{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7KAKV3AHMSA2U5HYNCDO6QKFD5","short_pith_number":"pith:7KAKV3AH","schema_version":"1.0","canonical_sha256":"fa80aaec076481aa74f86886ef41451f540080152ccbe54136c4e543d228fb13","source":{"kind":"arxiv","id":"2605.15232","version":1},"attestation_state":"computed","paper":{"title":"Method-level Change-proneness: A Better Metric for Black-box Test Suite Minimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Method-level change-proneness provides a stronger guide than class-level metrics for shrinking black-box test suites.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Kazi Sakib, Md Siam","submitted_at":"2026-05-13T18:13:58Z","abstract_excerpt":"Test Suite Minimization (TSM) reduces the size of test suites while preserving their fault detection capability. In black-box TSM, reduction is performed without analyzing production code. While several black-box TSM approaches have explored metrics like test logs or test similarity, those often suffer from scalability and efficiency issues. On the other hand, change-proneness (CP), recently emerged as an efficient and scalable alternative metric, has only been applied at class level. To accurately identify fault-revealing test cases, we propose CP at finer-grained method-level and implement M"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.15232","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-13T18:13:58Z","cross_cats_sorted":[],"title_canon_sha256":"9b7898824214567de52a5188b81bf0386f5fb6532bc8d30325e6703948a0fa7c","abstract_canon_sha256":"08b438355852abcec3992dec5dd99f59509a8eb3583fcb76cd59bec135e2e211"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:47.558344Z","signature_b64":"hAdvVmaWu5U5z8EvJgscQ9/Mbx2wCIgvPySJwdS6bctqzgfzZaQZc+cse3ouwg00ocaNfgzis2LucpWxzkDOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa80aaec076481aa74f86886ef41451f540080152ccbe54136c4e543d228fb13","last_reissued_at":"2026-05-20T00:00:47.557447Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:47.557447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Method-level Change-proneness: A Better Metric for Black-box Test Suite Minimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Method-level change-proneness provides a stronger guide than class-level metrics for shrinking black-box test suites.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Kazi Sakib, Md Siam","submitted_at":"2026-05-13T18:13:58Z","abstract_excerpt":"Test Suite Minimization (TSM) reduces the size of test suites while preserving their fault detection capability. In black-box TSM, reduction is performed without analyzing production code. While several black-box TSM approaches have explored metrics like test logs or test similarity, those often suffer from scalability and efficiency issues. On the other hand, change-proneness (CP), recently emerged as an efficient and scalable alternative metric, has only been applied at class level. To accurately identify fault-revealing test cases, we propose CP at finer-grained method-level and implement M"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MCTM achieves 0.93 accuracy and 0.94 fault detection rate on average, significantly outperforming class-level CP and similarity-based approaches while maintaining superior efficiency.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The dependency between test cases and methods can be accurately determined by analyzing the test-code call-graph, allowing reliable scoring of association with change-prone methods.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MCTM applies method-level change-proneness from version history and call-graph analysis to minimize black-box test suites, reporting 0.93 accuracy and 0.94 fault detection rate on 15 Java projects with 635 buggy versions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Method-level change-proneness provides a stronger guide than class-level metrics for shrinking black-box test suites.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c1ab08421071a929755d823e0760ab67a652e3467e6cd638e43b9d9841facc6f"},"source":{"id":"2605.15232","kind":"arxiv","version":1},"verdict":{"id":"38ced200-43cc-43a2-8130-3e056910feb8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T17:13:45.133174Z","strongest_claim":"MCTM achieves 0.93 accuracy and 0.94 fault detection rate on average, significantly outperforming class-level CP and similarity-based approaches while maintaining superior efficiency.","one_line_summary":"MCTM applies method-level change-proneness from version history and call-graph analysis to minimize black-box test suites, reporting 0.93 accuracy and 0.94 fault detection rate on 15 Java projects with 635 buggy versions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The dependency between test cases and methods can be accurately determined by analyzing the test-code call-graph, allowing reliable scoring of association with change-prone methods.","pith_extraction_headline":"Method-level change-proneness provides a stronger guide than class-level metrics for shrinking black-box test suites."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15232/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.182685Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T17:31:18.486418Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:26:25.399236Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.828827Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"13dc9d9b2676904bac0cced75bea493512a1c0f28d31246c120deff4c5003d86"},"references":{"count":53,"sample":[{"doi":"10.1002/stv.430","year":2012,"title":"Regression testing minimization, selection and prioritization: a survey,","work_id":"28ee0157-e0ec-4bfb-b97c-25a734f83cf9","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/access.2018.2809600","year":2018,"title":"A systematic review on test suite reduction: Approaches, experiment’s quality evaluation, and guidelines,","work_id":"eecbb667-2cc9-4d98-bda2-2f378372714f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/icse.2019.00054","year":2019,"title":"E., & Ray, T","work_id":"3d7bbe44-fb83-47b6-a131-32663f0b507c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/icse48619","year":2023,"title":"ATM: black-box test case minimization based on test code similarity and evolutionary search,","work_id":"4eb1fa99-8ef1-4d5d-ad5b-850dda7f8cc5","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Ltm: Scalable and black-box similarity-based test suite mini- mization based on language models,","work_id":"518a3e33-2147-4760-b71b-fcb8b61ea519","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":53,"snapshot_sha256":"cc18b77abc2b923ba44153af4b813403bf387b7385024614a00dc204a4f65d1f","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0e6ee60e118139262440344fb39f24becf4efead12b37d053ffa0957560db481"},"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":"2605.15232","created_at":"2026-05-20T00:00:47.557581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15232v1","created_at":"2026-05-20T00:00:47.557581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15232","created_at":"2026-05-20T00:00:47.557581+00:00"},{"alias_kind":"pith_short_12","alias_value":"7KAKV3AHMSA2","created_at":"2026-05-20T00:00:47.557581+00:00"},{"alias_kind":"pith_short_16","alias_value":"7KAKV3AHMSA2U5HY","created_at":"2026-05-20T00:00:47.557581+00:00"},{"alias_kind":"pith_short_8","alias_value":"7KAKV3AH","created_at":"2026-05-20T00:00:47.557581+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7KAKV3AHMSA2U5HYNCDO6QKFD5","json":"https://pith.science/pith/7KAKV3AHMSA2U5HYNCDO6QKFD5.json","graph_json":"https://pith.science/api/pith-number/7KAKV3AHMSA2U5HYNCDO6QKFD5/graph.json","events_json":"https://pith.science/api/pith-number/7KAKV3AHMSA2U5HYNCDO6QKFD5/events.json","paper":"https://pith.science/paper/7KAKV3AH"},"agent_actions":{"view_html":"https://pith.science/pith/7KAKV3AHMSA2U5HYNCDO6QKFD5","download_json":"https://pith.science/pith/7KAKV3AHMSA2U5HYNCDO6QKFD5.json","view_paper":"https://pith.science/paper/7KAKV3AH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15232&json=true","fetch_graph":"https://pith.science/api/pith-number/7KAKV3AHMSA2U5HYNCDO6QKFD5/graph.json","fetch_events":"https://pith.science/api/pith-number/7KAKV3AHMSA2U5HYNCDO6QKFD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7KAKV3AHMSA2U5HYNCDO6QKFD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7KAKV3AHMSA2U5HYNCDO6QKFD5/action/storage_attestation","attest_author":"https://pith.science/pith/7KAKV3AHMSA2U5HYNCDO6QKFD5/action/author_attestation","sign_citation":"https://pith.science/pith/7KAKV3AHMSA2U5HYNCDO6QKFD5/action/citation_signature","submit_replication":"https://pith.science/pith/7KAKV3AHMSA2U5HYNCDO6QKFD5/action/replication_record"}},"created_at":"2026-05-20T00:00:47.557581+00:00","updated_at":"2026-05-20T00:00:47.557581+00:00"}