{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MPTWST6JU5CATJXFEB6UATCMSE","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":"6bc403b950d107a56afa6d5fc586a7f857ab066bcef1316ae55f33e95c29e5a2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-27T23:16:14Z","title_canon_sha256":"edb4d861bef72c0c1b700f497db0494225001ca66cd647acfa400669c3ed99d6"},"schema_version":"1.0","source":{"id":"2507.20439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20439","created_at":"2026-07-05T11:44:19Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20439v1","created_at":"2026-07-05T11:44:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20439","created_at":"2026-07-05T11:44:19Z"},{"alias_kind":"pith_short_12","alias_value":"MPTWST6JU5CA","created_at":"2026-07-05T11:44:19Z"},{"alias_kind":"pith_short_16","alias_value":"MPTWST6JU5CATJXF","created_at":"2026-07-05T11:44:19Z"},{"alias_kind":"pith_short_8","alias_value":"MPTWST6J","created_at":"2026-07-05T11:44:19Z"}],"graph_snapshots":[{"event_id":"sha256:c32062e674b21c807da5e458cddd329e8b829917649e1c3c2fd120c3266ae503","target":"graph","created_at":"2026-07-05T11:44:19Z","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/2507.20439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive performance in code generation tasks under idealized conditions, where task descriptions are clear and precise. However, in practice, task descriptions frequently exhibit ambiguity, incompleteness, or internal contradictions. In this paper, we present the first empirical study examining the robustness of state-of-the-art code generation models when faced with such unclear task descriptions. We extend the HumanEval and MBPP benchmarks by systematically introducing realistic task descriptions flaws through guided mutation strategies, prod","authors_text":"Amal Akli, Federica Sarro, Maxime Cordy, Maya Larbi, Mike Papadakis, Rihab Bouyousfi, Yves Le Traon","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-27T23:16:14Z","title":"When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20439","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:b7cbe95dd48ce6d880b6be5eeacbdee4f2cdca953ccc74bf9d76dfe46d6da110","target":"record","created_at":"2026-07-05T11:44:19Z","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":"6bc403b950d107a56afa6d5fc586a7f857ab066bcef1316ae55f33e95c29e5a2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-27T23:16:14Z","title_canon_sha256":"edb4d861bef72c0c1b700f497db0494225001ca66cd647acfa400669c3ed99d6"},"schema_version":"1.0","source":{"id":"2507.20439","kind":"arxiv","version":1}},"canonical_sha256":"63e7694fc9a74409a6e5207d404c4c913725258760b919c0f762ff81c6a7a739","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63e7694fc9a74409a6e5207d404c4c913725258760b919c0f762ff81c6a7a739","first_computed_at":"2026-07-05T11:44:19.421441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:19.421441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FbbIwOfxt4wYxuYrTaKm5Sfv0Zo0RE0EuIrEyIxWqP+nf3sUX61PNxA0ND50Adt0q7TF53hOrmpZevQcTJ7wDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:19.421891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.20439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7cbe95dd48ce6d880b6be5eeacbdee4f2cdca953ccc74bf9d76dfe46d6da110","sha256:c32062e674b21c807da5e458cddd329e8b829917649e1c3c2fd120c3266ae503"],"state_sha256":"f777c1a44d855cd89574d04e001a513cebd649a5bb6f98f39163120b5fd95843"}