{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZJZA7RCM6VHFB5LFXKYASMM4TG","short_pith_number":"pith:ZJZA7RCM","schema_version":"1.0","canonical_sha256":"ca720fc44cf54e50f565bab009319c99afe51ab29498b6ddf06e63bf78b67ae2","source":{"kind":"arxiv","id":"2507.15003","version":1},"attestation_state":"computed","paper":{"title":"The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping Software Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AIDev supplies the first large-scale dataset of 456,000 real pull requests from five autonomous coding agents to ground study of AI teammates in software development.","cross_cats":["cs.AI","cs.CE","cs.LG"],"primary_cat":"cs.SE","authors_text":"Ahmed E. Hassan, Hao Li, Haoxiang Zhang","submitted_at":"2025-07-20T15:15:58Z","abstract_excerpt":"The future of software engineering--SE 3.0--is unfolding with the rise of AI teammates: autonomous, goal-driven systems collaborating with human developers. Among these, autonomous coding agents are especially transformative, now actively initiating, reviewing, and evolving code at scale. This paper introduces AIDev, the first large-scale dataset capturing how such agents operate in the wild. Spanning over 456,000 pull requests by five leading agents--OpenAI Codex, Devin, GitHub Copilot, Cursor, and Claude Code--across 61,000 repositories and 47,000 developers, AIDev provides an unprecedented "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2507.15003","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-07-20T15:15:58Z","cross_cats_sorted":["cs.AI","cs.CE","cs.LG"],"title_canon_sha256":"3b9664f850f1d53c86b06929b5687763eb75ed5d400c99aae46b421ccc8cb53f","abstract_canon_sha256":"ac90786921648937088c23af9aa396e242626e0ba202d8a3d6906974fc44b045"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.697228Z","signature_b64":"yy1UCvVhJZVRnyBWxqNCBOUA+eKWLKzTOkhB+vfy0QrHTW6zFxEBxQuZyMhoiMfWObvgpP7GyUt4UySzCWydAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca720fc44cf54e50f565bab009319c99afe51ab29498b6ddf06e63bf78b67ae2","last_reissued_at":"2026-05-17T23:38:50.696599Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.696599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping Software Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AIDev supplies the first large-scale dataset of 456,000 real pull requests from five autonomous coding agents to ground study of AI teammates in software development.","cross_cats":["cs.AI","cs.CE","cs.LG"],"primary_cat":"cs.SE","authors_text":"Ahmed E. Hassan, Hao Li, Haoxiang Zhang","submitted_at":"2025-07-20T15:15:58Z","abstract_excerpt":"The future of software engineering--SE 3.0--is unfolding with the rise of AI teammates: autonomous, goal-driven systems collaborating with human developers. Among these, autonomous coding agents are especially transformative, now actively initiating, reviewing, and evolving code at scale. This paper introduces AIDev, the first large-scale dataset capturing how such agents operate in the wild. Spanning over 456,000 pull requests by five leading agents--OpenAI Codex, Devin, GitHub Copilot, Cursor, and Claude Code--across 61,000 repositories and 47,000 developers, AIDev provides an unprecedented "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"AIDev provides an unprecedented empirical foundation for studying autonomous teammates in software development, enabling research in benchmarking, agent readiness, optimization, collaboration modeling, and AI governance beyond synthetic benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The collected pull requests accurately represent typical in-the-wild agent behavior without major selection bias from the five chosen agents or the repositories that expose their activity.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AIDev is a new open dataset of 456k AI-agent pull requests showing agents submit code faster than humans but with lower acceptance rates and simpler changes.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AIDev supplies the first large-scale dataset of 456,000 real pull requests from five autonomous coding agents to ground study of AI teammates in software development.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d3f6b38d22f72f943a304b522feca0ae6cfe54c3df3cf3f9b91431e00e62d2ad"},"source":{"id":"2507.15003","kind":"arxiv","version":1},"verdict":{"id":"dafd4420-85cd-40e6-a794-76c2de7b0c6e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T17:33:33.499204Z","strongest_claim":"AIDev provides an unprecedented empirical foundation for studying autonomous teammates in software development, enabling research in benchmarking, agent readiness, optimization, collaboration modeling, and AI governance beyond synthetic benchmarks.","one_line_summary":"AIDev is a new open dataset of 456k AI-agent pull requests showing agents submit code faster than humans but with lower acceptance rates and simpler changes.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The collected pull requests accurately represent typical in-the-wild agent behavior without major selection bias from the five chosen agents or the repositories that expose their activity.","pith_extraction_headline":"AIDev supplies the first large-scale dataset of 456,000 real pull requests from five autonomous coding agents to ground study of AI teammates in software development."},"references":{"count":37,"sample":[{"doi":"","year":2025,"title":"[n. d.]. Introducing Codex. https://openai.com/index/introducing-codex/. [Accessed 07-07-2025]","work_id":"f377b901-8bf3-4329-952e-a7d652f6d4a2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"[n. d.]. Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity. https://metr.org/blog/2025-07-10-early-2025- ai-experienced-os-dev-study/. [Accessed 17-07-2025]","work_id":"bd928b87-8770-4027-b4e0-299981a62e16","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/msr66628.2025.00086","year":2025,"title":"Prompting in the wild: An empirical study of prompt evolution in software repositories","work_id":"52282e0f-2551-44cd-8740-aeb6b8647f0f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"arXiv preprint arXiv:2506.14683 , year=","work_id":"01fd03b1-426c-4c4e-bc63-b8db16574f87","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Viraat Aryabumi, Yixuan Su, Raymond Ma, Adrien Morisot, Ivan Zhang, Acyr Locatelli, Marzieh Fadaee, Ahmet Üstün, and Sara Hooker. 2025. To Code or Not To Code? Exploring Impact of Code in Pre-training","work_id":"df207421-4809-49de-8751-862cd12820f3","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":37,"snapshot_sha256":"242e5f551de4f70df6054347dd1a76212f3f90a4ad147a21c9acfd915575685b","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"37dcc004eff648f3be42977d22bd38f41a974ff2554afc38e7814717a916dafd"},"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":"2507.15003","created_at":"2026-05-17T23:38:50.696702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.15003v1","created_at":"2026-05-17T23:38:50.696702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15003","created_at":"2026-05-17T23:38:50.696702+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJZA7RCM6VHF","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJZA7RCM6VHFB5LF","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJZA7RCM","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":28,"sample":[{"citing_arxiv_id":"2605.08380","citing_title":"What Software Engineering Looks Like to AI Agents? -- An Empirical Study of AI-Only Technical Discourse on MoltBook","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22534","citing_title":"Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21453","citing_title":"Quality and Security Signals in AI-Generated Python Refactoring Pull Requests","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2601.17581","citing_title":"How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2602.00496","citing_title":"From Junior to Senior: Allocating Agency and Navigating Professional Growth in Agentic AI-Mediated Software Engineering","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2602.02934","citing_title":"AgenticSZZ: Temporal Knowledge Graph-Guided Agentic Bug-Inducing Commit Identification","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08915","citing_title":"Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2602.17955","citing_title":"Mining Type Constructs Using Patterns in AI-Generated Code","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16323","citing_title":"Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2603.06847","citing_title":"Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2603.18916","citing_title":"Agentic Business Process Management: A Research Manifesto","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2603.27130","citing_title":"A Large-Scale Empirical Study of AI-Generated Code in Real-World Repositories","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03551","citing_title":"AgenticFlict: A Large-Scale Dataset of Merge Conflicts in AI Coding Agent Pull Requests on GitHub","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12746","citing_title":"CoT-Guard: Small Models for Strong Monitoring","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03196","citing_title":"From Industry Claims to Empirical Reality: An Empirical Study of Code Review Agents in Pull Requests","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26892","citing_title":"Hot Fixing in the Wild","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06464","citing_title":"To What Extent Does Agent-generated Code Require Maintenance? An Empirical Study","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24450","citing_title":"On the Footprints of Reviewer Bots Feedback on Agentic Pull Requests in OSS GitHub Repositories","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23822","citing_title":"KISS Sorcar: A Stupidly-Simple General-Purpose and Software Engineering AI Assistant","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06464","citing_title":"To What Extent Does Agent-generated Code Require Maintenance? An Empirical Study","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19965","citing_title":"Insights into Security-Related AI-Generated Pull Requests","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12048","citing_title":"ORBIT: Guided Agentic Orchestration for Autonomous C-to-Rust Transpilation","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09409","citing_title":"Do AI Coding Agents Log Like Humans? An Empirical Study","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13103","citing_title":"Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06373","citing_title":"Beyond Functional Correctness: Design Issues in AI IDE-Generated Large-Scale Projects","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJZA7RCM6VHFB5LFXKYASMM4TG","json":"https://pith.science/pith/ZJZA7RCM6VHFB5LFXKYASMM4TG.json","graph_json":"https://pith.science/api/pith-number/ZJZA7RCM6VHFB5LFXKYASMM4TG/graph.json","events_json":"https://pith.science/api/pith-number/ZJZA7RCM6VHFB5LFXKYASMM4TG/events.json","paper":"https://pith.science/paper/ZJZA7RCM"},"agent_actions":{"view_html":"https://pith.science/pith/ZJZA7RCM6VHFB5LFXKYASMM4TG","download_json":"https://pith.science/pith/ZJZA7RCM6VHFB5LFXKYASMM4TG.json","view_paper":"https://pith.science/paper/ZJZA7RCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.15003&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJZA7RCM6VHFB5LFXKYASMM4TG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJZA7RCM6VHFB5LFXKYASMM4TG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJZA7RCM6VHFB5LFXKYASMM4TG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJZA7RCM6VHFB5LFXKYASMM4TG/action/storage_attestation","attest_author":"https://pith.science/pith/ZJZA7RCM6VHFB5LFXKYASMM4TG/action/author_attestation","sign_citation":"https://pith.science/pith/ZJZA7RCM6VHFB5LFXKYASMM4TG/action/citation_signature","submit_replication":"https://pith.science/pith/ZJZA7RCM6VHFB5LFXKYASMM4TG/action/replication_record"}},"created_at":"2026-05-17T23:38:50.696702+00:00","updated_at":"2026-05-17T23:38:50.696702+00:00"}