{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KSLJQKRBPMM2M2KGR65SDPIEAV","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":"341dbcf94def0f7bd9d51837859bf77a456ddd895bf1955e050ebbec5b155e33","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-08-04T12:15:17Z","title_canon_sha256":"f57aaa85ef00503e7413f1f629f7a8ea6353566378e1229076ef65ca06050a5e"},"schema_version":"1.0","source":{"id":"2608.03535","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03535","created_at":"2026-08-05T01:36:03Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03535v1","created_at":"2026-08-05T01:36:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03535","created_at":"2026-08-05T01:36:03Z"},{"alias_kind":"pith_short_12","alias_value":"KSLJQKRBPMM2","created_at":"2026-08-05T01:36:03Z"},{"alias_kind":"pith_short_16","alias_value":"KSLJQKRBPMM2M2KG","created_at":"2026-08-05T01:36:03Z"},{"alias_kind":"pith_short_8","alias_value":"KSLJQKRB","created_at":"2026-08-05T01:36:03Z"}],"graph_snapshots":[{"event_id":"sha256:96c5d17ec92595cf0e54ba1b21c0ae780bddf57889f1d1846c71487958a3b686","target":"graph","created_at":"2026-08-05T01:36:03Z","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/2608.03535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models are increasingly evaluated for code generation using test-based benchmarks. The validity of such evaluations depends on the reliability of their references and tests, while test-based correctness captures only part of the observable properties of generated code. We present CodeAssay, a taxonomy-first benchmark of 185 Python tasks across ten software-engineering categories. It combines audited ground truth, public tests for generation and repair, hidden tests for grading, mutation-based test-suite validation, and selected code-property measures. Regrading fixed model outpu","authors_text":"Muhammad Waseem, Pekka Abrahamsson, Shahbaz Siddeeq, Umar Subhan Malhi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-08-04T12:15:17Z","title":"CodeAssay: A Multi-Metric Benchmark with Audited Ground Truth for LLM Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03535","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":"sha256:49df2f3f0abf9b65b809e8f089ddb0b4b5d419a6e08ad3f4679537075999dcbd","target":"record","created_at":"2026-08-05T01:36:03Z","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":"341dbcf94def0f7bd9d51837859bf77a456ddd895bf1955e050ebbec5b155e33","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-08-04T12:15:17Z","title_canon_sha256":"f57aaa85ef00503e7413f1f629f7a8ea6353566378e1229076ef65ca06050a5e"},"schema_version":"1.0","source":{"id":"2608.03535","kind":"arxiv","version":1}},"canonical_sha256":"5496982a217b19a669468fbb21bd04054063b10f5d2e0d5d851278ea8b2aab3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5496982a217b19a669468fbb21bd04054063b10f5d2e0d5d851278ea8b2aab3e","first_computed_at":"2026-08-05T01:36:03.732987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:36:03.732987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rvBFMBcVNjZf2trDBorykQnh6JwUotn5s5Q/ptUx4BaE5qQSomRqaPzhF+o+XQ6tecqE+WnRuQSQcMl8lAQCAA==","signature_status":"signed_v1","signed_at":"2026-08-05T01:36:03.734628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03535","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49df2f3f0abf9b65b809e8f089ddb0b4b5d419a6e08ad3f4679537075999dcbd","sha256:96c5d17ec92595cf0e54ba1b21c0ae780bddf57889f1d1846c71487958a3b686"],"state_sha256":"5b2cb109b7d8b36fd2d786188a12242ebb3b42fd6d5c620a778af6c8d22cadb4"}