{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UCSDDPYYCOYPIDS2PKBZIF7V7P","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"983fed9ae5ce25892ae46ea73f3402beea07f28f4efe3f27e1676c46d2a86324","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-14T13:43:14Z","title_canon_sha256":"5cd727f07389e832ac33ad19573abb52d14724e85b6bff8ddbc23e79901c6009"},"schema_version":"1.0","source":{"id":"2402.09171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09171","created_at":"2026-07-05T07:45:09Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09171v1","created_at":"2026-07-05T07:45:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09171","created_at":"2026-07-05T07:45:09Z"},{"alias_kind":"pith_short_12","alias_value":"UCSDDPYYCOYP","created_at":"2026-07-05T07:45:09Z"},{"alias_kind":"pith_short_16","alias_value":"UCSDDPYYCOYPIDS2","created_at":"2026-07-05T07:45:09Z"},{"alias_kind":"pith_short_8","alias_value":"UCSDDPYY","created_at":"2026-07-05T07:45:09Z"}],"graph_snapshots":[{"event_id":"sha256:9c7f5a365c3ac90d6efd1f745d42bbd5a6a7f255351da7196d53bd7fe7e7f769","target":"graph","created_at":"2026-07-05T07:45:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.09171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexandru Marginean, Anastasia Finegenova, Beliz Gokkaya, Eddy Wang, Inna Harper, Jubin Chheda, Mark Harman, Nadia Alshahwan, Shubho Sengupta","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-14T13:43:14Z","title":"Automated Unit Test Improvement using Large Language Models at Meta"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09171","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4a1b5ad50e9839dab1bd752d7c17efa971383318974bd09377bc54f8a1be8e22","target":"record","created_at":"2026-07-05T07:45:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"983fed9ae5ce25892ae46ea73f3402beea07f28f4efe3f27e1676c46d2a86324","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-14T13:43:14Z","title_canon_sha256":"5cd727f07389e832ac33ad19573abb52d14724e85b6bff8ddbc23e79901c6009"},"schema_version":"1.0","source":{"id":"2402.09171","kind":"arxiv","version":1}},"canonical_sha256":"a0a431bf1813b0f40e5a7a839417f5fbf5ddc91f6bf5d62ddaeb900f8cb2462d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0a431bf1813b0f40e5a7a839417f5fbf5ddc91f6bf5d62ddaeb900f8cb2462d","first_computed_at":"2026-07-05T07:45:09.606881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:09.606881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8ISElIy5kh53d5xN04AyFq+uHgec+pyMiNNrsKCEMfFQ7Ivkro+YTIga7e26I8ydlCejLCbU0r4n75DO7oLtBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:09.607272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.09171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a1b5ad50e9839dab1bd752d7c17efa971383318974bd09377bc54f8a1be8e22","sha256:9c7f5a365c3ac90d6efd1f745d42bbd5a6a7f255351da7196d53bd7fe7e7f769"],"state_sha256":"b04bbce3f6f9df3798497f991228670571d4950d98708a311ad7201149bf99e7"}