{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YIERGV26HLGG3PZ54FIQ2GVPTR","short_pith_number":"pith:YIERGV26","schema_version":"1.0","canonical_sha256":"c20913575e3acc6dbf3de1510d1aaf9c68f044960625ff14d0493e86e18e620a","source":{"kind":"arxiv","id":"2506.11094","version":2},"attestation_state":"computed","paper":{"title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CL","authors_text":"Chaozhuo Li, Feiran Huang, Jiameng Qiu, Litian Zhang, Philip S. Yu, Songyang Liu, Xi Zhang, Yiming Hei","submitted_at":"2025-06-06T05:50:50Z","abstract_excerpt":"With the rapid advancement of artificial intelligence, Large Language Models (LLMs) have shown remarkable capabilities in Natural Language Processing (NLP), including content generation, human-computer interaction, machine translation, and code generation. However, their widespread deployment has also raised significant safety concerns. In particular, LLM-generated content can exhibit unsafe behaviors such as toxicity, bias, or misinformation, especially in adversarial contexts, which has attracted increasing attention from both academia and industry. Although numerous studies have attempted t"},"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":"2506.11094","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T05:50:50Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"923c200c6f7d1c055438e8b4016d4baea910ea8067a6a91a9c28027ff7b9e4be","abstract_canon_sha256":"1422d0b2af9a25831db70e145bac3646453e02633c7cf812159a0df3738f38af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:40.108616Z","signature_b64":"1MEME+ZgC5rK9xZhIEz+xqTiKB1mxGI4uC6FtZknZPa5Dw5izTUt9FQHrChyjXgkEjrZUUnCxUrUO5kekXLeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c20913575e3acc6dbf3de1510d1aaf9c68f044960625ff14d0493e86e18e620a","last_reissued_at":"2026-07-01T01:17:40.108091Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:40.108091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CL","authors_text":"Chaozhuo Li, Feiran Huang, Jiameng Qiu, Litian Zhang, Philip S. Yu, Songyang Liu, Xi Zhang, Yiming Hei","submitted_at":"2025-06-06T05:50:50Z","abstract_excerpt":"With the rapid advancement of artificial intelligence, Large Language Models (LLMs) have shown remarkable capabilities in Natural Language Processing (NLP), including content generation, human-computer interaction, machine translation, and code generation. However, their widespread deployment has also raised significant safety concerns. In particular, LLM-generated content can exhibit unsafe behaviors such as toxicity, bias, or misinformation, especially in adversarial contexts, which has attracted increasing attention from both academia and industry. Although numerous studies have attempted t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11094","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/2506.11094/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":"2506.11094","created_at":"2026-07-01T01:17:40.108151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11094v2","created_at":"2026-07-01T01:17:40.108151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11094","created_at":"2026-07-01T01:17:40.108151+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIERGV26HLGG","created_at":"2026-07-01T01:17:40.108151+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIERGV26HLGG3PZ5","created_at":"2026-07-01T01:17:40.108151+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIERGV26","created_at":"2026-07-01T01:17:40.108151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2606.20626","citing_title":"Efficient Safety Benchmarking via Item Response Theory","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2508.05452","citing_title":"LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2512.10687","citing_title":"Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YIERGV26HLGG3PZ54FIQ2GVPTR","json":"https://pith.science/pith/YIERGV26HLGG3PZ54FIQ2GVPTR.json","graph_json":"https://pith.science/api/pith-number/YIERGV26HLGG3PZ54FIQ2GVPTR/graph.json","events_json":"https://pith.science/api/pith-number/YIERGV26HLGG3PZ54FIQ2GVPTR/events.json","paper":"https://pith.science/paper/YIERGV26"},"agent_actions":{"view_html":"https://pith.science/pith/YIERGV26HLGG3PZ54FIQ2GVPTR","download_json":"https://pith.science/pith/YIERGV26HLGG3PZ54FIQ2GVPTR.json","view_paper":"https://pith.science/paper/YIERGV26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11094&json=true","fetch_graph":"https://pith.science/api/pith-number/YIERGV26HLGG3PZ54FIQ2GVPTR/graph.json","fetch_events":"https://pith.science/api/pith-number/YIERGV26HLGG3PZ54FIQ2GVPTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIERGV26HLGG3PZ54FIQ2GVPTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIERGV26HLGG3PZ54FIQ2GVPTR/action/storage_attestation","attest_author":"https://pith.science/pith/YIERGV26HLGG3PZ54FIQ2GVPTR/action/author_attestation","sign_citation":"https://pith.science/pith/YIERGV26HLGG3PZ54FIQ2GVPTR/action/citation_signature","submit_replication":"https://pith.science/pith/YIERGV26HLGG3PZ54FIQ2GVPTR/action/replication_record"}},"created_at":"2026-07-01T01:17:40.108151+00:00","updated_at":"2026-07-01T01:17:40.108151+00:00"}