{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LZBA242BSDHWYBPXGPAUUISWLC","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":"c26c10329c494fabb7280f754f297ec5fa7c06d298d66cc7c8811fc656629323","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-12-30T18:58:58Z","title_canon_sha256":"e990448744106ddc3f3b43bdb5bb48f32095bd570a63878f755f20467f4cb32c"},"schema_version":"1.0","source":{"id":"2412.21199","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.21199","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.21199v2","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.21199","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"LZBA242BSDHW","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_16","alias_value":"LZBA242BSDHWYBPX","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_8","alias_value":"LZBA242B","created_at":"2026-07-05T09:55:37Z"}],"graph_snapshots":[{"event_id":"sha256:0c0f0d2bf3b5cd109022a970a3e8650b78259fa785efcc9902235d2e9cfb457b","target":"graph","created_at":"2026-07-05T09:55:37Z","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/2412.21199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. In this task, models are presented with a base problem and a related, more complex problem. They must solve the base problem and then utilize its solution to address the more complex one. This work features three key contributions. First, we propose a general recipe for generating more challenging versions of existing benchmarks, resulting in three new benchmarks: HumanEval Pro, MBPP Pro, and BigCodeBench-Lite Pro, specifically designed to assess LLMs ","authors_text":"Arman Cohan, Xiao-Ping Zhang, Yilun Zhao, Zhaojian Yu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-12-30T18:58:58Z","title":"HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.21199","kind":"arxiv","version":2},"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":"sha256:23f7db0801fcacb4647e5675fbd077a028731e25842b591621315742828925b9","target":"record","created_at":"2026-07-05T09:55:37Z","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":"c26c10329c494fabb7280f754f297ec5fa7c06d298d66cc7c8811fc656629323","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-12-30T18:58:58Z","title_canon_sha256":"e990448744106ddc3f3b43bdb5bb48f32095bd570a63878f755f20467f4cb32c"},"schema_version":"1.0","source":{"id":"2412.21199","kind":"arxiv","version":2}},"canonical_sha256":"5e420d734190cf6c05f733c14a2256589998181ab742146e259c5b1cbf167217","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e420d734190cf6c05f733c14a2256589998181ab742146e259c5b1cbf167217","first_computed_at":"2026-07-05T09:55:37.339378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:37.339378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0JXVwESPkO2B77buUjrZdOi1ZlFuSZw5CiQ7ubbIfFMGNAG8UK2qQM0suAD5QUi33xMcyx88zz57fH38qccVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:37.339926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.21199","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23f7db0801fcacb4647e5675fbd077a028731e25842b591621315742828925b9","sha256:0c0f0d2bf3b5cd109022a970a3e8650b78259fa785efcc9902235d2e9cfb457b"],"state_sha256":"d6f5c22e61e391d23aad57901aa74be389981d0d2788189528fd111d439c6ade"}