{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YQTEBTQA7AFIEIRVBW4H4NPHMM","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":"35970e1747bb7dfbc4dbce08f66697169f395c37de5e390e382f5e9bf429367f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-29T09:04:27Z","title_canon_sha256":"78cd9ec7c817493668dbf5d2459b7e83c92c6a933c18284145735c101066ac02"},"schema_version":"1.0","source":{"id":"2606.00160","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00160","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00160v1","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00160","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"YQTEBTQA7AFI","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"pith_short_16","alias_value":"YQTEBTQA7AFIEIRV","created_at":"2026-06-02T01:03:20Z"},{"alias_kind":"pith_short_8","alias_value":"YQTEBTQA","created_at":"2026-06-02T01:03:20Z"}],"graph_snapshots":[{"event_id":"sha256:4ce0cbd2cce1f4e1cd56cac0f939ef1192eddaba120ccd1b3ce9e5ad7ea89788","target":"graph","created_at":"2026-06-02T01:03:20Z","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/2606.00160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets. However, existing methods for identifying safety-degrading samples in benign datasets suffer from high computational costs and significant noise issues. In this paper, we propose DataShield to efficiently and effectively identify potential safety-degrading samples. Our key intuition is based on the observation that benign fine-tuning increases the overall response compliance of LLMs. DataShield's key technical insight is to quantify each sample's contribution to the model's complian","authors_text":"Jie Pan, Jinbiao Zhu, Junbo Zhang, Qianli Zhou, Wen Jiang, Xinyang Deng","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-29T09:04:27Z","title":"DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00160","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":"sha256:7daa27a2cbd07160dc49d4717a630449b44333c61ed77db6e27fb896f23bb862","target":"record","created_at":"2026-06-02T01:03:20Z","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":"35970e1747bb7dfbc4dbce08f66697169f395c37de5e390e382f5e9bf429367f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-29T09:04:27Z","title_canon_sha256":"78cd9ec7c817493668dbf5d2459b7e83c92c6a933c18284145735c101066ac02"},"schema_version":"1.0","source":{"id":"2606.00160","kind":"arxiv","version":1}},"canonical_sha256":"c42640ce00f80a8222350db87e35e7630fb63f4f54a28aa071c1ef93dd0da80e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c42640ce00f80a8222350db87e35e7630fb63f4f54a28aa071c1ef93dd0da80e","first_computed_at":"2026-06-02T01:03:20.153272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:20.153272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fqmY5Jh72WkfSzF43duFvynpyFX/YR5t+DmjAh+rg3mJAD03CJ95I2VjAUvVaXTZErsNHx4zMpCC6ZzgI874DA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:20.153702Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00160","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7daa27a2cbd07160dc49d4717a630449b44333c61ed77db6e27fb896f23bb862","sha256:4ce0cbd2cce1f4e1cd56cac0f939ef1192eddaba120ccd1b3ce9e5ad7ea89788"],"state_sha256":"3d75beed08d0af391d21d65d5fabb36fb0e475d4c0653db7530aa9096bed8af2"}