{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VTMFG6J7WH3TZVV5S273L2ZPEU","short_pith_number":"pith:VTMFG6J7","schema_version":"1.0","canonical_sha256":"acd853793fb1f73cd6bd96bfb5eb2f2514a75b2504ae1d788a623354b1f15c59","source":{"kind":"arxiv","id":"2204.08108","version":1},"attestation_state":"computed","paper":{"title":"How are Software Repositories Mined? A Systematic Literature Review of Workflows, Methodologies, Reproducibility, and Tools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Adam Tutko, Audris Mockus, Austin Z. Henley","submitted_at":"2022-04-17T23:39:52Z","abstract_excerpt":"With the advent of open source software, a veritable treasure trove of previously proprietary software development data was made available. This opened the field of empirical software engineering research to anyone in academia. Data that is mined from software projects, however, requires extensive processing and needs to be handled with utmost care to ensure valid conclusions. Since the software development practices and tools have changed over two decades, we aim to understand the state-of-the-art research workflows and to highlight potential challenges. We employ a systematic literature revi"},"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":"2204.08108","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-04-17T23:39:52Z","cross_cats_sorted":[],"title_canon_sha256":"b11d5358404556e06bea157b28e245bcd25e7478977d506295a5f6a131d43c6f","abstract_canon_sha256":"7a4e10f3cb60bfb1c7e0137bf3e93ac4665ec21fb2c26d069564c011a3596680"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:22.193172Z","signature_b64":"YBz9IjPrBGoR/TccNVjc1e/t9RIwF2bz1SRp01OFkW/gDvFofYnK7N9u9lilXdRK7f7RU5iLPaMiSyCm4Y59BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acd853793fb1f73cd6bd96bfb5eb2f2514a75b2504ae1d788a623354b1f15c59","last_reissued_at":"2026-07-05T04:15:22.192652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:22.192652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How are Software Repositories Mined? A Systematic Literature Review of Workflows, Methodologies, Reproducibility, and Tools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Adam Tutko, Audris Mockus, Austin Z. Henley","submitted_at":"2022-04-17T23:39:52Z","abstract_excerpt":"With the advent of open source software, a veritable treasure trove of previously proprietary software development data was made available. This opened the field of empirical software engineering research to anyone in academia. Data that is mined from software projects, however, requires extensive processing and needs to be handled with utmost care to ensure valid conclusions. Since the software development practices and tools have changed over two decades, we aim to understand the state-of-the-art research workflows and to highlight potential challenges. We employ a systematic literature revi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08108","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/2204.08108/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":"2204.08108","created_at":"2026-07-05T04:15:22.192714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.08108v1","created_at":"2026-07-05T04:15:22.192714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08108","created_at":"2026-07-05T04:15:22.192714+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTMFG6J7WH3T","created_at":"2026-07-05T04:15:22.192714+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTMFG6J7WH3TZVV5","created_at":"2026-07-05T04:15:22.192714+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTMFG6J7","created_at":"2026-07-05T04:15:22.192714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06471","citing_title":"Domain-Driven Design in Practice: A Large-Scale Empirical Characterisation of the Open-Source Ecosystem","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTMFG6J7WH3TZVV5S273L2ZPEU","json":"https://pith.science/pith/VTMFG6J7WH3TZVV5S273L2ZPEU.json","graph_json":"https://pith.science/api/pith-number/VTMFG6J7WH3TZVV5S273L2ZPEU/graph.json","events_json":"https://pith.science/api/pith-number/VTMFG6J7WH3TZVV5S273L2ZPEU/events.json","paper":"https://pith.science/paper/VTMFG6J7"},"agent_actions":{"view_html":"https://pith.science/pith/VTMFG6J7WH3TZVV5S273L2ZPEU","download_json":"https://pith.science/pith/VTMFG6J7WH3TZVV5S273L2ZPEU.json","view_paper":"https://pith.science/paper/VTMFG6J7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.08108&json=true","fetch_graph":"https://pith.science/api/pith-number/VTMFG6J7WH3TZVV5S273L2ZPEU/graph.json","fetch_events":"https://pith.science/api/pith-number/VTMFG6J7WH3TZVV5S273L2ZPEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTMFG6J7WH3TZVV5S273L2ZPEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTMFG6J7WH3TZVV5S273L2ZPEU/action/storage_attestation","attest_author":"https://pith.science/pith/VTMFG6J7WH3TZVV5S273L2ZPEU/action/author_attestation","sign_citation":"https://pith.science/pith/VTMFG6J7WH3TZVV5S273L2ZPEU/action/citation_signature","submit_replication":"https://pith.science/pith/VTMFG6J7WH3TZVV5S273L2ZPEU/action/replication_record"}},"created_at":"2026-07-05T04:15:22.192714+00:00","updated_at":"2026-07-05T04:15:22.192714+00:00"}