{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SRJWDHGQEMZHZQR4WT4RNRMGSQ","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":"bec5704648350d5cccecd1bd803c68449c80f412b8187bb9849fa555f9e0df35","cross_cats_sorted":["cs.AI","cs.CL","cs.PL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-01T14:43:06Z","title_canon_sha256":"a25d785926dddf87870b7d5fe1a64bdbc87bb228b734fd36ee6e87f9ee2df23c"},"schema_version":"1.0","source":{"id":"2403.00894","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00894","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00894v2","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00894","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"pith_short_12","alias_value":"SRJWDHGQEMZH","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"pith_short_16","alias_value":"SRJWDHGQEMZHZQR4","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"pith_short_8","alias_value":"SRJWDHGQ","created_at":"2026-07-05T10:02:44Z"}],"graph_snapshots":[{"event_id":"sha256:dfff286879793262b56a0cd93a978555f2359f05411754c5ae655303488e110c","target":"graph","created_at":"2026-07-05T10:02:44Z","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/2403.00894/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We systematically evaluated the performance of seven large language models in generating programming code using various prompt strategies, programming languages, and task difficulties. GPT-4 substantially outperforms other large language models, including Gemini Ultra and Claude 2. The coding performance of GPT-4 varies considerably with different prompt strategies. In most LeetCode and GeeksforGeeks coding contests evaluated in this study, GPT-4 employing the optimal prompt strategy outperforms 85 percent of human participants. Additionally, GPT-4 demonstrates strong capabilities in translati","authors_text":"Wenpin Hou, Zhicheng Ji","cross_cats":["cs.AI","cs.CL","cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-01T14:43:06Z","title":"Comparing large language models and human programmers for generating programming code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00894","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:c94fe159491d0585736afc6b4742a1bf30480164f50b5845ffe9b1f3df023334","target":"record","created_at":"2026-07-05T10:02:44Z","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":"bec5704648350d5cccecd1bd803c68449c80f412b8187bb9849fa555f9e0df35","cross_cats_sorted":["cs.AI","cs.CL","cs.PL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-01T14:43:06Z","title_canon_sha256":"a25d785926dddf87870b7d5fe1a64bdbc87bb228b734fd36ee6e87f9ee2df23c"},"schema_version":"1.0","source":{"id":"2403.00894","kind":"arxiv","version":2}},"canonical_sha256":"9453619cd023327cc23cb4f916c5869433b0fcc5ed63039c74344ae5892e48e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9453619cd023327cc23cb4f916c5869433b0fcc5ed63039c74344ae5892e48e0","first_computed_at":"2026-07-05T10:02:44.059889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:44.059889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5j3zsO7RlG+mtisfsl63EK9piYGAZ9mBAej20iTFJ6I/RdiPNFXGRZZ8hG+wiB884i+ITyO4slrezVE4dOuJDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:44.060437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00894","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c94fe159491d0585736afc6b4742a1bf30480164f50b5845ffe9b1f3df023334","sha256:dfff286879793262b56a0cd93a978555f2359f05411754c5ae655303488e110c"],"state_sha256":"336f7d9f7fdaca399c304d7ea3f7f585cdf07087ee694e7ce4e4f2bf84c75c8e"}