{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FMEI6E6B4BNOJQQIXG2XTSJACC","short_pith_number":"pith:FMEI6E6B","schema_version":"1.0","canonical_sha256":"2b088f13c1e05ae4c208b9b579c920109b08ff84cb0c76402a6b75b4793d82cf","source":{"kind":"arxiv","id":"2206.15000","version":3},"attestation_state":"computed","paper":{"title":"Grounded Copilot: How Programmers Interact with Code-Generating Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.HC","authors_text":"Michael B. James, Nadia Polikarpova, Shraddha Barke","submitted_at":"2022-06-30T03:18:03Z","abstract_excerpt":"Powered by recent advances in code-generating models, AI assistants like Github Copilot promise to change the face of programming forever. But what is this new face of programming? We present the first grounded theory analysis of how programmers interact with Copilot, based on observing 20 participants--with a range of prior experience using the assistant--as they solve diverse programming tasks across four languages. Our main finding is that interactions with programming assistants are bimodal: in acceleration mode, the programmer knows what to do next and uses Copilot to get there faster; in"},"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":"2206.15000","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2022-06-30T03:18:03Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"5809cdc0350299cd4db10c1247677e53d73c966b9593a7b537b2f73589ebbedf","abstract_canon_sha256":"15dcbd1881d65e6a2d349867f686a3876f29da69fed86842b4203dc09d623a48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:02.948081Z","signature_b64":"99h5/T0Jg6DTLDxkslZZZPbUlFigtzqd3m98FTI9Qr1SBmVAdNxZYtu0iQgHBNpD5LSBuwORlx3jMs+wyEmPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b088f13c1e05ae4c208b9b579c920109b08ff84cb0c76402a6b75b4793d82cf","last_reissued_at":"2026-07-05T05:12:02.947676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:02.947676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounded Copilot: How Programmers Interact with Code-Generating Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.HC","authors_text":"Michael B. James, Nadia Polikarpova, Shraddha Barke","submitted_at":"2022-06-30T03:18:03Z","abstract_excerpt":"Powered by recent advances in code-generating models, AI assistants like Github Copilot promise to change the face of programming forever. But what is this new face of programming? We present the first grounded theory analysis of how programmers interact with Copilot, based on observing 20 participants--with a range of prior experience using the assistant--as they solve diverse programming tasks across four languages. Our main finding is that interactions with programming assistants are bimodal: in acceleration mode, the programmer knows what to do next and uses Copilot to get there faster; in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15000","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/2206.15000/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":"2206.15000","created_at":"2026-07-05T05:12:02.947727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.15000v3","created_at":"2026-07-05T05:12:02.947727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15000","created_at":"2026-07-05T05:12:02.947727+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMEI6E6B4BNO","created_at":"2026-07-05T05:12:02.947727+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMEI6E6B4BNOJQQI","created_at":"2026-07-05T05:12:02.947727+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMEI6E6B","created_at":"2026-07-05T05:12:02.947727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26173","citing_title":"AlgoEvolve: LLM-driven Meta-evolution of Algorithmic Trading Programs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06921","citing_title":"Teaching Astronomy with Large Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18334","citing_title":"Reliability of AI Bots Footprints in GitHub Actions CI/CD Workflows","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FMEI6E6B4BNOJQQIXG2XTSJACC","json":"https://pith.science/pith/FMEI6E6B4BNOJQQIXG2XTSJACC.json","graph_json":"https://pith.science/api/pith-number/FMEI6E6B4BNOJQQIXG2XTSJACC/graph.json","events_json":"https://pith.science/api/pith-number/FMEI6E6B4BNOJQQIXG2XTSJACC/events.json","paper":"https://pith.science/paper/FMEI6E6B"},"agent_actions":{"view_html":"https://pith.science/pith/FMEI6E6B4BNOJQQIXG2XTSJACC","download_json":"https://pith.science/pith/FMEI6E6B4BNOJQQIXG2XTSJACC.json","view_paper":"https://pith.science/paper/FMEI6E6B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.15000&json=true","fetch_graph":"https://pith.science/api/pith-number/FMEI6E6B4BNOJQQIXG2XTSJACC/graph.json","fetch_events":"https://pith.science/api/pith-number/FMEI6E6B4BNOJQQIXG2XTSJACC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMEI6E6B4BNOJQQIXG2XTSJACC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMEI6E6B4BNOJQQIXG2XTSJACC/action/storage_attestation","attest_author":"https://pith.science/pith/FMEI6E6B4BNOJQQIXG2XTSJACC/action/author_attestation","sign_citation":"https://pith.science/pith/FMEI6E6B4BNOJQQIXG2XTSJACC/action/citation_signature","submit_replication":"https://pith.science/pith/FMEI6E6B4BNOJQQIXG2XTSJACC/action/replication_record"}},"created_at":"2026-07-05T05:12:02.947727+00:00","updated_at":"2026-07-05T05:12:02.947727+00:00"}