{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BKUUNJUMZSXPJF5H4O47AXBCGB","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":"45fae60280dcb957b4a36b8707e2ed3e98000acc125c6a21e76546a55c2d11e4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-12-22T17:29:08Z","title_canon_sha256":"64c88709b93b2d0be6734a163cd7f90d9760bc7710d378df5284847940b19d68"},"schema_version":"1.0","source":{"id":"2312.14856","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14856","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14856v3","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14856","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"BKUUNJUMZSXP","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"BKUUNJUMZSXPJF5H","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"BKUUNJUM","created_at":"2026-07-05T10:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:d2ea385497cb2cbdaef10da833042cdeef6973662d062fe50f2708e80613259e","target":"graph","created_at":"2026-07-05T10:05:08Z","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/2312.14856/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a method for systematically evaluating the correctness and robustness of instruction-tuned large language models (LLMs) for code generation via a new benchmark, Turbulence. Turbulence consists of a large set of natural language $\\textit{question templates}$, each of which is a programming problem, parameterised so that it can be asked in many different forms. Each question template has an associated $\\textit{test oracle}$ that judges whether a code solution returned by an LLM is correct. Thus, from a single question template, it is possible to ask an LLM a $\\textit{neighbourhood}$ o","authors_text":"Alastair Donaldson, Mark van der Wilk, Shahin Honarvar","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-12-22T17:29:08Z","title":"Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14856","kind":"arxiv","version":3},"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":"sha256:03d8efc2b9bbb91b51890922b6d9356a0c8aeeb8bdd31f2a1a2d65ab408077e3","target":"record","created_at":"2026-07-05T10:05:08Z","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":"45fae60280dcb957b4a36b8707e2ed3e98000acc125c6a21e76546a55c2d11e4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-12-22T17:29:08Z","title_canon_sha256":"64c88709b93b2d0be6734a163cd7f90d9760bc7710d378df5284847940b19d68"},"schema_version":"1.0","source":{"id":"2312.14856","kind":"arxiv","version":3}},"canonical_sha256":"0aa946a68cccaef497a7e3b9f05c22307dd94001d16b890e46447bd6fe9aeb74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0aa946a68cccaef497a7e3b9f05c22307dd94001d16b890e46447bd6fe9aeb74","first_computed_at":"2026-07-05T10:05:08.362092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:08.362092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YXe7cEctUrqKClgcKYor9lUyxttmmHqTsfmr3pUeLKqLbRfLhqX2jsprhX/gVPGCYEZ0nInqv8xeAa1y0wwuDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:08.362579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14856","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03d8efc2b9bbb91b51890922b6d9356a0c8aeeb8bdd31f2a1a2d65ab408077e3","sha256:d2ea385497cb2cbdaef10da833042cdeef6973662d062fe50f2708e80613259e"],"state_sha256":"f2d43f8624274e54d47e014d5c5a36d2ee0c67b7214cc733d760900ede910465"}