{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HCWU5YICHTAMSAQLYNFDWIGDR6","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":"5ee8d8078c7c86c37482d57bd1787000f523ebbbb391ddd31af33832b9deac8f","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T16:33:14Z","title_canon_sha256":"d16502cd6ab74e3792c26a6579512f2cd05c74a432a29075ef61f2f24dc9a539"},"schema_version":"1.0","source":{"id":"2607.01153","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01153","created_at":"2026-07-02T01:18:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01153v1","created_at":"2026-07-02T01:18:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01153","created_at":"2026-07-02T01:18:30Z"},{"alias_kind":"pith_short_12","alias_value":"HCWU5YICHTAM","created_at":"2026-07-02T01:18:30Z"},{"alias_kind":"pith_short_16","alias_value":"HCWU5YICHTAMSAQL","created_at":"2026-07-02T01:18:30Z"},{"alias_kind":"pith_short_8","alias_value":"HCWU5YIC","created_at":"2026-07-02T01:18:30Z"}],"graph_snapshots":[{"event_id":"sha256:a1bc982ae1a9de9e4cd3bbd0a091d3715c976ce6faf36e04c4d9c9a4ed087288","target":"graph","created_at":"2026-07-02T01:18:30Z","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/2607.01153/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model has followed an instruction, refused appropriately, complied with a policy, resisted an embedded command, or misreported progress in an agentic task. Existing benchmarks often compress these distinctions into pass/fail labels, obscuring whether failures arise from capability limits, policy ambiguity, instruction conflict, scaffold failure, or unstable evaluator judgments.\n  This paper introduces adversarial pragmatics as a benchmark and annotation protocol for eva","authors_text":"Brett Reynolds","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T16:33:14Z","title":"Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01153","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:c0f12614ccaf224eab368c486ba01fc27befe8319246e766b54eff263ced4762","target":"record","created_at":"2026-07-02T01:18:30Z","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":"5ee8d8078c7c86c37482d57bd1787000f523ebbbb391ddd31af33832b9deac8f","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T16:33:14Z","title_canon_sha256":"d16502cd6ab74e3792c26a6579512f2cd05c74a432a29075ef61f2f24dc9a539"},"schema_version":"1.0","source":{"id":"2607.01153","kind":"arxiv","version":1}},"canonical_sha256":"38ad4ee1023cc0c9020bc34a3b20c38fa8c6296eb224bb69b890a9b733433e63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38ad4ee1023cc0c9020bc34a3b20c38fa8c6296eb224bb69b890a9b733433e63","first_computed_at":"2026-07-02T01:18:30.632435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:18:30.632435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3X14Oe0B1GI/0BdtWgF3ZgsPUKlC8S+gIrPXXZLy/HDvihOIxu92lR9Etm019bzAuLh6inDv9zlge9SAES0sCQ==","signature_status":"signed_v1","signed_at":"2026-07-02T01:18:30.632838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01153","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0f12614ccaf224eab368c486ba01fc27befe8319246e766b54eff263ced4762","sha256:a1bc982ae1a9de9e4cd3bbd0a091d3715c976ce6faf36e04c4d9c9a4ed087288"],"state_sha256":"420407adc6f3abd72613c0599913fd0c5f4f13a32596ce0ed32dbe725096ed40"}