{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UCSDDPYYCOYPIDS2PKBZIF7V7P","short_pith_number":"pith:UCSDDPYY","schema_version":"1.0","canonical_sha256":"a0a431bf1813b0f40e5a7a839417f5fbf5ddc91f6bf5d62ddaeb900f8cb2462d","source":{"kind":"arxiv","id":"2402.09171","version":1},"attestation_state":"computed","paper":{"title":"Automated Unit Test Improvement using Large Language Models at Meta","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Alexandru Marginean, Anastasia Finegenova, Beliz Gokkaya, Eddy Wang, Inna Harper, Jubin Chheda, Mark Harman, Nadia Alshahwan, Shubho Sengupta","submitted_at":"2024-02-14T13:43:14Z","abstract_excerpt":"This paper describes Meta's TestGen-LLM tool, which uses LLMs to automatically improve existing human-written tests. TestGen-LLM verifies that its generated test classes successfully clear a set of filters that assure measurable improvement over the original test suite, thereby eliminating problems due to LLM hallucination. We describe the deployment of TestGen-LLM at Meta test-a-thons for the Instagram and Facebook platforms. In an evaluation on Reels and Stories products for Instagram, 75% of TestGen-LLM's test cases built correctly, 57% passed reliably, and 25% increased coverage. During Me"},"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":"2402.09171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-14T13:43:14Z","cross_cats_sorted":[],"title_canon_sha256":"5cd727f07389e832ac33ad19573abb52d14724e85b6bff8ddbc23e79901c6009","abstract_canon_sha256":"983fed9ae5ce25892ae46ea73f3402beea07f28f4efe3f27e1676c46d2a86324"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:09.607272Z","signature_b64":"8ISElIy5kh53d5xN04AyFq+uHgec+pyMiNNrsKCEMfFQ7Ivkro+YTIga7e26I8ydlCejLCbU0r4n75DO7oLtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0a431bf1813b0f40e5a7a839417f5fbf5ddc91f6bf5d62ddaeb900f8cb2462d","last_reissued_at":"2026-07-05T07:45:09.606881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:09.606881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Unit Test Improvement using Large Language Models at Meta","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Alexandru Marginean, Anastasia Finegenova, Beliz Gokkaya, Eddy Wang, Inna Harper, Jubin Chheda, Mark Harman, Nadia Alshahwan, Shubho Sengupta","submitted_at":"2024-02-14T13:43:14Z","abstract_excerpt":"This paper describes Meta's TestGen-LLM tool, which uses LLMs to automatically improve existing human-written tests. TestGen-LLM verifies that its generated test classes successfully clear a set of filters that assure measurable improvement over the original test suite, thereby eliminating problems due to LLM hallucination. We describe the deployment of TestGen-LLM at Meta test-a-thons for the Instagram and Facebook platforms. In an evaluation on Reels and Stories products for Instagram, 75% of TestGen-LLM's test cases built correctly, 57% passed reliably, and 25% increased coverage. During Me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09171","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/2402.09171/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":"2402.09171","created_at":"2026-07-05T07:45:09.606932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09171v1","created_at":"2026-07-05T07:45:09.606932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09171","created_at":"2026-07-05T07:45:09.606932+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCSDDPYYCOYP","created_at":"2026-07-05T07:45:09.606932+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCSDDPYYCOYPIDS2","created_at":"2026-07-05T07:45:09.606932+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCSDDPYY","created_at":"2026-07-05T07:45:09.606932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.02954","citing_title":"Mutation-Guided Unit Test Generation with a Large Language Model","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2403.17134","citing_title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2402.06196","citing_title":"Large Language Models: A Survey","ref_index":220,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UCSDDPYYCOYPIDS2PKBZIF7V7P","json":"https://pith.science/pith/UCSDDPYYCOYPIDS2PKBZIF7V7P.json","graph_json":"https://pith.science/api/pith-number/UCSDDPYYCOYPIDS2PKBZIF7V7P/graph.json","events_json":"https://pith.science/api/pith-number/UCSDDPYYCOYPIDS2PKBZIF7V7P/events.json","paper":"https://pith.science/paper/UCSDDPYY"},"agent_actions":{"view_html":"https://pith.science/pith/UCSDDPYYCOYPIDS2PKBZIF7V7P","download_json":"https://pith.science/pith/UCSDDPYYCOYPIDS2PKBZIF7V7P.json","view_paper":"https://pith.science/paper/UCSDDPYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09171&json=true","fetch_graph":"https://pith.science/api/pith-number/UCSDDPYYCOYPIDS2PKBZIF7V7P/graph.json","fetch_events":"https://pith.science/api/pith-number/UCSDDPYYCOYPIDS2PKBZIF7V7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCSDDPYYCOYPIDS2PKBZIF7V7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCSDDPYYCOYPIDS2PKBZIF7V7P/action/storage_attestation","attest_author":"https://pith.science/pith/UCSDDPYYCOYPIDS2PKBZIF7V7P/action/author_attestation","sign_citation":"https://pith.science/pith/UCSDDPYYCOYPIDS2PKBZIF7V7P/action/citation_signature","submit_replication":"https://pith.science/pith/UCSDDPYYCOYPIDS2PKBZIF7V7P/action/replication_record"}},"created_at":"2026-07-05T07:45:09.606932+00:00","updated_at":"2026-07-05T07:45:09.606932+00:00"}