{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QF4DHV3V3LOT25DQVDF2647ZE7","short_pith_number":"pith:QF4DHV3V","canonical_record":{"source":{"id":"2410.07095","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:34:27Z","cross_cats_sorted":[],"title_canon_sha256":"4808a882ceec70a9b006e387a5a4ae7304b8cf998c4b6ce47d411243cfcd32ac","abstract_canon_sha256":"78f46afeabf2db76f56a21a7180c73b2d734f47ae536a6871ce359a462ad3ca3"},"schema_version":"1.0"},"canonical_sha256":"817833d775dadd3d7470a8cbaf73f927c0b85a28e7779cb388e5a4f85ca9466a","source":{"kind":"arxiv","id":"2410.07095","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07095","created_at":"2026-05-17T23:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07095v6","created_at":"2026-05-17T23:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07095","created_at":"2026-05-17T23:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"QF4DHV3V3LOT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QF4DHV3V3LOT25DQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QF4DHV3V","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QF4DHV3V3LOT25DQVDF2647ZE7","target":"record","payload":{"canonical_record":{"source":{"id":"2410.07095","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:34:27Z","cross_cats_sorted":[],"title_canon_sha256":"4808a882ceec70a9b006e387a5a4ae7304b8cf998c4b6ce47d411243cfcd32ac","abstract_canon_sha256":"78f46afeabf2db76f56a21a7180c73b2d734f47ae536a6871ce359a462ad3ca3"},"schema_version":"1.0"},"canonical_sha256":"817833d775dadd3d7470a8cbaf73f927c0b85a28e7779cb388e5a4f85ca9466a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:22.256596Z","signature_b64":"1znAovspyhiSPEOL/R96dfp4n6YPxit0qA2YoWDxjzkQQS7MBxrCWC/RQhywW3XpH89jdwY+klps/GpnhxkDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"817833d775dadd3d7470a8cbaf73f927c0b85a28e7779cb388e5a4f85ca9466a","last_reissued_at":"2026-05-17T23:39:22.256025Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:22.256025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.07095","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/kJGKP33tm7DskKdos+cFzgcNXUKVTzb7jqt8oEIv0hh/oGEroPL4RpgCrfCYRGkFgmNhpyC09vW6yXli3aJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:40:45.821873Z"},"content_sha256":"eb666119ebff1df7fb1be8f165d3bdfa45bd56f69e94ae696f3d88b042f87ec5","schema_version":"1.0","event_id":"sha256:eb666119ebff1df7fb1be8f165d3bdfa45bd56f69e94ae696f3d88b042f87ec5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QF4DHV3V3LOT25DQVDF2647ZE7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aleksander M\\k{a}dry, Dane Sherburn, Evan Mays, Giulio Starace, James Aung, Jun Shern Chan, Kevin Liu, Leon Maksin, Lilian Weng, Neil Chowdhury, Oliver Jaffe, Tejal Patwardhan","submitted_at":"2024-10-09T17:34:27Z","abstract_excerpt":"We introduce MLE-bench, a benchmark for measuring how well AI agents perform at machine learning engineering. To this end, we curate 75 ML engineering-related competitions from Kaggle, creating a diverse set of challenging tasks that test real-world ML engineering skills such as training models, preparing datasets, and running experiments. We establish human baselines for each competition using Kaggle's publicly available leaderboards. We use open-source agent scaffolds to evaluate several frontier language models on our benchmark, finding that the best-performing setup--OpenAI's o1-preview wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07095","kind":"arxiv","version":6},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bLWwM8203EGykHAq7+9us9k4XN4GvzhYQrf4bMQGK1Pty57EIZ80DbPzGIGb7z8cdvGYZtvSXm0a4Ch1bEhGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:40:45.822551Z"},"content_sha256":"2c914b16f16cfe326f04ea7aed9b1bb351f2558b78d00b9076d9659941ef0543","schema_version":"1.0","event_id":"sha256:2c914b16f16cfe326f04ea7aed9b1bb351f2558b78d00b9076d9659941ef0543"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QF4DHV3V3LOT25DQVDF2647ZE7/bundle.json","state_url":"https://pith.science/pith/QF4DHV3V3LOT25DQVDF2647ZE7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QF4DHV3V3LOT25DQVDF2647ZE7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T20:40:45Z","links":{"resolver":"https://pith.science/pith/QF4DHV3V3LOT25DQVDF2647ZE7","bundle":"https://pith.science/pith/QF4DHV3V3LOT25DQVDF2647ZE7/bundle.json","state":"https://pith.science/pith/QF4DHV3V3LOT25DQVDF2647ZE7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QF4DHV3V3LOT25DQVDF2647ZE7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QF4DHV3V3LOT25DQVDF2647ZE7","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":"78f46afeabf2db76f56a21a7180c73b2d734f47ae536a6871ce359a462ad3ca3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:34:27Z","title_canon_sha256":"4808a882ceec70a9b006e387a5a4ae7304b8cf998c4b6ce47d411243cfcd32ac"},"schema_version":"1.0","source":{"id":"2410.07095","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07095","created_at":"2026-05-17T23:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07095v6","created_at":"2026-05-17T23:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07095","created_at":"2026-05-17T23:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"QF4DHV3V3LOT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QF4DHV3V3LOT25DQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QF4DHV3V","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2c914b16f16cfe326f04ea7aed9b1bb351f2558b78d00b9076d9659941ef0543","target":"graph","created_at":"2026-05-17T23:39:22Z","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"},"paper":{"abstract_excerpt":"We introduce MLE-bench, a benchmark for measuring how well AI agents perform at machine learning engineering. To this end, we curate 75 ML engineering-related competitions from Kaggle, creating a diverse set of challenging tasks that test real-world ML engineering skills such as training models, preparing datasets, and running experiments. We establish human baselines for each competition using Kaggle's publicly available leaderboards. We use open-source agent scaffolds to evaluate several frontier language models on our benchmark, finding that the best-performing setup--OpenAI's o1-preview wi","authors_text":"Aleksander M\\k{a}dry, Dane Sherburn, Evan Mays, Giulio Starace, James Aung, Jun Shern Chan, Kevin Liu, Leon Maksin, Lilian Weng, Neil Chowdhury, Oliver Jaffe, Tejal Patwardhan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:34:27Z","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07095","kind":"arxiv","version":6},"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:eb666119ebff1df7fb1be8f165d3bdfa45bd56f69e94ae696f3d88b042f87ec5","target":"record","created_at":"2026-05-17T23:39:22Z","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":"78f46afeabf2db76f56a21a7180c73b2d734f47ae536a6871ce359a462ad3ca3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:34:27Z","title_canon_sha256":"4808a882ceec70a9b006e387a5a4ae7304b8cf998c4b6ce47d411243cfcd32ac"},"schema_version":"1.0","source":{"id":"2410.07095","kind":"arxiv","version":6}},"canonical_sha256":"817833d775dadd3d7470a8cbaf73f927c0b85a28e7779cb388e5a4f85ca9466a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"817833d775dadd3d7470a8cbaf73f927c0b85a28e7779cb388e5a4f85ca9466a","first_computed_at":"2026-05-17T23:39:22.256025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:22.256025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1znAovspyhiSPEOL/R96dfp4n6YPxit0qA2YoWDxjzkQQS7MBxrCWC/RQhywW3XpH89jdwY+klps/GpnhxkDDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:22.256596Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07095","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb666119ebff1df7fb1be8f165d3bdfa45bd56f69e94ae696f3d88b042f87ec5","sha256:2c914b16f16cfe326f04ea7aed9b1bb351f2558b78d00b9076d9659941ef0543"],"state_sha256":"af5371ed7b2e6032026ec2a10211ba9eb2a7709f9e83a17b77c0a47599715155"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g7h2KTy++W860YOCZBYQ5ZK/tfaq+5zlCzgxUTeUYB7QRTs3mF6hUAZQAfTqT69po6PP54tAuCPKmFgmXFarBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:40:45.826086Z","bundle_sha256":"8de9beaf9ba967c440ee5d6d88adb811f379569fb93388d260f1f84b6bd38264"}}