{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6G4TBLATTF4C7BPC32RT5QDWZK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9f899459b155688a86f8ee2fe4b3c72b27f8e8899f0fa842f60fd8f631878910","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T16:21:29Z","title_canon_sha256":"6e6437b964d6eda29a8e68d037d724af42d1c395c0224064d099bfe6d02a4222"},"schema_version":"1.0","source":{"id":"2505.15710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15710","created_at":"2026-07-05T11:06:49Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15710v1","created_at":"2026-07-05T11:06:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15710","created_at":"2026-07-05T11:06:49Z"},{"alias_kind":"pith_short_12","alias_value":"6G4TBLATTF4C","created_at":"2026-07-05T11:06:49Z"},{"alias_kind":"pith_short_16","alias_value":"6G4TBLATTF4C7BPC","created_at":"2026-07-05T11:06:49Z"},{"alias_kind":"pith_short_8","alias_value":"6G4TBLAT","created_at":"2026-07-05T11:06:49Z"}],"graph_snapshots":[{"event_id":"sha256:9db9effc83c95783ae63826ca7e38107016ecf5cff8ad80e37f629adb16267ca","target":"graph","created_at":"2026-07-05T11:06:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.15710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancement of large language models (LLMs) has demonstrated milestone success in a variety of tasks, yet their potential for generating harmful content has raised significant safety concerns. Existing safety evaluation approaches typically operate directly on textual responses, overlooking the rich information embedded in the model's internal representations. In this paper, we propose Safety Representation Ranking (SRR), a listwise ranking framework that selects safe responses using hidden states from the LLM itself. SRR encodes both instructions and candidate completions using inte","authors_text":"Chenheng Zhang, Quan Chen, Tianqi Du, Yisen Wang, Zeming Wei","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T16:21:29Z","title":"Advancing LLM Safe Alignment with Safety Representation Ranking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15710","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:952639d792fda0761bebaf56ea968a2fada15fa36736318b0a4cd1d5e49c4927","target":"record","created_at":"2026-07-05T11:06:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9f899459b155688a86f8ee2fe4b3c72b27f8e8899f0fa842f60fd8f631878910","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T16:21:29Z","title_canon_sha256":"6e6437b964d6eda29a8e68d037d724af42d1c395c0224064d099bfe6d02a4222"},"schema_version":"1.0","source":{"id":"2505.15710","kind":"arxiv","version":1}},"canonical_sha256":"f1b930ac1399782f85e2dea33ec076caa1fe79b224101492dea062f31f9d8cfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1b930ac1399782f85e2dea33ec076caa1fe79b224101492dea062f31f9d8cfc","first_computed_at":"2026-07-05T11:06:49.871617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:49.871617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ifBxVIDOCzLM8AWqf5e2s2y7n4Wk7rP74p5tYs0AlwCFUm34l6EbCYGiGWlrX5Mf7DnYZvGOm1qewAUtldCdDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:49.872242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:952639d792fda0761bebaf56ea968a2fada15fa36736318b0a4cd1d5e49c4927","sha256:9db9effc83c95783ae63826ca7e38107016ecf5cff8ad80e37f629adb16267ca"],"state_sha256":"4d384601ef702a4af40c3a0131e4722983ab67fc6b0df85e9833f496caf00da4"}