{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z4K5VRKEUMRMP3ZEFOKBDEHPGL","short_pith_number":"pith:Z4K5VRKE","schema_version":"1.0","canonical_sha256":"cf15dac544a322c7ef242b941190ef32e2494bf933d681b44d112e4942c7cae3","source":{"kind":"arxiv","id":"2501.12862","version":1},"attestation_state":"computed","paper":{"title":"Mutation-Guided LLM-based Test Generation at Meta","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Abhishek Gulati, Christopher Foster, Herv\\'e Robert, Inna Harper, Jillian Ritchey, Ke Mao, Mark Harman, Shubho Sengupta","submitted_at":"2025-01-22T13:14:02Z","abstract_excerpt":"This paper describes Meta's ACH system for mutation-guided LLM-based test generation. ACH generates relatively few mutants (aka simulated faults), compared to traditional mutation testing. Instead, it focuses on generating currently undetected faults that are specific to an issue of concern. From these currently uncaught faults, ACH generates tests that can catch them, thereby `killing' the mutants and consequently hardening the platform against regressions. We use privacy concerns to illustrate our approach, but ACH can harden code against {\\em any} type of regression. In total, ACH was appli"},"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":"2501.12862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-01-22T13:14:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"84345f3cd7d305c6547fcb4eaa4e0adb9bb63ffcf461c36efe39cf318b0f6f06","abstract_canon_sha256":"2564980e824751c04d60e8db4864eb2ea66086ca19444ad0723e3afe3233ac7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:59.799741Z","signature_b64":"kKqh1oUZ46QpWg3FWya9C887CE74tcVL4Z0U+fe+thdLmCROlfNP3lSBgNHFIhFniHT7bZo8O5DEVVW8bQdoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf15dac544a322c7ef242b941190ef32e2494bf933d681b44d112e4942c7cae3","last_reissued_at":"2026-07-05T10:03:59.799262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:59.799262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mutation-Guided LLM-based Test Generation at Meta","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Abhishek Gulati, Christopher Foster, Herv\\'e Robert, Inna Harper, Jillian Ritchey, Ke Mao, Mark Harman, Shubho Sengupta","submitted_at":"2025-01-22T13:14:02Z","abstract_excerpt":"This paper describes Meta's ACH system for mutation-guided LLM-based test generation. ACH generates relatively few mutants (aka simulated faults), compared to traditional mutation testing. Instead, it focuses on generating currently undetected faults that are specific to an issue of concern. From these currently uncaught faults, ACH generates tests that can catch them, thereby `killing' the mutants and consequently hardening the platform against regressions. We use privacy concerns to illustrate our approach, but ACH can harden code against {\\em any} type of regression. In total, ACH was appli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12862","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/2501.12862/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":"2501.12862","created_at":"2026-07-05T10:03:59.799322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12862v1","created_at":"2026-07-05T10:03:59.799322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12862","created_at":"2026-07-05T10:03:59.799322+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4K5VRKEUMRM","created_at":"2026-07-05T10:03:59.799322+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4K5VRKEUMRMP3ZE","created_at":"2026-07-05T10:03:59.799322+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4K5VRKE","created_at":"2026-07-05T10:03:59.799322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.13766","citing_title":"A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02954","citing_title":"Mutation-Guided Unit Test Generation with a Large Language Model","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19315","citing_title":"Improving LLM-Driven Test Generation by Learning from Mocking Information","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10761","citing_title":"Improving Dynamic Specification Inference with LLM-Generated Counterexamples","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4K5VRKEUMRMP3ZEFOKBDEHPGL","json":"https://pith.science/pith/Z4K5VRKEUMRMP3ZEFOKBDEHPGL.json","graph_json":"https://pith.science/api/pith-number/Z4K5VRKEUMRMP3ZEFOKBDEHPGL/graph.json","events_json":"https://pith.science/api/pith-number/Z4K5VRKEUMRMP3ZEFOKBDEHPGL/events.json","paper":"https://pith.science/paper/Z4K5VRKE"},"agent_actions":{"view_html":"https://pith.science/pith/Z4K5VRKEUMRMP3ZEFOKBDEHPGL","download_json":"https://pith.science/pith/Z4K5VRKEUMRMP3ZEFOKBDEHPGL.json","view_paper":"https://pith.science/paper/Z4K5VRKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12862&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4K5VRKEUMRMP3ZEFOKBDEHPGL/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4K5VRKEUMRMP3ZEFOKBDEHPGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4K5VRKEUMRMP3ZEFOKBDEHPGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4K5VRKEUMRMP3ZEFOKBDEHPGL/action/storage_attestation","attest_author":"https://pith.science/pith/Z4K5VRKEUMRMP3ZEFOKBDEHPGL/action/author_attestation","sign_citation":"https://pith.science/pith/Z4K5VRKEUMRMP3ZEFOKBDEHPGL/action/citation_signature","submit_replication":"https://pith.science/pith/Z4K5VRKEUMRMP3ZEFOKBDEHPGL/action/replication_record"}},"created_at":"2026-07-05T10:03:59.799322+00:00","updated_at":"2026-07-05T10:03:59.799322+00:00"}