{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KLAEZOL7FFBRTXRGLSC3LZMK72","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":"f8258880987259824177fc2dabdf5f4b9cf44cf18d45f49722fe6927ca5a009b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-06T13:14:34Z","title_canon_sha256":"a20ca33f741e794c2431ea3719a66fd12240f8e7fd5456320332b1f2934eed4d"},"schema_version":"1.0","source":{"id":"2501.02997","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02997","created_at":"2026-07-05T09:57:28Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02997v1","created_at":"2026-07-05T09:57:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02997","created_at":"2026-07-05T09:57:28Z"},{"alias_kind":"pith_short_12","alias_value":"KLAEZOL7FFBR","created_at":"2026-07-05T09:57:28Z"},{"alias_kind":"pith_short_16","alias_value":"KLAEZOL7FFBRTXRG","created_at":"2026-07-05T09:57:28Z"},{"alias_kind":"pith_short_8","alias_value":"KLAEZOL7","created_at":"2026-07-05T09:57:28Z"}],"graph_snapshots":[{"event_id":"sha256:2612cf0a08b8070d94d6e03e37009e819f0a9b96f9baa9ff2a25a99afa59cfe5","target":"graph","created_at":"2026-07-05T09:57:28Z","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/2501.02997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Auditing Large Language Models (LLMs) is a crucial and challenging task. In this study, we focus on auditing black-box LLMs without access to their parameters, only to the provided service. We treat this type of auditing as a black-box optimization problem where the goal is to automatically uncover input-output pairs of the target LLMs that exhibit illegal, immoral, or unsafe behaviors. For instance, we may seek a non-toxic input that the target LLM responds to with a toxic output or an input that induces the hallucinative response from the target LLM containing politically sensitive individua","authors_text":"Chao Shen, Cong Wang, Longxiang Wang, Xiang Zheng, Xingjun Ma, Yi Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-06T13:14:34Z","title":"CALM: Curiosity-Driven Auditing for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02997","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":"sha256:7f7f4309f8be85df968620a1888fd1a0620adbb66ba5017234edd1ff4691091a","target":"record","created_at":"2026-07-05T09:57:28Z","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":"f8258880987259824177fc2dabdf5f4b9cf44cf18d45f49722fe6927ca5a009b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-06T13:14:34Z","title_canon_sha256":"a20ca33f741e794c2431ea3719a66fd12240f8e7fd5456320332b1f2934eed4d"},"schema_version":"1.0","source":{"id":"2501.02997","kind":"arxiv","version":1}},"canonical_sha256":"52c04cb97f294319de265c85b5e58afea2ffa321e60dfb297ef8a26ee3bdb2f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52c04cb97f294319de265c85b5e58afea2ffa321e60dfb297ef8a26ee3bdb2f3","first_computed_at":"2026-07-05T09:57:28.936052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:28.936052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Avff/6TccNUVWQio3OOWrhYSAEvXmIBERhMjnHXIm3gpItXiUZCmXz4s4wvBzEGp/oCyjwKsNOrp2Qiy3OKKDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:28.936507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.02997","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f7f4309f8be85df968620a1888fd1a0620adbb66ba5017234edd1ff4691091a","sha256:2612cf0a08b8070d94d6e03e37009e819f0a9b96f9baa9ff2a25a99afa59cfe5"],"state_sha256":"742d71578f4371af6e17987030f3f22f9a826e46fa0e2e1a6ff96ab8fd68d583"}