{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ELQFIH5EOZWQFPVPXPSMHHNIVD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d29e1160f0829934e62f2188e3aa1e9d46e97cda89a17cc868edd101513cde50","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T18:41:16Z","title_canon_sha256":"cc93763be4dec212b13abeb2323b65ea126b0d23b772ab67786f810bf1d0b259"},"schema_version":"1.0","source":{"id":"2502.12115","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12115","created_at":"2026-07-05T11:12:27Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12115v4","created_at":"2026-07-05T11:12:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12115","created_at":"2026-07-05T11:12:27Z"},{"alias_kind":"pith_short_12","alias_value":"ELQFIH5EOZWQ","created_at":"2026-07-05T11:12:27Z"},{"alias_kind":"pith_short_16","alias_value":"ELQFIH5EOZWQFPVP","created_at":"2026-07-05T11:12:27Z"},{"alias_kind":"pith_short_8","alias_value":"ELQFIH5E","created_at":"2026-07-05T11:12:27Z"}],"graph_snapshots":[{"event_id":"sha256:31660242da1a698abe457b10084f0da5070853089498876ee1839f9b12617914","target":"graph","created_at":"2026-07-05T11:12:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.12115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Johannes Heidecke, Michele Wang, Samuel Miserendino, Tejal Patwardhan","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T18:41:16Z","title":"SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12115","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:00a0f1e85167107f9fede17fc796fdb2eec48d62851ada6781f1f99b74ad469e","target":"record","created_at":"2026-07-05T11:12:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d29e1160f0829934e62f2188e3aa1e9d46e97cda89a17cc868edd101513cde50","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T18:41:16Z","title_canon_sha256":"cc93763be4dec212b13abeb2323b65ea126b0d23b772ab67786f810bf1d0b259"},"schema_version":"1.0","source":{"id":"2502.12115","kind":"arxiv","version":4}},"canonical_sha256":"22e0541fa4766d02beafbbe4c39da8a8ffd6fe13fcde2c457b0197d97effbd69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22e0541fa4766d02beafbbe4c39da8a8ffd6fe13fcde2c457b0197d97effbd69","first_computed_at":"2026-07-05T11:12:27.334750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:27.334750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nEZYjC0hOghg6Vy0yDX+XnL/FFChduWklZhP1GIQm5LsBkXSauKWZ8z7Kv7XrGsKEwYpCquanTxAKrQh6XCdBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:27.335338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12115","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00a0f1e85167107f9fede17fc796fdb2eec48d62851ada6781f1f99b74ad469e","sha256:31660242da1a698abe457b10084f0da5070853089498876ee1839f9b12617914"],"state_sha256":"c29ac3bf55cace2967c075e4a6d1a73c8d81c08ee7aace0c92eac480c9fa7f77"}