{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WKDOCSSDIQS67NCJKFM7SUB42T","short_pith_number":"pith:WKDOCSSD","schema_version":"1.0","canonical_sha256":"b286e14a434425efb4495159f9503cd4e6d060ffa5656a292f0e3c45f276e773","source":{"kind":"arxiv","id":"2012.08387","version":1},"attestation_state":"computed","paper":{"title":"Run, Forest, Run? On Randomization and Reproducibility in Predictive Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Annibale Panichella, Cynthia C. S. Liem","submitted_at":"2020-12-15T16:01:21Z","abstract_excerpt":"Machine learning (ML) has been widely used in the literature to automate software engineering tasks. However, ML outcomes may be sensitive to randomization in data sampling mechanisms and learning procedures. To understand whether and how researchers in SE address these threats, we surveyed 45 recent papers related to three predictive tasks: defect prediction (DP), predictive mutation testing (PMT), and code smell detection (CSD). We found that less than 50% of the surveyed papers address the threats related to randomized data sampling (via multiple repetitions); only 8% of the papers address "},"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":"2012.08387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2020-12-15T16:01:21Z","cross_cats_sorted":[],"title_canon_sha256":"1eb994216c4da5634636bb7c3cb973496d7f30549f64bbb00cbf013720d2929d","abstract_canon_sha256":"83d30e84bd6cf0680d610fbe0b3941a76732c3934586d6372fe1c51cde256d5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:42.903003Z","signature_b64":"EXaJ64gt5aTfc6wAsnpOiyTRDvNBuEzeOL1hVlxauXgOnhhXZzE3VjyH/kcAU9nNMUbyUqC/Ui3ujRM+RT50CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b286e14a434425efb4495159f9503cd4e6d060ffa5656a292f0e3c45f276e773","last_reissued_at":"2026-07-05T01:59:42.902597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:42.902597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Run, Forest, Run? On Randomization and Reproducibility in Predictive Software Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Annibale Panichella, Cynthia C. S. Liem","submitted_at":"2020-12-15T16:01:21Z","abstract_excerpt":"Machine learning (ML) has been widely used in the literature to automate software engineering tasks. However, ML outcomes may be sensitive to randomization in data sampling mechanisms and learning procedures. To understand whether and how researchers in SE address these threats, we surveyed 45 recent papers related to three predictive tasks: defect prediction (DP), predictive mutation testing (PMT), and code smell detection (CSD). We found that less than 50% of the surveyed papers address the threats related to randomized data sampling (via multiple repetitions); only 8% of the papers address "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.08387","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/2012.08387/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":"2012.08387","created_at":"2026-07-05T01:59:42.902654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.08387v1","created_at":"2026-07-05T01:59:42.902654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.08387","created_at":"2026-07-05T01:59:42.902654+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKDOCSSDIQS6","created_at":"2026-07-05T01:59:42.902654+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKDOCSSDIQS67NCJ","created_at":"2026-07-05T01:59:42.902654+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKDOCSSD","created_at":"2026-07-05T01:59:42.902654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05985","citing_title":"Auto-DSM Under the Lens: A Black-Box Evaluation Framework for LLM-Based DSM Generation","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T","json":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T.json","graph_json":"https://pith.science/api/pith-number/WKDOCSSDIQS67NCJKFM7SUB42T/graph.json","events_json":"https://pith.science/api/pith-number/WKDOCSSDIQS67NCJKFM7SUB42T/events.json","paper":"https://pith.science/paper/WKDOCSSD"},"agent_actions":{"view_html":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T","download_json":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T.json","view_paper":"https://pith.science/paper/WKDOCSSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.08387&json=true","fetch_graph":"https://pith.science/api/pith-number/WKDOCSSDIQS67NCJKFM7SUB42T/graph.json","fetch_events":"https://pith.science/api/pith-number/WKDOCSSDIQS67NCJKFM7SUB42T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T/action/storage_attestation","attest_author":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T/action/author_attestation","sign_citation":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T/action/citation_signature","submit_replication":"https://pith.science/pith/WKDOCSSDIQS67NCJKFM7SUB42T/action/replication_record"}},"created_at":"2026-07-05T01:59:42.902654+00:00","updated_at":"2026-07-05T01:59:42.902654+00:00"}