{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RYCS6RI2FUPUHP42YMP4HZZA4J","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":"4d87b4c7d0b997c0cb431180c5be992f3706786b6a2be74079347d9ec8e01550","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-08T09:54:47Z","title_canon_sha256":"8bc5c33fb81d63610eb085a5198d98ff1cc523c21df00c31bd0e097d2fe5c06c"},"schema_version":"1.0","source":{"id":"2502.08657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08657","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08657v1","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08657","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"pith_short_12","alias_value":"RYCS6RI2FUPU","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"pith_short_16","alias_value":"RYCS6RI2FUPUHP42","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"pith_short_8","alias_value":"RYCS6RI2","created_at":"2026-07-05T10:13:28Z"}],"graph_snapshots":[{"event_id":"sha256:dd6e35d11ab357a9696e949f9830d3823b829196393c0c00e366040505ca97f4","target":"graph","created_at":"2026-07-05T10:13:28Z","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/2502.08657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent AI agents, such as ChatGPT and LLaMA, primarily rely on instruction tuning and reinforcement learning to calibrate the output of large language models (LLMs) with human intentions, ensuring the outputs are harmless and helpful. Existing methods heavily depend on the manual annotation of high-quality positive samples, while contending with issues such as noisy labels and minimal distinctions between preferred and dispreferred response data. However, readily available toxic samples with clear safety distinctions are often filtered out, removing valuable negative references that could aid ","authors_text":"Guoshun Nan, Jingxin Xu, Sheng Guan, Sicong Leng, Xiaofeng Tao, Yanzhao Hou, Yilian Liu, Yuyang Ma, Zhili Zhou, Zixiao Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-08T09:54:47Z","title":"Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08657","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":"sha256:7538b9c8e960684fa52e2360e8525f7d50c21b5e053efaa8f2f9c0254d656924","target":"record","created_at":"2026-07-05T10:13:28Z","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":"4d87b4c7d0b997c0cb431180c5be992f3706786b6a2be74079347d9ec8e01550","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-08T09:54:47Z","title_canon_sha256":"8bc5c33fb81d63610eb085a5198d98ff1cc523c21df00c31bd0e097d2fe5c06c"},"schema_version":"1.0","source":{"id":"2502.08657","kind":"arxiv","version":1}},"canonical_sha256":"8e052f451a2d1f43bf9ac31fc3e720e26e575d1999576b686f1214b628323f79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e052f451a2d1f43bf9ac31fc3e720e26e575d1999576b686f1214b628323f79","first_computed_at":"2026-07-05T10:13:28.065477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:28.065477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ucsTROmBOud4fjeL1GpJL7K60sZZVYkrRR8T6oVfaRndthgOZHiOBEHOXSaI0xVCz4vVwNscowaOX2MFvB58Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:28.065891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7538b9c8e960684fa52e2360e8525f7d50c21b5e053efaa8f2f9c0254d656924","sha256:dd6e35d11ab357a9696e949f9830d3823b829196393c0c00e366040505ca97f4"],"state_sha256":"7b3aeb25b4c1e66cf1b49e1281647e088d4870c93f8edf023b8ea4a941f9d65a"}