{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OC3IC6WIJ3MZRQM4YCJNN6ADCK","short_pith_number":"pith:OC3IC6WI","schema_version":"1.0","canonical_sha256":"70b6817ac84ed998c19cc092d6f80312ad73a87f630d79a9a35d1c9f61a9a648","source":{"kind":"arxiv","id":"2505.13028","version":2},"attestation_state":"computed","paper":{"title":"Evaluating the efficacy of LLM Safety Solutions : The Palit Benchmark Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Daniel Woods, Sayon Palit","submitted_at":"2025-05-19T12:12:00Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly integrated into critical systems in industries like healthcare and finance. Users can often submit queries to LLM-enabled chatbots, some of which can enrich responses with information retrieved from internal databases storing sensitive data. This gives rise to a range of attacks in which a user submits a malicious query and the LLM-system outputs a response that creates harm to the owner, such as leaking internal data or creating legal liability by harming a third-party. While security tools are being developed to counter these threats, there is li"},"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":"2505.13028","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-05-19T12:12:00Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"50434a8320e8a585222563d66bfc08710b04079496855e460f6131d7fbc43b9b","abstract_canon_sha256":"d6c1b9d2202dabb8fda188109d17acbca8df46faa3e459f45217a6d3f96273f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:45.756249Z","signature_b64":"6ZKH5mxHlH5XoHRfItpMj4LrvHetJDKGbanBeDfnqBmM1DCu6cVzaru92z8dhaIqdc0WKzQM4ox30FzjFKhvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70b6817ac84ed998c19cc092d6f80312ad73a87f630d79a9a35d1c9f61a9a648","last_reissued_at":"2026-07-05T11:05:45.755792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:45.755792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the efficacy of LLM Safety Solutions : The Palit Benchmark Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Daniel Woods, Sayon Palit","submitted_at":"2025-05-19T12:12:00Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly integrated into critical systems in industries like healthcare and finance. Users can often submit queries to LLM-enabled chatbots, some of which can enrich responses with information retrieved from internal databases storing sensitive data. This gives rise to a range of attacks in which a user submits a malicious query and the LLM-system outputs a response that creates harm to the owner, such as leaking internal data or creating legal liability by harming a third-party. While security tools are being developed to counter these threats, there is li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13028","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/2505.13028/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":"2505.13028","created_at":"2026-07-05T11:05:45.755864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13028v2","created_at":"2026-07-05T11:05:45.755864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13028","created_at":"2026-07-05T11:05:45.755864+00:00"},{"alias_kind":"pith_short_12","alias_value":"OC3IC6WIJ3MZ","created_at":"2026-07-05T11:05:45.755864+00:00"},{"alias_kind":"pith_short_16","alias_value":"OC3IC6WIJ3MZRQM4","created_at":"2026-07-05T11:05:45.755864+00:00"},{"alias_kind":"pith_short_8","alias_value":"OC3IC6WI","created_at":"2026-07-05T11:05:45.755864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02959","citing_title":"Gate AI: LLM Security Benchmark Evaluation Methodology and Results","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OC3IC6WIJ3MZRQM4YCJNN6ADCK","json":"https://pith.science/pith/OC3IC6WIJ3MZRQM4YCJNN6ADCK.json","graph_json":"https://pith.science/api/pith-number/OC3IC6WIJ3MZRQM4YCJNN6ADCK/graph.json","events_json":"https://pith.science/api/pith-number/OC3IC6WIJ3MZRQM4YCJNN6ADCK/events.json","paper":"https://pith.science/paper/OC3IC6WI"},"agent_actions":{"view_html":"https://pith.science/pith/OC3IC6WIJ3MZRQM4YCJNN6ADCK","download_json":"https://pith.science/pith/OC3IC6WIJ3MZRQM4YCJNN6ADCK.json","view_paper":"https://pith.science/paper/OC3IC6WI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13028&json=true","fetch_graph":"https://pith.science/api/pith-number/OC3IC6WIJ3MZRQM4YCJNN6ADCK/graph.json","fetch_events":"https://pith.science/api/pith-number/OC3IC6WIJ3MZRQM4YCJNN6ADCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OC3IC6WIJ3MZRQM4YCJNN6ADCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OC3IC6WIJ3MZRQM4YCJNN6ADCK/action/storage_attestation","attest_author":"https://pith.science/pith/OC3IC6WIJ3MZRQM4YCJNN6ADCK/action/author_attestation","sign_citation":"https://pith.science/pith/OC3IC6WIJ3MZRQM4YCJNN6ADCK/action/citation_signature","submit_replication":"https://pith.science/pith/OC3IC6WIJ3MZRQM4YCJNN6ADCK/action/replication_record"}},"created_at":"2026-07-05T11:05:45.755864+00:00","updated_at":"2026-07-05T11:05:45.755864+00:00"}