{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JDNZMEPGB5YSTP5PSZP42VRHVP","short_pith_number":"pith:JDNZMEPG","schema_version":"1.0","canonical_sha256":"48db9611e60f7129bfaf965fcd5627abced010a932c70f8198f54b338f342b12","source":{"kind":"arxiv","id":"2405.03786","version":2},"attestation_state":"computed","paper":{"title":"TOGLL: Correct and Strong Test Oracle Generation with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Matthew Dwyer, Soneya Binta Hossain","submitted_at":"2024-05-06T18:37:35Z","abstract_excerpt":"Test oracles play a crucial role in software testing, enabling effective bug detection. Despite initial promise, neural-based methods for automated test oracle generation often result in a large number of false positives and weaker test oracles. While LLMs have demonstrated impressive effectiveness in various software engineering tasks, including code generation, test case creation, and bug fixing, there remains a notable absence of large-scale studies exploring their effectiveness in test oracle generation. The question of whether LLMs can address the challenges in effective oracle generation"},"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":"2405.03786","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-05-06T18:37:35Z","cross_cats_sorted":[],"title_canon_sha256":"ed0851e15adb1a788d39a0c397ff7dc0f9c6ba3973cbe3a144ca0b845ac85a79","abstract_canon_sha256":"0a7c9be6deac3e7ecc98b760d0ab61dfc9295b43c3ecb4bf223679fff2cda239"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:45.502682Z","signature_b64":"oOEfQQxrUTcTbqjkrv3UO7TmtRfAavue2Va6D3/WAcjw/3wW294RQAXO+dEKJsV1PkNn4mxsdAsmeR2jeDb7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48db9611e60f7129bfaf965fcd5627abced010a932c70f8198f54b338f342b12","last_reissued_at":"2026-07-05T11:49:45.502212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:45.502212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TOGLL: Correct and Strong Test Oracle Generation with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Matthew Dwyer, Soneya Binta Hossain","submitted_at":"2024-05-06T18:37:35Z","abstract_excerpt":"Test oracles play a crucial role in software testing, enabling effective bug detection. Despite initial promise, neural-based methods for automated test oracle generation often result in a large number of false positives and weaker test oracles. While LLMs have demonstrated impressive effectiveness in various software engineering tasks, including code generation, test case creation, and bug fixing, there remains a notable absence of large-scale studies exploring their effectiveness in test oracle generation. The question of whether LLMs can address the challenges in effective oracle generation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03786","kind":"arxiv","version":2},"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/2405.03786/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":"2405.03786","created_at":"2026-07-05T11:49:45.502276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03786v2","created_at":"2026-07-05T11:49:45.502276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03786","created_at":"2026-07-05T11:49:45.502276+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDNZMEPGB5YS","created_at":"2026-07-05T11:49:45.502276+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDNZMEPGB5YSTP5P","created_at":"2026-07-05T11:49:45.502276+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDNZMEPG","created_at":"2026-07-05T11:49:45.502276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26851","citing_title":"LLM-based Mockless Unit Test Generation for Java","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18315","citing_title":"Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27112","citing_title":"On the Effectiveness of Modular Testing in EvoSuite","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JDNZMEPGB5YSTP5PSZP42VRHVP","json":"https://pith.science/pith/JDNZMEPGB5YSTP5PSZP42VRHVP.json","graph_json":"https://pith.science/api/pith-number/JDNZMEPGB5YSTP5PSZP42VRHVP/graph.json","events_json":"https://pith.science/api/pith-number/JDNZMEPGB5YSTP5PSZP42VRHVP/events.json","paper":"https://pith.science/paper/JDNZMEPG"},"agent_actions":{"view_html":"https://pith.science/pith/JDNZMEPGB5YSTP5PSZP42VRHVP","download_json":"https://pith.science/pith/JDNZMEPGB5YSTP5PSZP42VRHVP.json","view_paper":"https://pith.science/paper/JDNZMEPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03786&json=true","fetch_graph":"https://pith.science/api/pith-number/JDNZMEPGB5YSTP5PSZP42VRHVP/graph.json","fetch_events":"https://pith.science/api/pith-number/JDNZMEPGB5YSTP5PSZP42VRHVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDNZMEPGB5YSTP5PSZP42VRHVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDNZMEPGB5YSTP5PSZP42VRHVP/action/storage_attestation","attest_author":"https://pith.science/pith/JDNZMEPGB5YSTP5PSZP42VRHVP/action/author_attestation","sign_citation":"https://pith.science/pith/JDNZMEPGB5YSTP5PSZP42VRHVP/action/citation_signature","submit_replication":"https://pith.science/pith/JDNZMEPGB5YSTP5PSZP42VRHVP/action/replication_record"}},"created_at":"2026-07-05T11:49:45.502276+00:00","updated_at":"2026-07-05T11:49:45.502276+00:00"}