{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ELQFIH5EOZWQFPVPXPSMHHNIVD","short_pith_number":"pith:ELQFIH5E","schema_version":"1.0","canonical_sha256":"22e0541fa4766d02beafbbe4c39da8a8ffd6fe13fcde2c457b0197d97effbd69","source":{"kind":"arxiv","id":"2502.12115","version":4},"attestation_state":"computed","paper":{"title":"SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Johannes Heidecke, Michele Wang, Samuel Miserendino, Tejal Patwardhan","submitted_at":"2025-02-17T18:41:16Z","abstract_excerpt":"We introduce SWE-Lancer, a benchmark of over 1,400 freelance software engineering tasks from Upwork, valued at \\$1 million USD total in real-world payouts. SWE-Lancer encompasses both independent engineering tasks--ranging from \\$50 bug fixes to \\$32,000 feature implementations--and managerial tasks, where models choose between technical implementation proposals. Independent tasks are graded with end-to-end tests triple-verified by experienced software engineers, while managerial decisions are assessed against the choices of the original hired engineering managers. We evaluate model performanc"},"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":"2502.12115","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T18:41:16Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"cc93763be4dec212b13abeb2323b65ea126b0d23b772ab67786f810bf1d0b259","abstract_canon_sha256":"d29e1160f0829934e62f2188e3aa1e9d46e97cda89a17cc868edd101513cde50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:27.335338Z","signature_b64":"nEZYjC0hOghg6Vy0yDX+XnL/FFChduWklZhP1GIQm5LsBkXSauKWZ8z7Kv7XrGsKEwYpCquanTxAKrQh6XCdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22e0541fa4766d02beafbbe4c39da8a8ffd6fe13fcde2c457b0197d97effbd69","last_reissued_at":"2026-07-05T11:12:27.334750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:27.334750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Johannes Heidecke, Michele Wang, Samuel Miserendino, Tejal Patwardhan","submitted_at":"2025-02-17T18:41:16Z","abstract_excerpt":"We introduce SWE-Lancer, a benchmark of over 1,400 freelance software engineering tasks from Upwork, valued at \\$1 million USD total in real-world payouts. SWE-Lancer encompasses both independent engineering tasks--ranging from \\$50 bug fixes to \\$32,000 feature implementations--and managerial tasks, where models choose between technical implementation proposals. Independent tasks are graded with end-to-end tests triple-verified by experienced software engineers, while managerial decisions are assessed against the choices of the original hired engineering managers. We evaluate model performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12115","kind":"arxiv","version":4},"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/2502.12115/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":"2502.12115","created_at":"2026-07-05T11:12:27.334824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12115v4","created_at":"2026-07-05T11:12:27.334824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12115","created_at":"2026-07-05T11:12:27.334824+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELQFIH5EOZWQ","created_at":"2026-07-05T11:12:27.334824+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELQFIH5EOZWQFPVP","created_at":"2026-07-05T11:12:27.334824+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELQFIH5E","created_at":"2026-07-05T11:12:27.334824+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17799","citing_title":"Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11166","citing_title":"Flaws in the LLM Automation Narrative","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00248","citing_title":"Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03829","citing_title":"BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14790","citing_title":"Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30182","citing_title":"MirrorCode: AI can rebuild entire programs from behavior alone","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25411","citing_title":"Heimdall: Formally Verified Automated Migration of Legacy eBPF Programs to Rust","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00750","citing_title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23262","citing_title":"Design and Report Benchmarks for Knowledge Work","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04601","citing_title":"Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12925","citing_title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12108","citing_title":"LLM-Based Automated Diagnosis Of Integration Test Failures At Google","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10866","citing_title":"OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05912","citing_title":"FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2507.20534","citing_title":"Kimi K2: Open Agentic Intelligence","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02244","citing_title":"The Conversations Beneath the Code: Triadic Data for Long-Horizon Software Engineering Agents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02661","citing_title":"AcademiClaw: When Students Set Challenges for AI Agents","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ELQFIH5EOZWQFPVPXPSMHHNIVD","json":"https://pith.science/pith/ELQFIH5EOZWQFPVPXPSMHHNIVD.json","graph_json":"https://pith.science/api/pith-number/ELQFIH5EOZWQFPVPXPSMHHNIVD/graph.json","events_json":"https://pith.science/api/pith-number/ELQFIH5EOZWQFPVPXPSMHHNIVD/events.json","paper":"https://pith.science/paper/ELQFIH5E"},"agent_actions":{"view_html":"https://pith.science/pith/ELQFIH5EOZWQFPVPXPSMHHNIVD","download_json":"https://pith.science/pith/ELQFIH5EOZWQFPVPXPSMHHNIVD.json","view_paper":"https://pith.science/paper/ELQFIH5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12115&json=true","fetch_graph":"https://pith.science/api/pith-number/ELQFIH5EOZWQFPVPXPSMHHNIVD/graph.json","fetch_events":"https://pith.science/api/pith-number/ELQFIH5EOZWQFPVPXPSMHHNIVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELQFIH5EOZWQFPVPXPSMHHNIVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELQFIH5EOZWQFPVPXPSMHHNIVD/action/storage_attestation","attest_author":"https://pith.science/pith/ELQFIH5EOZWQFPVPXPSMHHNIVD/action/author_attestation","sign_citation":"https://pith.science/pith/ELQFIH5EOZWQFPVPXPSMHHNIVD/action/citation_signature","submit_replication":"https://pith.science/pith/ELQFIH5EOZWQFPVPXPSMHHNIVD/action/replication_record"}},"created_at":"2026-07-05T11:12:27.334824+00:00","updated_at":"2026-07-05T11:12:27.334824+00:00"}