{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:46P4AAZST35IINIROIXSZ432LP","short_pith_number":"pith:46P4AAZS","schema_version":"1.0","canonical_sha256":"e79fc003329efa843511722f2cf37a5bcac81a1c6c22df5ee7ba27bba9bfce59","source":{"kind":"arxiv","id":"1905.08327","version":1},"attestation_state":"computed","paper":{"title":"Tools for analyzing R code the tidy way","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Jeffrey T. Leek, Lucy D'Agostino McGowan, Sean Kross","submitted_at":"2019-05-20T20:04:44Z","abstract_excerpt":"With the current emphasis on reproducibility and replicability, there is an increasing need to examine how data analyses are conducted. In order to analyze the between researcher variability in data analysis choices as well as the aspects within the data analysis pipeline that contribute to the variability in results, we have created two R packages: matahari and tidycode. These packages build on methods created for natural language processing; rather than allowing for the processing of natural language, we focus on R code as the substrate of interest. The matahari package facilitates the loggi"},"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":"1905.08327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2019-05-20T20:04:44Z","cross_cats_sorted":[],"title_canon_sha256":"011defd11acfb43cafca47e435767a39f918db402d59e2c720b0a83c2886960e","abstract_canon_sha256":"8cde4563c45f4364ae044b48017d875d4c283dd4aa552be63ce47ffd218e846c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:36.281395Z","signature_b64":"tcA4KYFN6CjdjWmv/0rjJmPrD8tWDz9qy0bRVbusutcYq9eFudBiOzXS406gXuRu7/5kw65RR2mtu294CjWkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e79fc003329efa843511722f2cf37a5bcac81a1c6c22df5ee7ba27bba9bfce59","last_reissued_at":"2026-07-05T01:51:36.281019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:36.281019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tools for analyzing R code the tidy way","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Jeffrey T. Leek, Lucy D'Agostino McGowan, Sean Kross","submitted_at":"2019-05-20T20:04:44Z","abstract_excerpt":"With the current emphasis on reproducibility and replicability, there is an increasing need to examine how data analyses are conducted. In order to analyze the between researcher variability in data analysis choices as well as the aspects within the data analysis pipeline that contribute to the variability in results, we have created two R packages: matahari and tidycode. These packages build on methods created for natural language processing; rather than allowing for the processing of natural language, we focus on R code as the substrate of interest. The matahari package facilitates the loggi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.08327","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/1905.08327/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":"1905.08327","created_at":"2026-07-05T01:51:36.281075+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.08327v1","created_at":"2026-07-05T01:51:36.281075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.08327","created_at":"2026-07-05T01:51:36.281075+00:00"},{"alias_kind":"pith_short_12","alias_value":"46P4AAZST35I","created_at":"2026-07-05T01:51:36.281075+00:00"},{"alias_kind":"pith_short_16","alias_value":"46P4AAZST35IINIR","created_at":"2026-07-05T01:51:36.281075+00:00"},{"alias_kind":"pith_short_8","alias_value":"46P4AAZS","created_at":"2026-07-05T01:51:36.281075+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/46P4AAZST35IINIROIXSZ432LP","json":"https://pith.science/pith/46P4AAZST35IINIROIXSZ432LP.json","graph_json":"https://pith.science/api/pith-number/46P4AAZST35IINIROIXSZ432LP/graph.json","events_json":"https://pith.science/api/pith-number/46P4AAZST35IINIROIXSZ432LP/events.json","paper":"https://pith.science/paper/46P4AAZS"},"agent_actions":{"view_html":"https://pith.science/pith/46P4AAZST35IINIROIXSZ432LP","download_json":"https://pith.science/pith/46P4AAZST35IINIROIXSZ432LP.json","view_paper":"https://pith.science/paper/46P4AAZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.08327&json=true","fetch_graph":"https://pith.science/api/pith-number/46P4AAZST35IINIROIXSZ432LP/graph.json","fetch_events":"https://pith.science/api/pith-number/46P4AAZST35IINIROIXSZ432LP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46P4AAZST35IINIROIXSZ432LP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46P4AAZST35IINIROIXSZ432LP/action/storage_attestation","attest_author":"https://pith.science/pith/46P4AAZST35IINIROIXSZ432LP/action/author_attestation","sign_citation":"https://pith.science/pith/46P4AAZST35IINIROIXSZ432LP/action/citation_signature","submit_replication":"https://pith.science/pith/46P4AAZST35IINIROIXSZ432LP/action/replication_record"}},"created_at":"2026-07-05T01:51:36.281075+00:00","updated_at":"2026-07-05T01:51:36.281075+00:00"}