{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZNJ4BBU62XRONBZO6AYZY5MZRW","short_pith_number":"pith:ZNJ4BBU6","schema_version":"1.0","canonical_sha256":"cb53c0869ed5e2e6872ef0319c75998d9a5eef9b0f35874249c147d98ab726ba","source":{"kind":"arxiv","id":"2607.10277","version":1},"attestation_state":"computed","paper":{"title":"From Business Requirements to Test Assertions: Evaluating LLM-Generated Oracles on Real Bugs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Nasir U. Eisty, Tiancheng Ma","submitted_at":"2026-07-11T12:17:49Z","abstract_excerpt":"The oracle problem (determining the correct expected outcome for a test) remains a major bottleneck in automated testing, and is increasingly relevant as non-experts rely on AI-generated code they cannot reliably validate. We study whether large language models (LLMs) can generate generalizable test oracles directly from natural-language business requirements, without access to source code or example input-output pairs. We propose a reproducible, requirement-driven pipeline grounded in Defects4J. For each of 10 real bugs from Defects4J Lang (Bugs 1 and 3-11), we (i) extract behavioral changes "},"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":"2607.10277","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-11T12:17:49Z","cross_cats_sorted":[],"title_canon_sha256":"3b74725dd95f1cfc707ba12b2065d6ff64b35a51c76eb1572c5f463704857b97","abstract_canon_sha256":"7e1b0b6745988c341a5f20bb3543968ff731fd0d89983aae6f4fa9f5d550a223"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:20:34.223394Z","signature_b64":"4Q3fc4C2wMU/+WQGxcevapKg/gghuL244Sy3dYlPkLk91pkNtxm3l4da1Ox639Gx5/LkUShI+71G3hZcO8wGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb53c0869ed5e2e6872ef0319c75998d9a5eef9b0f35874249c147d98ab726ba","last_reissued_at":"2026-07-14T01:20:34.222516Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:20:34.222516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Business Requirements to Test Assertions: Evaluating LLM-Generated Oracles on Real Bugs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Nasir U. Eisty, Tiancheng Ma","submitted_at":"2026-07-11T12:17:49Z","abstract_excerpt":"The oracle problem (determining the correct expected outcome for a test) remains a major bottleneck in automated testing, and is increasingly relevant as non-experts rely on AI-generated code they cannot reliably validate. We study whether large language models (LLMs) can generate generalizable test oracles directly from natural-language business requirements, without access to source code or example input-output pairs. We propose a reproducible, requirement-driven pipeline grounded in Defects4J. For each of 10 real bugs from Defects4J Lang (Bugs 1 and 3-11), we (i) extract behavioral changes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10277","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/2607.10277/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":"2607.10277","created_at":"2026-07-14T01:20:34.222958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10277v1","created_at":"2026-07-14T01:20:34.222958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10277","created_at":"2026-07-14T01:20:34.222958+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNJ4BBU62XRO","created_at":"2026-07-14T01:20:34.222958+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNJ4BBU62XRONBZO","created_at":"2026-07-14T01:20:34.222958+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNJ4BBU6","created_at":"2026-07-14T01:20:34.222958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZNJ4BBU62XRONBZO6AYZY5MZRW","json":"https://pith.science/pith/ZNJ4BBU62XRONBZO6AYZY5MZRW.json","graph_json":"https://pith.science/api/pith-number/ZNJ4BBU62XRONBZO6AYZY5MZRW/graph.json","events_json":"https://pith.science/api/pith-number/ZNJ4BBU62XRONBZO6AYZY5MZRW/events.json","paper":"https://pith.science/paper/ZNJ4BBU6"},"agent_actions":{"view_html":"https://pith.science/pith/ZNJ4BBU62XRONBZO6AYZY5MZRW","download_json":"https://pith.science/pith/ZNJ4BBU62XRONBZO6AYZY5MZRW.json","view_paper":"https://pith.science/paper/ZNJ4BBU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10277&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNJ4BBU62XRONBZO6AYZY5MZRW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNJ4BBU62XRONBZO6AYZY5MZRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNJ4BBU62XRONBZO6AYZY5MZRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNJ4BBU62XRONBZO6AYZY5MZRW/action/storage_attestation","attest_author":"https://pith.science/pith/ZNJ4BBU62XRONBZO6AYZY5MZRW/action/author_attestation","sign_citation":"https://pith.science/pith/ZNJ4BBU62XRONBZO6AYZY5MZRW/action/citation_signature","submit_replication":"https://pith.science/pith/ZNJ4BBU62XRONBZO6AYZY5MZRW/action/replication_record"}},"created_at":"2026-07-14T01:20:34.222958+00:00","updated_at":"2026-07-14T01:20:34.222958+00:00"}