{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XESEPPKD7BTKUFWCYFSA3Z6RF7","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":"faa12810232d930fd62f80e1adf56780c8258f30efaa431ff912c05e99eb4034","cross_cats_sorted":["cs.CR","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-01T03:25:59Z","title_canon_sha256":"645b749c5e3ec5b0d41887ea74349e17cd5e5785d63a5debeca74ce0b96a93b2"},"schema_version":"1.0","source":{"id":"2409.00598","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00598","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00598v2","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00598","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"pith_short_12","alias_value":"XESEPPKD7BTK","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"pith_short_16","alias_value":"XESEPPKD7BTKUFWC","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"pith_short_8","alias_value":"XESEPPKD","created_at":"2026-07-05T11:19:20Z"}],"graph_snapshots":[{"event_id":"sha256:5d35ae3c0bcd1b2caac01a3d8e0a7a75a77ab2bd80cceca0041f7a90eb11ea12","target":"graph","created_at":"2026-07-05T11:19:20Z","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/2409.00598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like \"how to kill a mosquito,\" which are actually harmless. Frequent false refusals not only frustrate users but also provoke a public backlash against the very values alignment seeks to protect. In this paper, we propose the first method to auto-generate diverse, content-controlled, and model-dependent pseudo-harmful prompts. Using this method, we construct an evaluation dataset called PHTest, which is ten times larger than existing datasets, covers more false refusal patterns, and separately labels c","authors_text":"Bang An, Furong Huang, Michael-Andrei Panaitescu-Liess, Ruiyi Zhang, Sicheng Zhu, Yuancheng Xu","cross_cats":["cs.CR","cs.CY","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-01T03:25:59Z","title":"Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00598","kind":"arxiv","version":2},"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":"sha256:5a959f39a01171d838420c4f0f16c5797537f741fe956e4b30c069c4a7f8dd90","target":"record","created_at":"2026-07-05T11:19:20Z","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":"faa12810232d930fd62f80e1adf56780c8258f30efaa431ff912c05e99eb4034","cross_cats_sorted":["cs.CR","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-01T03:25:59Z","title_canon_sha256":"645b749c5e3ec5b0d41887ea74349e17cd5e5785d63a5debeca74ce0b96a93b2"},"schema_version":"1.0","source":{"id":"2409.00598","kind":"arxiv","version":2}},"canonical_sha256":"b92447bd43f866aa16c2c1640de7d12ff8b37b08a1e1d3bb4dd3f9fa0a5864d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b92447bd43f866aa16c2c1640de7d12ff8b37b08a1e1d3bb4dd3f9fa0a5864d0","first_computed_at":"2026-07-05T11:19:20.914282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:20.914282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cBvWteQ/I1SZpD83no0EHnATrE96t2uon0eiWrcOKoN0X9Ng9AUor75f0bWvFcT83XayFXJ/EMgBdL/CexPbAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:20.914739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.00598","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a959f39a01171d838420c4f0f16c5797537f741fe956e4b30c069c4a7f8dd90","sha256:5d35ae3c0bcd1b2caac01a3d8e0a7a75a77ab2bd80cceca0041f7a90eb11ea12"],"state_sha256":"2c7492ff26959ec0210e0f9e5b8020bf239f0dbc4951a853fd0cb5bad81f6782"}