMCUPHF64EDEWN7NAHYSVRY/action/storage_attestation","attest_author":"https://pith.science/pith/TANBMCUPHF64EDEWN7NAHYSVRY/action/author_attestation","sign_citation":"https://pith.science/pith/TANBMCUPHF64EDEWN7NAHYSVRY/action/citation_signature","submit_replication":"https://pith.science/pith/TANBMCUPHF64EDEWN7NAHYSVRY/action/replication_record"}},"created_at":"2026-07-05T10:34:22.876426+00:00","updated_at":"2026-07-05T10:34:22.876426+00:00"}