{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3QYZ2AM4WUO2ATTSPL5F6SH6BU","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":"72c9bf693f4e53755c1b8f27d1c0a0377bf31528a039e793b13b617550927de7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T02:02:06Z","title_canon_sha256":"a698ee5ff0f555206e153f07e50851977b680decef8e639b91e37ba0aebe59be"},"schema_version":"1.0","source":{"id":"2410.01174","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01174","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01174v1","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01174","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"pith_short_12","alias_value":"3QYZ2AM4WUO2","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"pith_short_16","alias_value":"3QYZ2AM4WUO2ATTS","created_at":"2026-07-05T09:14:44Z"},{"alias_kind":"pith_short_8","alias_value":"3QYZ2AM4","created_at":"2026-07-05T09:14:44Z"}],"graph_snapshots":[{"event_id":"sha256:3e1c23e75963e3bc73e5b854b0c352811c4366f302d3be9e5ddd5b1eb01ae6f3","target":"graph","created_at":"2026-07-05T09:14:44Z","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/2410.01174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large language models (LLMs) have seen unprecedented advancements in capabilities and applications across a variety of use-cases, safety alignment of these models is still an area of active research. The fragile nature of LLMs, even models that have undergone extensive alignment and safety training regimes, warrants additional safety steering steps via training-free, inference-time methods. While recent work in the area of mechanistic interpretability has investigated how activations in latent representation spaces may encode concepts, and thereafter performed representation engineering ","authors_text":"Amrita Bhattacharjee, Christopher Parisien, Shaona Ghosh, Traian Rebedea","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T02:02:06Z","title":"Towards Inference-time Category-wise Safety Steering for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01174","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":"sha256:7ae7d72e8a4fa49fcdd9b9878230dc3f967edba415efaf53a70e69dcec200616","target":"record","created_at":"2026-07-05T09:14:44Z","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":"72c9bf693f4e53755c1b8f27d1c0a0377bf31528a039e793b13b617550927de7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T02:02:06Z","title_canon_sha256":"a698ee5ff0f555206e153f07e50851977b680decef8e639b91e37ba0aebe59be"},"schema_version":"1.0","source":{"id":"2410.01174","kind":"arxiv","version":1}},"canonical_sha256":"dc319d019cb51da04e727afa5f48fe0d1fa25d26d8cc43a2941c76152b8ecda9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc319d019cb51da04e727afa5f48fe0d1fa25d26d8cc43a2941c76152b8ecda9","first_computed_at":"2026-07-05T09:14:44.327848Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:44.327848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S3/u0CucsobLG2XqHaaoxpJeB9yum7VbwA92Ic7/Lrnmu6yxT4NcNttNtUZwQNt/8xo/+oNsYAJMZjFMP7p8BA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:44.328303Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01174","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ae7d72e8a4fa49fcdd9b9878230dc3f967edba415efaf53a70e69dcec200616","sha256:3e1c23e75963e3bc73e5b854b0c352811c4366f302d3be9e5ddd5b1eb01ae6f3"],"state_sha256":"262e947310346696f4430674fa91bca5df10ad1aaa89eeddaecac27b83e24cda"}