{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3ATAVV3ZLBHVBRLTQWHT7CT7VO","short_pith_number":"pith:3ATAVV3Z","schema_version":"1.0","canonical_sha256":"d8260ad779584f50c573858f3f8a7fab8a00f8a065442315b5000bf094ca7ae4","source":{"kind":"arxiv","id":"2508.13757","version":1},"attestation_state":"computed","paper":{"title":"COMPASS: A Multi-Dimensional Benchmark for Evaluating Code Generation in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Grigori Melnik, James Meaden, Micha{\\l} Jarosz, Piotr Jod{\\l}owski","submitted_at":"2025-08-19T11:55:07Z","abstract_excerpt":"Current code generation benchmarks focus primarily on functional correctness while overlooking two critical aspects of real-world programming: algorithmic efficiency and code quality. We introduce COMPASS (COdility's Multi-dimensional Programming ASSessment), a comprehensive evaluation framework that assesses code generation across three dimensions: correctness, efficiency, and quality. COMPASS consists of 50 competitive programming problems from real Codility competitions, providing authentic human baselines from 393,150 submissions. Unlike existing benchmarks that treat algorithmically ineff"},"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":"2508.13757","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-08-19T11:55:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f72889ed780023f37df55616ea3a1ffce4a5164988088fce0f8b4472b2ec35d2","abstract_canon_sha256":"b842cb933a98ee1d65c74324b49f99d72e35c15ea9e0852633d7fa01ae22da1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:07.213252Z","signature_b64":"N7oLQ+FtgKc8OFCvh9J8kGbuarP3WHrdK/HUKxGj7uGh+LWZIhvggUuhjPikfy7djO5hsoXeDxJ8kQD1Kn3oCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8260ad779584f50c573858f3f8a7fab8a00f8a065442315b5000bf094ca7ae4","last_reissued_at":"2026-07-05T11:56:07.212823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:07.212823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COMPASS: A Multi-Dimensional Benchmark for Evaluating Code Generation in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Grigori Melnik, James Meaden, Micha{\\l} Jarosz, Piotr Jod{\\l}owski","submitted_at":"2025-08-19T11:55:07Z","abstract_excerpt":"Current code generation benchmarks focus primarily on functional correctness while overlooking two critical aspects of real-world programming: algorithmic efficiency and code quality. We introduce COMPASS (COdility's Multi-dimensional Programming ASSessment), a comprehensive evaluation framework that assesses code generation across three dimensions: correctness, efficiency, and quality. COMPASS consists of 50 competitive programming problems from real Codility competitions, providing authentic human baselines from 393,150 submissions. Unlike existing benchmarks that treat algorithmically ineff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13757","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/2508.13757/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":"2508.13757","created_at":"2026-07-05T11:56:07.212878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13757v1","created_at":"2026-07-05T11:56:07.212878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13757","created_at":"2026-07-05T11:56:07.212878+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ATAVV3ZLBHV","created_at":"2026-07-05T11:56:07.212878+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ATAVV3ZLBHVBRLT","created_at":"2026-07-05T11:56:07.212878+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ATAVV3Z","created_at":"2026-07-05T11:56:07.212878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02431","citing_title":"ARIADNE: Agentic Reward-Informed Adaptive Decision Exploration via Blackboard-Driven MCTS for Competitive Program Generation","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ATAVV3ZLBHVBRLTQWHT7CT7VO","json":"https://pith.science/pith/3ATAVV3ZLBHVBRLTQWHT7CT7VO.json","graph_json":"https://pith.science/api/pith-number/3ATAVV3ZLBHVBRLTQWHT7CT7VO/graph.json","events_json":"https://pith.science/api/pith-number/3ATAVV3ZLBHVBRLTQWHT7CT7VO/events.json","paper":"https://pith.science/paper/3ATAVV3Z"},"agent_actions":{"view_html":"https://pith.science/pith/3ATAVV3ZLBHVBRLTQWHT7CT7VO","download_json":"https://pith.science/pith/3ATAVV3ZLBHVBRLTQWHT7CT7VO.json","view_paper":"https://pith.science/paper/3ATAVV3Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13757&json=true","fetch_graph":"https://pith.science/api/pith-number/3ATAVV3ZLBHVBRLTQWHT7CT7VO/graph.json","fetch_events":"https://pith.science/api/pith-number/3ATAVV3ZLBHVBRLTQWHT7CT7VO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ATAVV3ZLBHVBRLTQWHT7CT7VO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ATAVV3ZLBHVBRLTQWHT7CT7VO/action/storage_attestation","attest_author":"https://pith.science/pith/3ATAVV3ZLBHVBRLTQWHT7CT7VO/action/author_attestation","sign_citation":"https://pith.science/pith/3ATAVV3ZLBHVBRLTQWHT7CT7VO/action/citation_signature","submit_replication":"https://pith.science/pith/3ATAVV3ZLBHVBRLTQWHT7CT7VO/action/replication_record"}},"created_at":"2026-07-05T11:56:07.212878+00:00","updated_at":"2026-07-05T11:56:07.212878+00:00"}