{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MVBMW7ODRXCUQD3PXJKVKG7YN3","short_pith_number":"pith:MVBMW7OD","schema_version":"1.0","canonical_sha256":"6542cb7dc38dc5480f6fba55551bf86ed282d743fa3bb2b9b9a70fc36072bdae","source":{"kind":"arxiv","id":"2508.10033","version":1},"attestation_state":"computed","paper":{"title":"Cognitive Cybersecurity for Artificial Intelligence: Guardrail Engineering with CCS-7","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Yuksel Aydin","submitted_at":"2025-08-09T15:46:30Z","abstract_excerpt":"Language models exhibit human-like cognitive vulnerabilities, such as emotional framing, that escape traditional behavioral alignment. We present CCS-7 (Cognitive Cybersecurity Suite), a taxonomy of seven vulnerabilities grounded in human cognitive security research. To establish a human benchmark, we ran a randomized controlled trial with 151 participants: a \"Think First, Verify Always\" (TFVA) lesson improved cognitive security by +7.9% overall. We then evaluated TFVA-style guardrails across 12,180 experiments on seven diverse language model architectures. Results reveal architecture-dependen"},"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":"2508.10033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-08-09T15:46:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0ab7bc6a1be3af3fad839c50faea49583893bd940d3fcbf9907132827ef0d912","abstract_canon_sha256":"f732434d5d9aae2ec79955fef3a5f65d9a831ee1bb2bf8d58c38d6fb9c9a6a29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:29.570937Z","signature_b64":"jjbhe0DIgVUSPI1+x79jUAcwc6aOZJlCmAin+0El5KQaERtJn7UE82e2TeZ0vTKq7PZ1BRjTBI92NauJdQVYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6542cb7dc38dc5480f6fba55551bf86ed282d743fa3bb2b9b9a70fc36072bdae","last_reissued_at":"2026-07-05T11:53:29.570462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:29.570462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cognitive Cybersecurity for Artificial Intelligence: Guardrail Engineering with CCS-7","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Yuksel Aydin","submitted_at":"2025-08-09T15:46:30Z","abstract_excerpt":"Language models exhibit human-like cognitive vulnerabilities, such as emotional framing, that escape traditional behavioral alignment. We present CCS-7 (Cognitive Cybersecurity Suite), a taxonomy of seven vulnerabilities grounded in human cognitive security research. To establish a human benchmark, we ran a randomized controlled trial with 151 participants: a \"Think First, Verify Always\" (TFVA) lesson improved cognitive security by +7.9% overall. We then evaluated TFVA-style guardrails across 12,180 experiments on seven diverse language model architectures. Results reveal architecture-dependen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10033","kind":"arxiv","version":1},"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/2508.10033/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":"2508.10033","created_at":"2026-07-05T11:53:29.570517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10033v1","created_at":"2026-07-05T11:53:29.570517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10033","created_at":"2026-07-05T11:53:29.570517+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVBMW7ODRXCU","created_at":"2026-07-05T11:53:29.570517+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVBMW7ODRXCUQD3P","created_at":"2026-07-05T11:53:29.570517+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVBMW7OD","created_at":"2026-07-05T11:53:29.570517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.15842","citing_title":"Lexical Hints of Accuracy in LLM Reasoning Chains","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVBMW7ODRXCUQD3PXJKVKG7YN3","json":"https://pith.science/pith/MVBMW7ODRXCUQD3PXJKVKG7YN3.json","graph_json":"https://pith.science/api/pith-number/MVBMW7ODRXCUQD3PXJKVKG7YN3/graph.json","events_json":"https://pith.science/api/pith-number/MVBMW7ODRXCUQD3PXJKVKG7YN3/events.json","paper":"https://pith.science/paper/MVBMW7OD"},"agent_actions":{"view_html":"https://pith.science/pith/MVBMW7ODRXCUQD3PXJKVKG7YN3","download_json":"https://pith.science/pith/MVBMW7ODRXCUQD3PXJKVKG7YN3.json","view_paper":"https://pith.science/paper/MVBMW7OD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10033&json=true","fetch_graph":"https://pith.science/api/pith-number/MVBMW7ODRXCUQD3PXJKVKG7YN3/graph.json","fetch_events":"https://pith.science/api/pith-number/MVBMW7ODRXCUQD3PXJKVKG7YN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVBMW7ODRXCUQD3PXJKVKG7YN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVBMW7ODRXCUQD3PXJKVKG7YN3/action/storage_attestation","attest_author":"https://pith.science/pith/MVBMW7ODRXCUQD3PXJKVKG7YN3/action/author_attestation","sign_citation":"https://pith.science/pith/MVBMW7ODRXCUQD3PXJKVKG7YN3/action/citation_signature","submit_replication":"https://pith.science/pith/MVBMW7ODRXCUQD3PXJKVKG7YN3/action/replication_record"}},"created_at":"2026-07-05T11:53:29.570517+00:00","updated_at":"2026-07-05T11:53:29.570517+00:00"}