{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3ATAVV3ZLBHVBRLTQWHT7CT7VO","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":"b842cb933a98ee1d65c74324b49f99d72e35c15ea9e0852633d7fa01ae22da1f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-08-19T11:55:07Z","title_canon_sha256":"f72889ed780023f37df55616ea3a1ffce4a5164988088fce0f8b4472b2ec35d2"},"schema_version":"1.0","source":{"id":"2508.13757","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.13757","created_at":"2026-07-05T11:56:07Z"},{"alias_kind":"arxiv_version","alias_value":"2508.13757v1","created_at":"2026-07-05T11:56:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13757","created_at":"2026-07-05T11:56:07Z"},{"alias_kind":"pith_short_12","alias_value":"3ATAVV3ZLBHV","created_at":"2026-07-05T11:56:07Z"},{"alias_kind":"pith_short_16","alias_value":"3ATAVV3ZLBHVBRLT","created_at":"2026-07-05T11:56:07Z"},{"alias_kind":"pith_short_8","alias_value":"3ATAVV3Z","created_at":"2026-07-05T11:56:07Z"}],"graph_snapshots":[{"event_id":"sha256:fe0a7e671cdabbdbd0ee7fe54de5488278a65aa0a3865cd0d272e8009c254059","target":"graph","created_at":"2026-07-05T11:56:07Z","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/2508.13757/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Grigori Melnik, James Meaden, Micha{\\l} Jarosz, Piotr Jod{\\l}owski","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-08-19T11:55:07Z","title":"COMPASS: A Multi-Dimensional Benchmark for Evaluating Code Generation in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13757","kind":"arxiv","version":1},"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":"sha256:2656d3b6f81aeef4aecaaddee488d4c187d65a45b5b7e06d1b7eae1bfcb8a7ec","target":"record","created_at":"2026-07-05T11:56:07Z","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":"b842cb933a98ee1d65c74324b49f99d72e35c15ea9e0852633d7fa01ae22da1f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-08-19T11:55:07Z","title_canon_sha256":"f72889ed780023f37df55616ea3a1ffce4a5164988088fce0f8b4472b2ec35d2"},"schema_version":"1.0","source":{"id":"2508.13757","kind":"arxiv","version":1}},"canonical_sha256":"d8260ad779584f50c573858f3f8a7fab8a00f8a065442315b5000bf094ca7ae4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8260ad779584f50c573858f3f8a7fab8a00f8a065442315b5000bf094ca7ae4","first_computed_at":"2026-07-05T11:56:07.212823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:07.212823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N7oLQ+FtgKc8OFCvh9J8kGbuarP3WHrdK/HUKxGj7uGh+LWZIhvggUuhjPikfy7djO5hsoXeDxJ8kQD1Kn3oCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:07.213252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.13757","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2656d3b6f81aeef4aecaaddee488d4c187d65a45b5b7e06d1b7eae1bfcb8a7ec","sha256:fe0a7e671cdabbdbd0ee7fe54de5488278a65aa0a3865cd0d272e8009c254059"],"state_sha256":"6499090399c0dbd24881ba8b2e9af5ceb774f13b83fe59ae8c0ca19a132e7166"}