{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CQK6PL6KQZCDDSACBCXTIBR4LG","short_pith_number":"pith:CQK6PL6K","schema_version":"1.0","canonical_sha256":"1415e7afca864431c80208af34063c59b3e6a9ed2c6628cbdb66f5f698394495","source":{"kind":"arxiv","id":"2008.03439","version":2},"attestation_state":"computed","paper":{"title":"More Effective Software Repository Mining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Adam Tutko, Audris Mockus, Austin Henley","submitted_at":"2020-08-08T04:18:55Z","abstract_excerpt":"Background: Data mining and analyzing of public Git software repositories is a growing research field. The tools used for studies that investigate a single project or a group of projects have been refined, but it is not clear whether the results obtained on such ``convenience samples'' generalize. Aims: This paper aims to elucidate the difficulties faced by researchers who would like to ascertain the generalizability of their findings by introducing an interface that addresses the issues with obtaining representative samples. Results: To do that we explore how to exploit the World of Code syst"},"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":"2008.03439","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2020-08-08T04:18:55Z","cross_cats_sorted":[],"title_canon_sha256":"71b706aa95d65cc065b9596e9cf4cd2d0a6a98ee43eee1aa3cd31f82480d9e6c","abstract_canon_sha256":"8ed5350923c28274efa88c006d28e907fa2764489435586bdd392dfae1238d32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:26.671592Z","signature_b64":"Aw513F3CD0KTWzv8cpFvoiR5Ebfq89yQ9Rp/zXZCuhEvPibzyZ8I1bibBrzTvqc76dh/XC4GavWgVMH2QA7TCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1415e7afca864431c80208af34063c59b3e6a9ed2c6628cbdb66f5f698394495","last_reissued_at":"2026-07-05T01:27:26.671127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:26.671127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"More Effective Software Repository Mining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Adam Tutko, Audris Mockus, Austin Henley","submitted_at":"2020-08-08T04:18:55Z","abstract_excerpt":"Background: Data mining and analyzing of public Git software repositories is a growing research field. The tools used for studies that investigate a single project or a group of projects have been refined, but it is not clear whether the results obtained on such ``convenience samples'' generalize. Aims: This paper aims to elucidate the difficulties faced by researchers who would like to ascertain the generalizability of their findings by introducing an interface that addresses the issues with obtaining representative samples. Results: To do that we explore how to exploit the World of Code syst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03439","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/2008.03439/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":"2008.03439","created_at":"2026-07-05T01:27:26.671188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.03439v2","created_at":"2026-07-05T01:27:26.671188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03439","created_at":"2026-07-05T01:27:26.671188+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQK6PL6KQZCD","created_at":"2026-07-05T01:27:26.671188+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQK6PL6KQZCDDSAC","created_at":"2026-07-05T01:27:26.671188+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQK6PL6K","created_at":"2026-07-05T01:27:26.671188+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/CQK6PL6KQZCDDSACBCXTIBR4LG","json":"https://pith.science/pith/CQK6PL6KQZCDDSACBCXTIBR4LG.json","graph_json":"https://pith.science/api/pith-number/CQK6PL6KQZCDDSACBCXTIBR4LG/graph.json","events_json":"https://pith.science/api/pith-number/CQK6PL6KQZCDDSACBCXTIBR4LG/events.json","paper":"https://pith.science/paper/CQK6PL6K"},"agent_actions":{"view_html":"https://pith.science/pith/CQK6PL6KQZCDDSACBCXTIBR4LG","download_json":"https://pith.science/pith/CQK6PL6KQZCDDSACBCXTIBR4LG.json","view_paper":"https://pith.science/paper/CQK6PL6K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.03439&json=true","fetch_graph":"https://pith.science/api/pith-number/CQK6PL6KQZCDDSACBCXTIBR4LG/graph.json","fetch_events":"https://pith.science/api/pith-number/CQK6PL6KQZCDDSACBCXTIBR4LG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQK6PL6KQZCDDSACBCXTIBR4LG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQK6PL6KQZCDDSACBCXTIBR4LG/action/storage_attestation","attest_author":"https://pith.science/pith/CQK6PL6KQZCDDSACBCXTIBR4LG/action/author_attestation","sign_citation":"https://pith.science/pith/CQK6PL6KQZCDDSACBCXTIBR4LG/action/citation_signature","submit_replication":"https://pith.science/pith/CQK6PL6KQZCDDSACBCXTIBR4LG/action/replication_record"}},"created_at":"2026-07-05T01:27:26.671188+00:00","updated_at":"2026-07-05T01:27:26.671188+00:00"}