{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I7TTSCBBDITVS7DPRSYLG7JG6L","short_pith_number":"pith:I7TTSCBB","schema_version":"1.0","canonical_sha256":"47e73908211a27597c6f8cb0b37d26f2e722c6a8c207ab5420114c9da2fbeb0d","source":{"kind":"arxiv","id":"2405.02260","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Large Language Models to Enhance Domain Expert Inclusion in Data Science Workflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Hariharan Subramonyam, Jasmine Y. Shih, Vishal Mohanty, Yannis Katsis","submitted_at":"2024-05-03T17:22:15Z","abstract_excerpt":"Domain experts can play a crucial role in guiding data scientists to optimize machine learning models while ensuring contextual relevance for downstream use. However, in current workflows, such collaboration is challenging due to differing expertise, abstract documentation practices, and lack of access and visibility into low-level implementation artifacts. To address these challenges and enable domain expert participation, we introduce CellSync, a collaboration framework comprising (1) a Jupyter Notebook extension that continuously tracks changes to dataframes and model metrics and (2) a Larg"},"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":"2405.02260","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-05-03T17:22:15Z","cross_cats_sorted":[],"title_canon_sha256":"8a0db2d8359edd19f2b4bbf80f6f37790c730fdf06288735569a47c5ea5e1aa8","abstract_canon_sha256":"b4a53fb8eb2b419214a160b9a1bc71dc34e5687c1137aab196594981419792d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:09.112897Z","signature_b64":"KaickxkWtvkRRQWhuU+p1MDX56TMBA+0oOY8B0i7G45IYMJF9KXkMCXzBDOMfXNtay6xXuTWwP09YfziiWO4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47e73908211a27597c6f8cb0b37d26f2e722c6a8c207ab5420114c9da2fbeb0d","last_reissued_at":"2026-07-05T08:15:09.112493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:09.112493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Large Language Models to Enhance Domain Expert Inclusion in Data Science Workflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Hariharan Subramonyam, Jasmine Y. Shih, Vishal Mohanty, Yannis Katsis","submitted_at":"2024-05-03T17:22:15Z","abstract_excerpt":"Domain experts can play a crucial role in guiding data scientists to optimize machine learning models while ensuring contextual relevance for downstream use. However, in current workflows, such collaboration is challenging due to differing expertise, abstract documentation practices, and lack of access and visibility into low-level implementation artifacts. To address these challenges and enable domain expert participation, we introduce CellSync, a collaboration framework comprising (1) a Jupyter Notebook extension that continuously tracks changes to dataframes and model metrics and (2) a Larg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02260","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/2405.02260/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":"2405.02260","created_at":"2026-07-05T08:15:09.112554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02260v1","created_at":"2026-07-05T08:15:09.112554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02260","created_at":"2026-07-05T08:15:09.112554+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7TTSCBBDITV","created_at":"2026-07-05T08:15:09.112554+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7TTSCBBDITVS7DP","created_at":"2026-07-05T08:15:09.112554+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7TTSCBB","created_at":"2026-07-05T08:15:09.112554+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/I7TTSCBBDITVS7DPRSYLG7JG6L","json":"https://pith.science/pith/I7TTSCBBDITVS7DPRSYLG7JG6L.json","graph_json":"https://pith.science/api/pith-number/I7TTSCBBDITVS7DPRSYLG7JG6L/graph.json","events_json":"https://pith.science/api/pith-number/I7TTSCBBDITVS7DPRSYLG7JG6L/events.json","paper":"https://pith.science/paper/I7TTSCBB"},"agent_actions":{"view_html":"https://pith.science/pith/I7TTSCBBDITVS7DPRSYLG7JG6L","download_json":"https://pith.science/pith/I7TTSCBBDITVS7DPRSYLG7JG6L.json","view_paper":"https://pith.science/paper/I7TTSCBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02260&json=true","fetch_graph":"https://pith.science/api/pith-number/I7TTSCBBDITVS7DPRSYLG7JG6L/graph.json","fetch_events":"https://pith.science/api/pith-number/I7TTSCBBDITVS7DPRSYLG7JG6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7TTSCBBDITVS7DPRSYLG7JG6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7TTSCBBDITVS7DPRSYLG7JG6L/action/storage_attestation","attest_author":"https://pith.science/pith/I7TTSCBBDITVS7DPRSYLG7JG6L/action/author_attestation","sign_citation":"https://pith.science/pith/I7TTSCBBDITVS7DPRSYLG7JG6L/action/citation_signature","submit_replication":"https://pith.science/pith/I7TTSCBBDITVS7DPRSYLG7JG6L/action/replication_record"}},"created_at":"2026-07-05T08:15:09.112554+00:00","updated_at":"2026-07-05T08:15:09.112554+00:00"}