{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QOBGJW5GCJD6J2M6VLICK3P36L","short_pith_number":"pith:QOBGJW5G","schema_version":"1.0","canonical_sha256":"838264dba61247e4e99eaad0256dfbf2dd8e677dab2fa02401f3e36ab2d34a9c","source":{"kind":"arxiv","id":"2606.12864","version":1},"attestation_state":"computed","paper":{"title":"Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alex Gu, Hangrui Zhou, Kaifeng Lyu, Tianle Cai, Tingqiang Xu","submitted_at":"2026-06-11T03:48:18Z","abstract_excerpt":"Despite strong performance in competitive programming, the role of Large Language Models (LLMs) in supporting human learning in the same setting remains largely unexplored. In this work, we introduce UOJ-Bench, a benchmark designed to evaluate not only the problem-solving ability of LLMs, but also their ability to identify errors in human-written code -- a crucial educational activity traditionally supported by running test cases over online judge systems. UOJ-Bench consists of three distinct tasks: code generation, code hacking, and code repair, all constructed from real-world code submission"},"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":"2606.12864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-11T03:48:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49190d4ceefdcaf81e9968ad0ace315e25b689a05adbab436c193b242454ab7a","abstract_canon_sha256":"4cc8b1b258cd07073623b644b12c78e0896b6171ca4117c8432c530fb2020f12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:55.511943Z","signature_b64":"rVaSf2wZcPMvXCK0dymNxRz/IW5YDy55SogfmPqaBZaNU7HEyfUx5jaCrcI2gebN1k3GZzWXjtZpOM1gVAyFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"838264dba61247e4e99eaad0256dfbf2dd8e677dab2fa02401f3e36ab2d34a9c","last_reissued_at":"2026-06-12T01:08:55.511084Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:55.511084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alex Gu, Hangrui Zhou, Kaifeng Lyu, Tianle Cai, Tingqiang Xu","submitted_at":"2026-06-11T03:48:18Z","abstract_excerpt":"Despite strong performance in competitive programming, the role of Large Language Models (LLMs) in supporting human learning in the same setting remains largely unexplored. In this work, we introduce UOJ-Bench, a benchmark designed to evaluate not only the problem-solving ability of LLMs, but also their ability to identify errors in human-written code -- a crucial educational activity traditionally supported by running test cases over online judge systems. UOJ-Bench consists of three distinct tasks: code generation, code hacking, and code repair, all constructed from real-world code submission"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12864","kind":"arxiv","version":1},"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/2606.12864/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":"2606.12864","created_at":"2026-06-12T01:08:55.511209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12864v1","created_at":"2026-06-12T01:08:55.511209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12864","created_at":"2026-06-12T01:08:55.511209+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOBGJW5GCJD6","created_at":"2026-06-12T01:08:55.511209+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOBGJW5GCJD6J2M6","created_at":"2026-06-12T01:08:55.511209+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOBGJW5G","created_at":"2026-06-12T01:08:55.511209+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01715","citing_title":"Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They Catch","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOBGJW5GCJD6J2M6VLICK3P36L","json":"https://pith.science/pith/QOBGJW5GCJD6J2M6VLICK3P36L.json","graph_json":"https://pith.science/api/pith-number/QOBGJW5GCJD6J2M6VLICK3P36L/graph.json","events_json":"https://pith.science/api/pith-number/QOBGJW5GCJD6J2M6VLICK3P36L/events.json","paper":"https://pith.science/paper/QOBGJW5G"},"agent_actions":{"view_html":"https://pith.science/pith/QOBGJW5GCJD6J2M6VLICK3P36L","download_json":"https://pith.science/pith/QOBGJW5GCJD6J2M6VLICK3P36L.json","view_paper":"https://pith.science/paper/QOBGJW5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12864&json=true","fetch_graph":"https://pith.science/api/pith-number/QOBGJW5GCJD6J2M6VLICK3P36L/graph.json","fetch_events":"https://pith.science/api/pith-number/QOBGJW5GCJD6J2M6VLICK3P36L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOBGJW5GCJD6J2M6VLICK3P36L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOBGJW5GCJD6J2M6VLICK3P36L/action/storage_attestation","attest_author":"https://pith.science/pith/QOBGJW5GCJD6J2M6VLICK3P36L/action/author_attestation","sign_citation":"https://pith.science/pith/QOBGJW5GCJD6J2M6VLICK3P36L/action/citation_signature","submit_replication":"https://pith.science/pith/QOBGJW5GCJD6J2M6VLICK3P36L/action/replication_record"}},"created_at":"2026-06-12T01:08:55.511209+00:00","updated_at":"2026-06-12T01:08:55.511209+00:00"}