{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LZBA242BSDHWYBPXGPAUUISWLC","short_pith_number":"pith:LZBA242B","schema_version":"1.0","canonical_sha256":"5e420d734190cf6c05f733c14a2256589998181ab742146e259c5b1cbf167217","source":{"kind":"arxiv","id":"2412.21199","version":2},"attestation_state":"computed","paper":{"title":"HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Arman Cohan, Xiao-Ping Zhang, Yilun Zhao, Zhaojian Yu","submitted_at":"2024-12-30T18:58:58Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.21199","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-12-30T18:58:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e990448744106ddc3f3b43bdb5bb48f32095bd570a63878f755f20467f4cb32c","abstract_canon_sha256":"c26c10329c494fabb7280f754f297ec5fa7c06d298d66cc7c8811fc656629323"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:37.339926Z","signature_b64":"0JXVwESPkO2B77buUjrZdOi1ZlFuSZw5CiQ7ubbIfFMGNAG8UK2qQM0suAD5QUi33xMcyx88zz57fH38qccVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e420d734190cf6c05f733c14a2256589998181ab742146e259c5b1cbf167217","last_reissued_at":"2026-07-05T09:55:37.339378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:37.339378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Arman Cohan, Xiao-Ping Zhang, Yilun Zhao, Zhaojian Yu","submitted_at":"2024-12-30T18:58:58Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.21199","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.21199/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.21199","created_at":"2026-07-05T09:55:37.339440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.21199v2","created_at":"2026-07-05T09:55:37.339440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.21199","created_at":"2026-07-05T09:55:37.339440+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZBA242BSDHW","created_at":"2026-07-05T09:55:37.339440+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZBA242BSDHWYBPX","created_at":"2026-07-05T09:55:37.339440+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZBA242B","created_at":"2026-07-05T09:55:37.339440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30394","citing_title":"CodeGolf Bench: A Multi-Language Benchmark for Evaluating Concise Code Generation Capabilities of Large Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18073","citing_title":"A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16321","citing_title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27763","citing_title":"Intent2Tx: Benchmarking LLMs for Translating Natural Language Intents into Ethereum Transactions","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08366","citing_title":"SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16646","citing_title":"Agentic Frameworks for Reasoning Tasks: An Empirical Study","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC","json":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC.json","graph_json":"https://pith.science/api/pith-number/LZBA242BSDHWYBPXGPAUUISWLC/graph.json","events_json":"https://pith.science/api/pith-number/LZBA242BSDHWYBPXGPAUUISWLC/events.json","paper":"https://pith.science/paper/LZBA242B"},"agent_actions":{"view_html":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC","download_json":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC.json","view_paper":"https://pith.science/paper/LZBA242B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.21199&json=true","fetch_graph":"https://pith.science/api/pith-number/LZBA242BSDHWYBPXGPAUUISWLC/graph.json","fetch_events":"https://pith.science/api/pith-number/LZBA242BSDHWYBPXGPAUUISWLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC/action/storage_attestation","attest_author":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC/action/author_attestation","sign_citation":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC/action/citation_signature","submit_replication":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC/action/replication_record"}},"created_at":"2026-07-05T09:55:37.339440+00:00","updated_at":"2026-07-05T09:55:37.339440+00:00"}