{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B26E4NR26NE4XGL6Q7QMOFPKIT","short_pith_number":"pith:B26E4NR2","schema_version":"1.0","canonical_sha256":"0ebc4e363af349cb997e87e0c715ea44de78c3ef4db38cd214ed95084f4caf57","source":{"kind":"arxiv","id":"2310.16164","version":1},"attestation_state":"computed","paper":{"title":"Conversational Challenges in AI-Powered Data Science: Obstacles, Needs, and Design Opportunities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Ananya Singha, Anna Fariha, Ashish Tiwari, Austin Z. Henley, Bhavya Chopra, Chris Parnin, Sumit Gulwani","submitted_at":"2023-10-24T20:19:07Z","abstract_excerpt":"Large Language Models (LLMs) are being increasingly employed in data science for tasks like data preprocessing and analytics. However, data scientists encounter substantial obstacles when conversing with LLM-powered chatbots and acting on their suggestions and answers. We conducted a mixed-methods study, including contextual observations, semi-structured interviews (n=14), and a survey (n=114), to identify these challenges. Our findings highlight key issues faced by data scientists, including contextual data retrieval, formulating prompts for complex tasks, adapting generated code to local env"},"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":"2310.16164","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2023-10-24T20:19:07Z","cross_cats_sorted":[],"title_canon_sha256":"e3b81f1a38c83b1707e6ffa091920a0d5e5629daeb03c973c72bd7d02e6da935","abstract_canon_sha256":"ac964cbb4c4d0d967ff0a1741d057884517c7fd85f8efbf1d702df483a523704"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:53.391734Z","signature_b64":"1HD6lfaEJwQTVJZP/8di5s5LPjSc+u86KnBpKdJ5L85B0FCsXJ1VQAQRKCsptxFa7s95RCACr0wOVxB4WEUeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ebc4e363af349cb997e87e0c715ea44de78c3ef4db38cd214ed95084f4caf57","last_reissued_at":"2026-07-05T07:04:53.391215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:53.391215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conversational Challenges in AI-Powered Data Science: Obstacles, Needs, and Design Opportunities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Ananya Singha, Anna Fariha, Ashish Tiwari, Austin Z. Henley, Bhavya Chopra, Chris Parnin, Sumit Gulwani","submitted_at":"2023-10-24T20:19:07Z","abstract_excerpt":"Large Language Models (LLMs) are being increasingly employed in data science for tasks like data preprocessing and analytics. However, data scientists encounter substantial obstacles when conversing with LLM-powered chatbots and acting on their suggestions and answers. We conducted a mixed-methods study, including contextual observations, semi-structured interviews (n=14), and a survey (n=114), to identify these challenges. Our findings highlight key issues faced by data scientists, including contextual data retrieval, formulating prompts for complex tasks, adapting generated code to local env"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16164","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/2310.16164/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":"2310.16164","created_at":"2026-07-05T07:04:53.391278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16164v1","created_at":"2026-07-05T07:04:53.391278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16164","created_at":"2026-07-05T07:04:53.391278+00:00"},{"alias_kind":"pith_short_12","alias_value":"B26E4NR26NE4","created_at":"2026-07-05T07:04:53.391278+00:00"},{"alias_kind":"pith_short_16","alias_value":"B26E4NR26NE4XGL6","created_at":"2026-07-05T07:04:53.391278+00:00"},{"alias_kind":"pith_short_8","alias_value":"B26E4NR2","created_at":"2026-07-05T07:04:53.391278+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.01026","citing_title":"Understanding the Human-LLM Dynamic: A Literature Survey of LLM Use in Programming Tasks","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08898","citing_title":"Omakase: proactive assistance with actionable suggestions for evolving scientific research projects","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B26E4NR26NE4XGL6Q7QMOFPKIT","json":"https://pith.science/pith/B26E4NR26NE4XGL6Q7QMOFPKIT.json","graph_json":"https://pith.science/api/pith-number/B26E4NR26NE4XGL6Q7QMOFPKIT/graph.json","events_json":"https://pith.science/api/pith-number/B26E4NR26NE4XGL6Q7QMOFPKIT/events.json","paper":"https://pith.science/paper/B26E4NR2"},"agent_actions":{"view_html":"https://pith.science/pith/B26E4NR26NE4XGL6Q7QMOFPKIT","download_json":"https://pith.science/pith/B26E4NR26NE4XGL6Q7QMOFPKIT.json","view_paper":"https://pith.science/paper/B26E4NR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16164&json=true","fetch_graph":"https://pith.science/api/pith-number/B26E4NR26NE4XGL6Q7QMOFPKIT/graph.json","fetch_events":"https://pith.science/api/pith-number/B26E4NR26NE4XGL6Q7QMOFPKIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B26E4NR26NE4XGL6Q7QMOFPKIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B26E4NR26NE4XGL6Q7QMOFPKIT/action/storage_attestation","attest_author":"https://pith.science/pith/B26E4NR26NE4XGL6Q7QMOFPKIT/action/author_attestation","sign_citation":"https://pith.science/pith/B26E4NR26NE4XGL6Q7QMOFPKIT/action/citation_signature","submit_replication":"https://pith.science/pith/B26E4NR26NE4XGL6Q7QMOFPKIT/action/replication_record"}},"created_at":"2026-07-05T07:04:53.391278+00:00","updated_at":"2026-07-05T07:04:53.391278+00:00"}