{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7EEPQ7ZSQOP43ZOIR4XBLA7GLY","short_pith_number":"pith:7EEPQ7ZS","schema_version":"1.0","canonical_sha256":"f908f87f32839fcde5c88f2e1583e65e28859f5b7f4941a2a582c17bcda1555e","source":{"kind":"arxiv","id":"2601.15588","version":2},"attestation_state":"computed","paper":{"title":"YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Defeng Li, Haiwen Hong, Hui Xue, Jinfeng Li, Junyu Lin, Lingyao Gao, Longtao Huang, Meizhen Liu, Ranjie Duan, Xiaohan Yuan, Xiufeng Huang, Yitong Yang, Yuchuan Fu, Yuefeng Chen, Zhikai Chen","submitted_at":"2026-01-22T02:23:18Z","abstract_excerpt":"As large language models (LLMs) are increasingly deployed in real-world applications, safety guardrails are required to go beyond coarse-grained filtering and support fine-grained, interpretable, and adaptable risk assessment. However, existing solutions often rely on rapid classification schemes or post-hoc rules, resulting in limited transparency, inflexible policies, or prohibitive inference costs. To this end, we present YuFeng-XGuard, a reasoning-centric guardrail model family designed to perform multi-dimensional risk perception for LLM interactions. Instead of producing opaque binary ju"},"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":"2601.15588","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-22T02:23:18Z","cross_cats_sorted":[],"title_canon_sha256":"6763dcd2b0710607cbb968059300c4a65a58f1b1c25a2e930dda758916691f7c","abstract_canon_sha256":"9276d0709b7917fbfc7985d181f604a2d36768dc7c659a96728715b29d5ee4c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:16.670326Z","signature_b64":"5j4++MmcUKK0AnEt8EG1XSZie1/HZwCx0l7aJRQx22C7zJNoa5Y0Qb6cNSkP9eGGzzB74AtvxD9SFf/53bwOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f908f87f32839fcde5c88f2e1583e65e28859f5b7f4941a2a582c17bcda1555e","last_reissued_at":"2026-07-03T01:17:16.669837Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:16.669837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Defeng Li, Haiwen Hong, Hui Xue, Jinfeng Li, Junyu Lin, Lingyao Gao, Longtao Huang, Meizhen Liu, Ranjie Duan, Xiaohan Yuan, Xiufeng Huang, Yitong Yang, Yuchuan Fu, Yuefeng Chen, Zhikai Chen","submitted_at":"2026-01-22T02:23:18Z","abstract_excerpt":"As large language models (LLMs) are increasingly deployed in real-world applications, safety guardrails are required to go beyond coarse-grained filtering and support fine-grained, interpretable, and adaptable risk assessment. However, existing solutions often rely on rapid classification schemes or post-hoc rules, resulting in limited transparency, inflexible policies, or prohibitive inference costs. To this end, we present YuFeng-XGuard, a reasoning-centric guardrail model family designed to perform multi-dimensional risk perception for LLM interactions. Instead of producing opaque binary ju"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.15588","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/2601.15588/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":"2601.15588","created_at":"2026-07-03T01:17:16.669895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.15588v2","created_at":"2026-07-03T01:17:16.669895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.15588","created_at":"2026-07-03T01:17:16.669895+00:00"},{"alias_kind":"pith_short_12","alias_value":"7EEPQ7ZSQOP4","created_at":"2026-07-03T01:17:16.669895+00:00"},{"alias_kind":"pith_short_16","alias_value":"7EEPQ7ZSQOP43ZOI","created_at":"2026-07-03T01:17:16.669895+00:00"},{"alias_kind":"pith_short_8","alias_value":"7EEPQ7ZS","created_at":"2026-07-03T01:17:16.669895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"2607.01793","citing_title":"Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02041","citing_title":"SentGuard: Sentence-Level Streaming Guardrails for Large Language Models","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01166","citing_title":"BraveGuard: From Open-World Threats to Safer Computer-Use Agents","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25034","citing_title":"Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27632","citing_title":"Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17329","citing_title":"LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2602.17283","citing_title":"Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05277","citing_title":"GLiNER Guard: Unified Encoder Family for Production LLM Safety and Privacy","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7EEPQ7ZSQOP43ZOIR4XBLA7GLY","json":"https://pith.science/pith/7EEPQ7ZSQOP43ZOIR4XBLA7GLY.json","graph_json":"https://pith.science/api/pith-number/7EEPQ7ZSQOP43ZOIR4XBLA7GLY/graph.json","events_json":"https://pith.science/api/pith-number/7EEPQ7ZSQOP43ZOIR4XBLA7GLY/events.json","paper":"https://pith.science/paper/7EEPQ7ZS"},"agent_actions":{"view_html":"https://pith.science/pith/7EEPQ7ZSQOP43ZOIR4XBLA7GLY","download_json":"https://pith.science/pith/7EEPQ7ZSQOP43ZOIR4XBLA7GLY.json","view_paper":"https://pith.science/paper/7EEPQ7ZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.15588&json=true","fetch_graph":"https://pith.science/api/pith-number/7EEPQ7ZSQOP43ZOIR4XBLA7GLY/graph.json","fetch_events":"https://pith.science/api/pith-number/7EEPQ7ZSQOP43ZOIR4XBLA7GLY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7EEPQ7ZSQOP43ZOIR4XBLA7GLY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7EEPQ7ZSQOP43ZOIR4XBLA7GLY/action/storage_attestation","attest_author":"https://pith.science/pith/7EEPQ7ZSQOP43ZOIR4XBLA7GLY/action/author_attestation","sign_citation":"https://pith.science/pith/7EEPQ7ZSQOP43ZOIR4XBLA7GLY/action/citation_signature","submit_replication":"https://pith.science/pith/7EEPQ7ZSQOP43ZOIR4XBLA7GLY/action/replication_record"}},"created_at":"2026-07-03T01:17:16.669895+00:00","updated_at":"2026-07-03T01:17:16.669895+00:00"}