{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:C4OBUISQTL6G5KMB4YTQNOJQXM","short_pith_number":"pith:C4OBUISQ","schema_version":"1.0","canonical_sha256":"171c1a22509afc6ea981e62706b930bb25de3c34a887024e89e7e2097b9cbf45","source":{"kind":"arxiv","id":"1708.07073","version":3},"attestation_state":"computed","paper":{"title":"A Grammar for Reproducible and Painless Extract-Transform-Load Operations on Medium Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Benjamin S. Baumer","submitted_at":"2017-08-23T16:05:32Z","abstract_excerpt":"Many interesting data sets available on the Internet are of a medium size---too big to fit into a personal computer's memory, but not so large that they won't fit comfortably on its hard disk. In the coming years, data sets of this magnitude will inform vital research in a wide array of application domains. However, due to a variety of constraints they are cumbersome to ingest, wrangle, analyze, and share in a reproducible fashion. These obstructions hamper thorough peer-review and thus disrupt the forward progress of science. We propose a predictable and pipeable framework for R (the state-of"},"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":"1708.07073","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2017-08-23T16:05:32Z","cross_cats_sorted":[],"title_canon_sha256":"0fbb68d919f6994b8375a753a0f4b1aedc29c04273d99ffecaaf95d256318eee","abstract_canon_sha256":"3758af778e2d9298f074a2e77532b9b43ebee4616a0a4e5605e9344b57bcf48f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:10.289384Z","signature_b64":"ugguIu7xbyqJ2TOIDf17uyuaGmQddJ6sx5xeOptbyDO+L0UNWvm1QtIkbewhzvW76aCBsoan+CmtijYv+BtTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"171c1a22509afc6ea981e62706b930bb25de3c34a887024e89e7e2097b9cbf45","last_reissued_at":"2026-05-18T00:15:10.288557Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:10.288557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Grammar for Reproducible and Painless Extract-Transform-Load Operations on Medium Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Benjamin S. Baumer","submitted_at":"2017-08-23T16:05:32Z","abstract_excerpt":"Many interesting data sets available on the Internet are of a medium size---too big to fit into a personal computer's memory, but not so large that they won't fit comfortably on its hard disk. In the coming years, data sets of this magnitude will inform vital research in a wide array of application domains. However, due to a variety of constraints they are cumbersome to ingest, wrangle, analyze, and share in a reproducible fashion. These obstructions hamper thorough peer-review and thus disrupt the forward progress of science. We propose a predictable and pipeable framework for R (the state-of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.07073","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1708.07073","created_at":"2026-05-18T00:15:10.288695+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.07073v3","created_at":"2026-05-18T00:15:10.288695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.07073","created_at":"2026-05-18T00:15:10.288695+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4OBUISQTL6G","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4OBUISQTL6G5KMB","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4OBUISQ","created_at":"2026-05-18T12:31:08.081275+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/C4OBUISQTL6G5KMB4YTQNOJQXM","json":"https://pith.science/pith/C4OBUISQTL6G5KMB4YTQNOJQXM.json","graph_json":"https://pith.science/api/pith-number/C4OBUISQTL6G5KMB4YTQNOJQXM/graph.json","events_json":"https://pith.science/api/pith-number/C4OBUISQTL6G5KMB4YTQNOJQXM/events.json","paper":"https://pith.science/paper/C4OBUISQ"},"agent_actions":{"view_html":"https://pith.science/pith/C4OBUISQTL6G5KMB4YTQNOJQXM","download_json":"https://pith.science/pith/C4OBUISQTL6G5KMB4YTQNOJQXM.json","view_paper":"https://pith.science/paper/C4OBUISQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.07073&json=true","fetch_graph":"https://pith.science/api/pith-number/C4OBUISQTL6G5KMB4YTQNOJQXM/graph.json","fetch_events":"https://pith.science/api/pith-number/C4OBUISQTL6G5KMB4YTQNOJQXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4OBUISQTL6G5KMB4YTQNOJQXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4OBUISQTL6G5KMB4YTQNOJQXM/action/storage_attestation","attest_author":"https://pith.science/pith/C4OBUISQTL6G5KMB4YTQNOJQXM/action/author_attestation","sign_citation":"https://pith.science/pith/C4OBUISQTL6G5KMB4YTQNOJQXM/action/citation_signature","submit_replication":"https://pith.science/pith/C4OBUISQTL6G5KMB4YTQNOJQXM/action/replication_record"}},"created_at":"2026-05-18T00:15:10.288695+00:00","updated_at":"2026-05-18T00:15:10.288695+00:00"}