{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TNIOBM2GEET2PZLDD33LM6XWGX","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":"0a2ea555f765116bd0a3ad324c5942b3a974bc692825e30b29dba64c66011bc3","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T18:51:43Z","title_canon_sha256":"59e59f1a969b0377cb15d191e55838926cffd5ce50d5ff7b060517acf4e48284"},"schema_version":"1.0","source":{"id":"2502.01619","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01619","created_at":"2026-07-05T11:56:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01619v3","created_at":"2026-07-05T11:56:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01619","created_at":"2026-07-05T11:56:52Z"},{"alias_kind":"pith_short_12","alias_value":"TNIOBM2GEET2","created_at":"2026-07-05T11:56:52Z"},{"alias_kind":"pith_short_16","alias_value":"TNIOBM2GEET2PZLD","created_at":"2026-07-05T11:56:52Z"},{"alias_kind":"pith_short_8","alias_value":"TNIOBM2G","created_at":"2026-07-05T11:56:52Z"}],"graph_snapshots":[{"event_id":"sha256:dcefd7e3329f3cbcf59863f588ce829f229dd1fc8ff292383e1d31efbebd1f48","target":"graph","created_at":"2026-07-05T11:56:52Z","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/2502.01619/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unit tests (UTs) play an instrumental role in assessing code correctness as well as providing feedback to large language models (LLMs), motivating automated test generation. However, we uncover a trade-off between generating unit test inputs that reveal errors when given a faulty code and correctly predicting the unit test output without access to the gold solution. To address this trade-off, we propose UTGen, which teaches LLMs to generate unit test inputs that reveal errors along with their correct expected outputs based on task descriptions. Since model-generated tests can provide noisy sig","authors_text":"Archiki Prasad, Elias Stengel-Eskin, Justin Chih-Yao Chen, Mohit Bansal, Zaid Khan","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T18:51:43Z","title":"Learning to Generate Unit Tests for Automated Debugging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01619","kind":"arxiv","version":3},"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:c349fbfb669a13e03dfc81266f0ad5b10aa920248ed1c421593f67c3fe984ca3","target":"record","created_at":"2026-07-05T11:56:52Z","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":"0a2ea555f765116bd0a3ad324c5942b3a974bc692825e30b29dba64c66011bc3","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T18:51:43Z","title_canon_sha256":"59e59f1a969b0377cb15d191e55838926cffd5ce50d5ff7b060517acf4e48284"},"schema_version":"1.0","source":{"id":"2502.01619","kind":"arxiv","version":3}},"canonical_sha256":"9b50e0b3462127a7e5631ef6b67af635e70375216ee601f19bc85dafd672dbf5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b50e0b3462127a7e5631ef6b67af635e70375216ee601f19bc85dafd672dbf5","first_computed_at":"2026-07-05T11:56:52.555750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:52.555750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"phGqpTpCKI98+0cAT/u+9ix77E1MIqwTyYgHWSCj1v0LElHD1LNkGsP8mdpMfOCyX84oyxkZOp9s5q88lB7WCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:52.556212Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01619","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c349fbfb669a13e03dfc81266f0ad5b10aa920248ed1c421593f67c3fe984ca3","sha256:dcefd7e3329f3cbcf59863f588ce829f229dd1fc8ff292383e1d31efbebd1f48"],"state_sha256":"5fc348a2344dd34df152002f5821cd7d72004db8471daa42a75ac46ad3377f2b"}