{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MJGHZXSXS3IPWFH5FSEPU7QTX6","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":"d9bae0fe9a624ee177e886fb45722c25d04fa44a0740feb0ea125bef04e79e44","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T12:28:23Z","title_canon_sha256":"0f395d8dd4ae9816faaac03a57ca605626afc8e4d08981125a3cc59a372e6087"},"schema_version":"1.0","source":{"id":"2502.14499","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14499","created_at":"2026-07-05T10:17:27Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14499v1","created_at":"2026-07-05T10:17:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14499","created_at":"2026-07-05T10:17:27Z"},{"alias_kind":"pith_short_12","alias_value":"MJGHZXSXS3IP","created_at":"2026-07-05T10:17:27Z"},{"alias_kind":"pith_short_16","alias_value":"MJGHZXSXS3IPWFH5","created_at":"2026-07-05T10:17:27Z"},{"alias_kind":"pith_short_8","alias_value":"MJGHZXSX","created_at":"2026-07-05T10:17:27Z"}],"graph_snapshots":[{"event_id":"sha256:1123bf0b847c80f1126207b8d60e276f47213d6437d600ef8990cfe8bb3be4b8","target":"graph","created_at":"2026-07-05T10:17:27Z","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/2502.14499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Meta MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. This is the first Gym environment for machine learning (ML) tasks, enabling research on reinforcement learning (RL) algorithms for training such agents. MLGym-bench consists of 13 diverse and open-ended AI research tasks from diverse domains such as computer vision, natural language processing, reinforcement learning, and game theory. Solving these tasks requires real-world AI research skills such as generating new ideas and hypotheses, creating and processing d","authors_text":"Ajay Menon, Amar Budhiraja, Deepak Nathani, Despoina Magka, Dieuwke Hupkes, Gaurav Chaurasia, Jakob Foerster, Lovish Madaan, Nicholas Roberts, Nikolay Bashlykov, Ricardo Silveira Cabral, Roberta Raileanu, Tatiana Shavrina, Vincent Moens, Vladislav Vorotilov, William Yang Wang, Yoram Bachrach","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T12:28:23Z","title":"MLGym: A New Framework and Benchmark for Advancing AI Research Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14499","kind":"arxiv","version":1},"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:e4d4ab795dd44d3c024826e4b58d9b135de1155c650c48622c0645077e4426c4","target":"record","created_at":"2026-07-05T10:17:27Z","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":"d9bae0fe9a624ee177e886fb45722c25d04fa44a0740feb0ea125bef04e79e44","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T12:28:23Z","title_canon_sha256":"0f395d8dd4ae9816faaac03a57ca605626afc8e4d08981125a3cc59a372e6087"},"schema_version":"1.0","source":{"id":"2502.14499","kind":"arxiv","version":1}},"canonical_sha256":"624c7cde5796d0fb14fd2c88fa7e13bf9c6d5338e8fa263f9ddf2a13d5eb4167","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"624c7cde5796d0fb14fd2c88fa7e13bf9c6d5338e8fa263f9ddf2a13d5eb4167","first_computed_at":"2026-07-05T10:17:27.601283Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:27.601283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vMXWRSdmOn4dTnYalieyL8J8nPoxLNHiJ22/ouS6xoRcnc3RJPTxbVPXdHDxH/I4scKTUaFLQXobLgKUeFoMAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:27.601764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14499","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4d4ab795dd44d3c024826e4b58d9b135de1155c650c48622c0645077e4426c4","sha256:1123bf0b847c80f1126207b8d60e276f47213d6437d600ef8990cfe8bb3be4b8"],"state_sha256":"930a7f2e7fa0b142f23037781355d3ee7748d3de54802da591216de6fde9d22c"}