{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SEIMDY3OUOJWK32GSOPGBKYCOW","short_pith_number":"pith:SEIMDY3O","schema_version":"1.0","canonical_sha256":"9110c1e36ea393656f46939e60ab0275940018b689b969feb4f6ec45fee77204","source":{"kind":"arxiv","id":"2001.06684","version":3},"attestation_state":"computed","paper":{"title":"How do Data Science Workers Collaborate? Roles, Workflows, and Tools","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SE","stat.ML"],"primary_cat":"cs.HC","authors_text":"Amy X. Zhang, Dakuo Wang, Michael Muller","submitted_at":"2020-01-18T15:11:56Z","abstract_excerpt":"Today, the prominence of data science within organizations has given rise to teams of data science workers collaborating on extracting insights from data, as opposed to individual data scientists working alone. However, we still lack a deep understanding of how data science workers collaborate in practice. In this work, we conducted an online survey with 183 participants who work in various aspects of data science. We focused on their reported interactions with each other (e.g., managers with engineers) and with different tools (e.g., Jupyter Notebook). We found that data science teams are ext"},"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":"2001.06684","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2020-01-18T15:11:56Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SE","stat.ML"],"title_canon_sha256":"91ad99676d729865725127b6de5adef7e9374a4f49d55b23b317457e475d4a5a","abstract_canon_sha256":"15f5409022ecaf54657864100f07275ac69264b5e52f956eba4672f98385b46a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:55:30.388382Z","signature_b64":"QwyDxPCkVxBdd17VI0UaqmoqS2RT7UT8RkU/sMXhRezR3Kd2qiTaQ8jRzOgn9/iKGUvEk1JcDnAGdvW+DiiFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9110c1e36ea393656f46939e60ab0275940018b689b969feb4f6ec45fee77204","last_reissued_at":"2026-07-05T00:55:30.387922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:55:30.387922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How do Data Science Workers Collaborate? Roles, Workflows, and Tools","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SE","stat.ML"],"primary_cat":"cs.HC","authors_text":"Amy X. Zhang, Dakuo Wang, Michael Muller","submitted_at":"2020-01-18T15:11:56Z","abstract_excerpt":"Today, the prominence of data science within organizations has given rise to teams of data science workers collaborating on extracting insights from data, as opposed to individual data scientists working alone. However, we still lack a deep understanding of how data science workers collaborate in practice. In this work, we conducted an online survey with 183 participants who work in various aspects of data science. We focused on their reported interactions with each other (e.g., managers with engineers) and with different tools (e.g., Jupyter Notebook). We found that data science teams are ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.06684","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.06684/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":"2001.06684","created_at":"2026-07-05T00:55:30.387981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.06684v3","created_at":"2026-07-05T00:55:30.387981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.06684","created_at":"2026-07-05T00:55:30.387981+00:00"},{"alias_kind":"pith_short_12","alias_value":"SEIMDY3OUOJW","created_at":"2026-07-05T00:55:30.387981+00:00"},{"alias_kind":"pith_short_16","alias_value":"SEIMDY3OUOJWK32G","created_at":"2026-07-05T00:55:30.387981+00:00"},{"alias_kind":"pith_short_8","alias_value":"SEIMDY3O","created_at":"2026-07-05T00:55:30.387981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.12225","citing_title":"Characterizing Data Scientists in the Real World","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SEIMDY3OUOJWK32GSOPGBKYCOW","json":"https://pith.science/pith/SEIMDY3OUOJWK32GSOPGBKYCOW.json","graph_json":"https://pith.science/api/pith-number/SEIMDY3OUOJWK32GSOPGBKYCOW/graph.json","events_json":"https://pith.science/api/pith-number/SEIMDY3OUOJWK32GSOPGBKYCOW/events.json","paper":"https://pith.science/paper/SEIMDY3O"},"agent_actions":{"view_html":"https://pith.science/pith/SEIMDY3OUOJWK32GSOPGBKYCOW","download_json":"https://pith.science/pith/SEIMDY3OUOJWK32GSOPGBKYCOW.json","view_paper":"https://pith.science/paper/SEIMDY3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.06684&json=true","fetch_graph":"https://pith.science/api/pith-number/SEIMDY3OUOJWK32GSOPGBKYCOW/graph.json","fetch_events":"https://pith.science/api/pith-number/SEIMDY3OUOJWK32GSOPGBKYCOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SEIMDY3OUOJWK32GSOPGBKYCOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SEIMDY3OUOJWK32GSOPGBKYCOW/action/storage_attestation","attest_author":"https://pith.science/pith/SEIMDY3OUOJWK32GSOPGBKYCOW/action/author_attestation","sign_citation":"https://pith.science/pith/SEIMDY3OUOJWK32GSOPGBKYCOW/action/citation_signature","submit_replication":"https://pith.science/pith/SEIMDY3OUOJWK32GSOPGBKYCOW/action/replication_record"}},"created_at":"2026-07-05T00:55:30.387981+00:00","updated_at":"2026-07-05T00:55:30.387981+00:00"}