{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:43XXVBN7B2STWAFEOLIGEYPYGF","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":"3f1d99f0507ea5a51dc23ff600484b362e797c1dde69f2ba6869a3d5e5cd424f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T23:04:12Z","title_canon_sha256":"a51ab7df95b1fceceb1387dfb597ae0d8e8b7b63b60fd080662603a6669a1ac8"},"schema_version":"1.0","source":{"id":"2506.02314","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02314","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02314v1","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02314","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"pith_short_12","alias_value":"43XXVBN7B2ST","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"pith_short_16","alias_value":"43XXVBN7B2STWAFE","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"pith_short_8","alias_value":"43XXVBN7","created_at":"2026-07-05T11:14:36Z"}],"graph_snapshots":[{"event_id":"sha256:ed5f2b3650129c8e588b4ec415708d951977743d5556beb2894af2a904482de2","target":"graph","created_at":"2026-07-05T11:14:36Z","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/2506.02314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown promise in transforming machine learning research, yet their capability to faithfully implement novel ideas from recent research papers-ideas unseen during pretraining-remains unclear. We introduce ResearchCodeBench, a benchmark of 212 coding challenges that evaluates LLMs' ability to translate cutting-edge ML contributions from top 2024-2025 research papers into executable code. We assessed 30+ proprietary and open-source LLMs, finding that even the best models correctly implement less than 40% of the code. We find Gemini-2.5-Pro-Preview to perform best","authors_text":"Benjamin Klieger, Fan-Yun Sun, Harper Hua, Nick Haber, Sang T. Truong, Tianyu Hua, Violet Xiang, Weixin Liang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T23:04:12Z","title":"ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02314","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":"sha256:298fe9dd7851b502df59c513d171b3a3735f661144edad99b8760087c76320b7","target":"record","created_at":"2026-07-05T11:14:36Z","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":"3f1d99f0507ea5a51dc23ff600484b362e797c1dde69f2ba6869a3d5e5cd424f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T23:04:12Z","title_canon_sha256":"a51ab7df95b1fceceb1387dfb597ae0d8e8b7b63b60fd080662603a6669a1ac8"},"schema_version":"1.0","source":{"id":"2506.02314","kind":"arxiv","version":1}},"canonical_sha256":"e6ef7a85bf0ea53b00a472d06261f83140a4ffbe798a54245d8619dc6b86b7cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6ef7a85bf0ea53b00a472d06261f83140a4ffbe798a54245d8619dc6b86b7cd","first_computed_at":"2026-07-05T11:14:36.252691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:36.252691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F5jF7r7U4gBXc7wfPch2MMlvA5IKJwGNYNWjSejdMmgV5hdrptOgeoDjJkLBggFUQVUDlRu8up9IrUT9A+FVBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:36.253173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02314","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:298fe9dd7851b502df59c513d171b3a3735f661144edad99b8760087c76320b7","sha256:ed5f2b3650129c8e588b4ec415708d951977743d5556beb2894af2a904482de2"],"state_sha256":"dbad75515e81f964666780de2b123ea9410de517533a9cbbc5d15a17a7540f6a"}