{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DHSNK6P4D7PP3BEL6I42KOKZLC","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":"f6ff25aad619c3fa304c486c83a0649348a35f5d539d509169ca77b063bdb564","cross_cats_sorted":["cs.CR","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-24T05:51:23Z","title_canon_sha256":"76ea3b9cb7b9d673157bf8dd5111fef9f258df693c222da9732cc788c4f4e95e"},"schema_version":"1.0","source":{"id":"2605.24883","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24883","created_at":"2026-05-26T01:04:03Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24883v1","created_at":"2026-05-26T01:04:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24883","created_at":"2026-05-26T01:04:03Z"},{"alias_kind":"pith_short_12","alias_value":"DHSNK6P4D7PP","created_at":"2026-05-26T01:04:03Z"},{"alias_kind":"pith_short_16","alias_value":"DHSNK6P4D7PP3BEL","created_at":"2026-05-26T01:04:03Z"},{"alias_kind":"pith_short_8","alias_value":"DHSNK6P4","created_at":"2026-05-26T01:04:03Z"}],"graph_snapshots":[{"event_id":"sha256:85db8efdb8f75a199cfe3d39ea90524a0bb0ecf7526538e7ca9a3f8c4dc993be","target":"graph","created_at":"2026-05-26T01:04:03Z","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/2605.24883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The widespread integration of Large Language Models (LLMs) necessitates rigorous and systematic safety evaluation. Existing paradigms either rely on constructed benchmarks to assess safety from predefined perspectives, or employ dynamic red-teaming to probe potential vulnerabilities. While effective, these approaches face challenges, as they depend heavily on expert domain knowledge, offer limited systematic guarantees, and are vulnerable to rapid obsolescence. To address these limitations, we introduce a novel framework POLARIS that brings the rigor of specification-based software testing to ","authors_text":"Haijun Liu, Jiahao Liu, Jin Song Dong, Kuntai Cai, Xianglin Yang, Xiaoyue Lu, Yan Xiao","cross_cats":["cs.CR","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-24T05:51:23Z","title":"Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24883","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":"sha256:7868810bbe1bcd27ea8fa182a346e18a21a951f26576731f8b7f862c577f09f3","target":"record","created_at":"2026-05-26T01:04:03Z","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":"f6ff25aad619c3fa304c486c83a0649348a35f5d539d509169ca77b063bdb564","cross_cats_sorted":["cs.CR","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-24T05:51:23Z","title_canon_sha256":"76ea3b9cb7b9d673157bf8dd5111fef9f258df693c222da9732cc788c4f4e95e"},"schema_version":"1.0","source":{"id":"2605.24883","kind":"arxiv","version":1}},"canonical_sha256":"19e4d579fc1fdefd848bf239a5395958a85dbe2744aa19f0d4b75c21fa024186","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19e4d579fc1fdefd848bf239a5395958a85dbe2744aa19f0d4b75c21fa024186","first_computed_at":"2026-05-26T01:04:03.409100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:04:03.409100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MHzRAYi3RApMWT7aGadL0NIe4QbdRvB6/rITML06/MGvdFuTn6MuBBc3LFZhNLmkhbbOZrIou1wtIEYCsHiRBw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:04:03.409926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24883","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7868810bbe1bcd27ea8fa182a346e18a21a951f26576731f8b7f862c577f09f3","sha256:85db8efdb8f75a199cfe3d39ea90524a0bb0ecf7526538e7ca9a3f8c4dc993be"],"state_sha256":"38e07ff1a31d8b4e007cef7316ca2d49688e56a8ac7ba04088dcb777cd248d6a"}