{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6YQREFMBIPOUVYHLQFDRXMYC5V","short_pith_number":"pith:6YQREFMB","schema_version":"1.0","canonical_sha256":"f62112158143dd4ae0eb81471bb302ed719545cbbedba77f4a280710a8448fe0","source":{"kind":"arxiv","id":"2504.14985","version":2},"attestation_state":"computed","paper":{"title":"aiXamine: Simplified LLM Safety and Security","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Dorde Popovic, Euisuh Jeong, Fatih Deniz, Issa Khalil, Minhaj Ahmad, Sanjay Chawla, Yazan Boshmaf","submitted_at":"2025-04-21T09:26:05Z","abstract_excerpt":"Evaluating Large Language Models (LLMs) for safety and security remains a complex task, often requiring users to navigate a fragmented landscape of ad hoc benchmarks, datasets, metrics, and reporting formats. To address this challenge, we present aiXamine, a comprehensive black-box evaluation platform for LLM safety and security. aiXamine integrates over 40 tests (i.e., benchmarks) organized into eight key services targeting specific dimensions of safety and security: adversarial robustness, code security, fairness and bias, hallucination, model and data privacy, out-of-distribution (OOD) robu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.14985","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-04-21T09:26:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e47e5d792738e0af9ace3d3b2a4a9e9ac0409216a8c4cf5e88ba471e515235ca","abstract_canon_sha256":"044584dbd4b3b3590953c24c6bc08747c8fe87e553e43dae19eed0d0989d5cfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:00.099588Z","signature_b64":"PjK6zJDXzV4lWZwnnan4A9qcn+QMAv2SJe8r6dxsdpJwD8CO4enTqHA2z9f0KGQF5ykNtKxGJlTEfhLGaU9BDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f62112158143dd4ae0eb81471bb302ed719545cbbedba77f4a280710a8448fe0","last_reissued_at":"2026-07-05T10:53:00.099114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:00.099114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"aiXamine: Simplified LLM Safety and Security","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Dorde Popovic, Euisuh Jeong, Fatih Deniz, Issa Khalil, Minhaj Ahmad, Sanjay Chawla, Yazan Boshmaf","submitted_at":"2025-04-21T09:26:05Z","abstract_excerpt":"Evaluating Large Language Models (LLMs) for safety and security remains a complex task, often requiring users to navigate a fragmented landscape of ad hoc benchmarks, datasets, metrics, and reporting formats. To address this challenge, we present aiXamine, a comprehensive black-box evaluation platform for LLM safety and security. aiXamine integrates over 40 tests (i.e., benchmarks) organized into eight key services targeting specific dimensions of safety and security: adversarial robustness, code security, fairness and bias, hallucination, model and data privacy, out-of-distribution (OOD) robu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14985","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.14985/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.14985","created_at":"2026-07-05T10:53:00.099174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14985v2","created_at":"2026-07-05T10:53:00.099174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14985","created_at":"2026-07-05T10:53:00.099174+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YQREFMBIPOU","created_at":"2026-07-05T10:53:00.099174+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YQREFMBIPOUVYHL","created_at":"2026-07-05T10:53:00.099174+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YQREFMB","created_at":"2026-07-05T10:53:00.099174+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09606","citing_title":"Evaluating Reliability Gaps in Large Language Model Safety via Repeated Prompt Sampling","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6YQREFMBIPOUVYHLQFDRXMYC5V","json":"https://pith.science/pith/6YQREFMBIPOUVYHLQFDRXMYC5V.json","graph_json":"https://pith.science/api/pith-number/6YQREFMBIPOUVYHLQFDRXMYC5V/graph.json","events_json":"https://pith.science/api/pith-number/6YQREFMBIPOUVYHLQFDRXMYC5V/events.json","paper":"https://pith.science/paper/6YQREFMB"},"agent_actions":{"view_html":"https://pith.science/pith/6YQREFMBIPOUVYHLQFDRXMYC5V","download_json":"https://pith.science/pith/6YQREFMBIPOUVYHLQFDRXMYC5V.json","view_paper":"https://pith.science/paper/6YQREFMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14985&json=true","fetch_graph":"https://pith.science/api/pith-number/6YQREFMBIPOUVYHLQFDRXMYC5V/graph.json","fetch_events":"https://pith.science/api/pith-number/6YQREFMBIPOUVYHLQFDRXMYC5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YQREFMBIPOUVYHLQFDRXMYC5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YQREFMBIPOUVYHLQFDRXMYC5V/action/storage_attestation","attest_author":"https://pith.science/pith/6YQREFMBIPOUVYHLQFDRXMYC5V/action/author_attestation","sign_citation":"https://pith.science/pith/6YQREFMBIPOUVYHLQFDRXMYC5V/action/citation_signature","submit_replication":"https://pith.science/pith/6YQREFMBIPOUVYHLQFDRXMYC5V/action/replication_record"}},"created_at":"2026-07-05T10:53:00.099174+00:00","updated_at":"2026-07-05T10:53:00.099174+00:00"}