{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LVIF2CDCVEMAT56A6MVCSEPCWN","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":"e702d008f561eedce194021837e05019ec617f99f259f86da88efe27237db942","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-18T17:59:31Z","title_canon_sha256":"bc9b28b5968b80a4075a2ad5e4e139cc5c7d55e38872bcdda7135c58a6c4fe2f"},"schema_version":"1.0","source":{"id":"2503.14499","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14499","created_at":"2026-07-14T00:18:18Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14499v4","created_at":"2026-07-14T00:18:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14499","created_at":"2026-07-14T00:18:18Z"},{"alias_kind":"pith_short_12","alias_value":"LVIF2CDCVEMA","created_at":"2026-07-14T00:18:18Z"},{"alias_kind":"pith_short_16","alias_value":"LVIF2CDCVEMAT56A","created_at":"2026-07-14T00:18:18Z"},{"alias_kind":"pith_short_8","alias_value":"LVIF2CDC","created_at":"2026-07-14T00:18:18Z"}],"graph_snapshots":[{"event_id":"sha256:8c29517a51d265321644687209fcf8c4d61c4c87c519754c69cfb2d687484058","target":"graph","created_at":"2026-07-14T00:18:18Z","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/2503.14499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite rapid progress on AI benchmarks, the real-world meaning of benchmark performance remains unclear. To quantify the capabilities of AI systems in terms of human capabilities, we propose a new metric: 50%-task-completion time horizon. This is the time humans typically take to complete tasks that AI models can complete with 50% success rate. We first timed humans with relevant domain expertise on a combination of RE-Bench, HCAST, and 66 novel shorter tasks. On these tasks, current frontier AI models such as Claude 3.7 Sonnet have a 50% time horizon of around 50 minutes. Furthermore, fronti","authors_text":"Amy Deng, Ben West, Brian Goodrich, Chris Painter, Daniel M. Ziegler, David Rein, Elizabeth Barnes, Haoxing Du, Hjalmar Wijk, Joel Becker, Katharyn Garcia, Lawrence Chan, Lucas Jun Koba Sato, Luke Harold Miles, Max Hasin, Megan Kinniment, Nate Rush, Neev Parikh, Nikola Jurkovic, Ryan Bloom, Sami Jawhar, Seraphina Nix, Sydney von Arx, Tao Lin, Thomas Broadley, Thomas Kwa","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-18T17:59:31Z","title":"Measuring AI Ability to Complete Long Software Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14499","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:d725d7fe3ea7629654b8f7a05a70ccd20f9f39258cb61f63192f9ab5f86b6571","target":"record","created_at":"2026-07-14T00:18:18Z","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":"e702d008f561eedce194021837e05019ec617f99f259f86da88efe27237db942","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-18T17:59:31Z","title_canon_sha256":"bc9b28b5968b80a4075a2ad5e4e139cc5c7d55e38872bcdda7135c58a6c4fe2f"},"schema_version":"1.0","source":{"id":"2503.14499","kind":"arxiv","version":4}},"canonical_sha256":"5d505d0862a91809f7c0f32a2911e2b37ff0e618dbc3ae2821a3b72f1d8147d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d505d0862a91809f7c0f32a2911e2b37ff0e618dbc3ae2821a3b72f1d8147d2","first_computed_at":"2026-07-14T00:18:18.548212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T00:18:18.548212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2QNV+Z26UrJsfUQtMrAcSZYkeNWz0L1e9PqaV3B6BpuU7OUp+3YkaUyQNmc+s+JEi/OEab65a/xIr8KYUFtUDA==","signature_status":"signed_v1","signed_at":"2026-07-14T00:18:18.549230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.14499","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d725d7fe3ea7629654b8f7a05a70ccd20f9f39258cb61f63192f9ab5f86b6571","sha256:8c29517a51d265321644687209fcf8c4d61c4c87c519754c69cfb2d687484058"],"state_sha256":"23fd5b73e25de4d4c2f87a04ae0b2618291efa33f86def7be4912519ce24a705"}