{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:75MREC5LIHAZXCED36BA4PYBHJ","short_pith_number":"pith:75MREC5L","schema_version":"1.0","canonical_sha256":"ff59120bab41c19b8883df820e3f013a523c2c0d1e8e8e479624244dc7fc8557","source":{"kind":"arxiv","id":"2012.07816","version":5},"attestation_state":"computed","paper":{"title":"Enabling Collaborative Data Science Development with the Ballet Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.SE"],"primary_cat":"cs.LG","authors_text":"J\\\"urgen Cito, Kalyan Veeramachaneni, Kelvin Lu, Micah J. Smith","submitted_at":"2020-12-14T18:51:23Z","abstract_excerpt":"While the open-source software development model has led to successful large-scale collaborations in building software systems, data science projects are frequently developed by individuals or small teams. We describe challenges to scaling data science collaborations and present a conceptual framework and ML programming model to address them. We instantiate these ideas in Ballet, a lightweight framework for collaborative, open-source data science through a focus on feature engineering, and an accompanying cloud-based development environment. Using our framework, collaborators incrementally pro"},"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":"2012.07816","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-14T18:51:23Z","cross_cats_sorted":["cs.HC","cs.SE"],"title_canon_sha256":"50ea6711f0500fc59c28a93403b916108553fa9962e4382728f38baedde36af9","abstract_canon_sha256":"4fbf72af9b496c0c47f75572f7d6f469da975dbda133bc7b0ef632371aa98888"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:55.662684Z","signature_b64":"zUFL4NE8hsswmYoywz2J6vF18MjNxZvhPxl6j+kCi8whx55+nmP58QeI9SK5XXDTNTkjctFjvhfmXQndbVYpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff59120bab41c19b8883df820e3f013a523c2c0d1e8e8e479624244dc7fc8557","last_reissued_at":"2026-07-05T03:24:55.662266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:55.662266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enabling Collaborative Data Science Development with the Ballet Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.SE"],"primary_cat":"cs.LG","authors_text":"J\\\"urgen Cito, Kalyan Veeramachaneni, Kelvin Lu, Micah J. Smith","submitted_at":"2020-12-14T18:51:23Z","abstract_excerpt":"While the open-source software development model has led to successful large-scale collaborations in building software systems, data science projects are frequently developed by individuals or small teams. We describe challenges to scaling data science collaborations and present a conceptual framework and ML programming model to address them. We instantiate these ideas in Ballet, a lightweight framework for collaborative, open-source data science through a focus on feature engineering, and an accompanying cloud-based development environment. Using our framework, collaborators incrementally pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07816","kind":"arxiv","version":5},"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/2012.07816/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":"2012.07816","created_at":"2026-07-05T03:24:55.662322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.07816v5","created_at":"2026-07-05T03:24:55.662322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07816","created_at":"2026-07-05T03:24:55.662322+00:00"},{"alias_kind":"pith_short_12","alias_value":"75MREC5LIHAZ","created_at":"2026-07-05T03:24:55.662322+00:00"},{"alias_kind":"pith_short_16","alias_value":"75MREC5LIHAZXCED","created_at":"2026-07-05T03:24:55.662322+00:00"},{"alias_kind":"pith_short_8","alias_value":"75MREC5L","created_at":"2026-07-05T03:24:55.662322+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/75MREC5LIHAZXCED36BA4PYBHJ","json":"https://pith.science/pith/75MREC5LIHAZXCED36BA4PYBHJ.json","graph_json":"https://pith.science/api/pith-number/75MREC5LIHAZXCED36BA4PYBHJ/graph.json","events_json":"https://pith.science/api/pith-number/75MREC5LIHAZXCED36BA4PYBHJ/events.json","paper":"https://pith.science/paper/75MREC5L"},"agent_actions":{"view_html":"https://pith.science/pith/75MREC5LIHAZXCED36BA4PYBHJ","download_json":"https://pith.science/pith/75MREC5LIHAZXCED36BA4PYBHJ.json","view_paper":"https://pith.science/paper/75MREC5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.07816&json=true","fetch_graph":"https://pith.science/api/pith-number/75MREC5LIHAZXCED36BA4PYBHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/75MREC5LIHAZXCED36BA4PYBHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75MREC5LIHAZXCED36BA4PYBHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75MREC5LIHAZXCED36BA4PYBHJ/action/storage_attestation","attest_author":"https://pith.science/pith/75MREC5LIHAZXCED36BA4PYBHJ/action/author_attestation","sign_citation":"https://pith.science/pith/75MREC5LIHAZXCED36BA4PYBHJ/action/citation_signature","submit_replication":"https://pith.science/pith/75MREC5LIHAZXCED36BA4PYBHJ/action/replication_record"}},"created_at":"2026-07-05T03:24:55.662322+00:00","updated_at":"2026-07-05T03:24:55.662322+00:00"}