{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LZBA242BSDHWYBPXGPAUUISWLC","short_pith_number":"pith:LZBA242B","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"},"canonical_sha256":"5e420d734190cf6c05f733c14a2256589998181ab742146e259c5b1cbf167217","source":{"kind":"arxiv","id":"2412.21199","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LZBA242BSDHWYBPXGPAUUISWLC","target":"record","payload":{"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"},"canonical_sha256":"5e420d734190cf6c05f733c14a2256589998181ab742146e259c5b1cbf167217","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"},"source_kind":"arxiv","source_id":"2412.21199","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Va9qOEbZb201rE0vQhra5VfDVDrssYqHRy5oMWqh4Kx8mpu8O4+LjTq1Qt0DYxOqqByEG62zVgsySQwq+4mCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T11:40:13.755302Z"},"content_sha256":"23f7db0801fcacb4647e5675fbd077a028731e25842b591621315742828925b9","schema_version":"1.0","event_id":"sha256:23f7db0801fcacb4647e5675fbd077a028731e25842b591621315742828925b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LZBA242BSDHWYBPXGPAUUISWLC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ZOJDG6twt2iS19KFV4VehfYvsxv+RYZPjZIIB212tbNF1YOwayNJ2B9qwHPiVMqn0hsamMvhO2cs1Yx8KVlBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T11:40:13.755632Z"},"content_sha256":"0c0f0d2bf3b5cd109022a970a3e8650b78259fa785efcc9902235d2e9cfb457b","schema_version":"1.0","event_id":"sha256:0c0f0d2bf3b5cd109022a970a3e8650b78259fa785efcc9902235d2e9cfb457b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC/bundle.json","state_url":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZBA242BSDHWYBPXGPAUUISWLC/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":"2026-08-14T11:40:13Z","links":{"resolver":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC","bundle":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC/bundle.json","state":"https://pith.science/pith/LZBA242BSDHWYBPXGPAUUISWLC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZBA242BSDHWYBPXGPAUUISWLC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c6OBOppZH45RwmT1nnKXYi10n8klfEWU7bFh/62kwqFjwHoH6dEljzsqz/uUqy9sNR8Iw9njPLopO822IhZ5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T11:40:13.757923Z","bundle_sha256":"6a534554e42918f9cd9c15bd49a5ed3fc12b7fcd6907cc69992cf5f71003cb62"}}