{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EKENX5IQN6WBUKREULAUGIIXYM","short_pith_number":"pith:EKENX5IQ","schema_version":"1.0","canonical_sha256":"2288dbf5106fac1a2a24a2c1432117c318a0e218ed959e3d3cbeada9063c64c7","source":{"kind":"arxiv","id":"2002.07764","version":6},"attestation_state":"computed","paper":{"title":"Sampling in Software Engineering Research: A Critical Review and Guidelines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Paul Ralph, Sebastian Baltes","submitted_at":"2020-02-18T17:53:55Z","abstract_excerpt":"Representative sampling appears rare in empirical software engineering research. Not all studies need representative samples, but a general lack of representative sampling undermines a scientific field. This article therefore reports a critical review of the state of sampling in recent, high-quality software engineering research. The key findings are: (1) random sampling is rare; (2) sophisticated sampling strategies are very rare; (3) sampling, representativeness and randomness often appear misunderstood. These findings suggest that software engineering research has a generalizability crisis."},"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":"2002.07764","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-02-18T17:53:55Z","cross_cats_sorted":[],"title_canon_sha256":"93a5f528db7c739d986d7edabd45b2dc0baea59c1658d15aceb289414ea934c9","abstract_canon_sha256":"d1315392db7cd5d5414b4bc7502b1c833f69fb31eae18e38c24a5b45ae6d7323"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:06.234831Z","signature_b64":"4CO8ByU2I4l3sAQAIqHG6SE2WGcukZ5Gpj1e0Pl1jgNo+9OwChBEJxA50RpLJ9OYPRjwsFJAICwbQyRSK6UzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2288dbf5106fac1a2a24a2c1432117c318a0e218ed959e3d3cbeada9063c64c7","last_reissued_at":"2026-07-05T03:24:06.234282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:06.234282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sampling in Software Engineering Research: A Critical Review and Guidelines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Paul Ralph, Sebastian Baltes","submitted_at":"2020-02-18T17:53:55Z","abstract_excerpt":"Representative sampling appears rare in empirical software engineering research. Not all studies need representative samples, but a general lack of representative sampling undermines a scientific field. This article therefore reports a critical review of the state of sampling in recent, high-quality software engineering research. The key findings are: (1) random sampling is rare; (2) sophisticated sampling strategies are very rare; (3) sampling, representativeness and randomness often appear misunderstood. These findings suggest that software engineering research has a generalizability crisis."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07764","kind":"arxiv","version":6},"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/2002.07764/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":"2002.07764","created_at":"2026-07-05T03:24:06.234350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.07764v6","created_at":"2026-07-05T03:24:06.234350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07764","created_at":"2026-07-05T03:24:06.234350+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKENX5IQN6WB","created_at":"2026-07-05T03:24:06.234350+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKENX5IQN6WBUKRE","created_at":"2026-07-05T03:24:06.234350+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKENX5IQ","created_at":"2026-07-05T03:24:06.234350+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.16771","citing_title":"Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EKENX5IQN6WBUKREULAUGIIXYM","json":"https://pith.science/pith/EKENX5IQN6WBUKREULAUGIIXYM.json","graph_json":"https://pith.science/api/pith-number/EKENX5IQN6WBUKREULAUGIIXYM/graph.json","events_json":"https://pith.science/api/pith-number/EKENX5IQN6WBUKREULAUGIIXYM/events.json","paper":"https://pith.science/paper/EKENX5IQ"},"agent_actions":{"view_html":"https://pith.science/pith/EKENX5IQN6WBUKREULAUGIIXYM","download_json":"https://pith.science/pith/EKENX5IQN6WBUKREULAUGIIXYM.json","view_paper":"https://pith.science/paper/EKENX5IQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.07764&json=true","fetch_graph":"https://pith.science/api/pith-number/EKENX5IQN6WBUKREULAUGIIXYM/graph.json","fetch_events":"https://pith.science/api/pith-number/EKENX5IQN6WBUKREULAUGIIXYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKENX5IQN6WBUKREULAUGIIXYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKENX5IQN6WBUKREULAUGIIXYM/action/storage_attestation","attest_author":"https://pith.science/pith/EKENX5IQN6WBUKREULAUGIIXYM/action/author_attestation","sign_citation":"https://pith.science/pith/EKENX5IQN6WBUKREULAUGIIXYM/action/citation_signature","submit_replication":"https://pith.science/pith/EKENX5IQN6WBUKREULAUGIIXYM/action/replication_record"}},"created_at":"2026-07-05T03:24:06.234350+00:00","updated_at":"2026-07-05T03:24:06.234350+00:00"}