{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZHOAIA7BRXCF2IBRKMNHYRRXNY","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":"19b71764724bb64ed456ec4271908cba40826cc1d7b9efbc79cea27ac2fc1d4f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T02:27:23Z","title_canon_sha256":"aa4f10204e7d2c2cb5d4df3246813ca6dca0a705e461dbc58e1987e8a31c49ba"},"schema_version":"1.0","source":{"id":"2502.12446","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12446","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12446v2","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12446","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"pith_short_12","alias_value":"ZHOAIA7BRXCF","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZHOAIA7BRXCF2IBR","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZHOAIA7B","created_at":"2026-07-05T11:34:04Z"}],"graph_snapshots":[{"event_id":"sha256:134a6cd7ccefad66de4e673fe3dd630ff5f183b730f6cdeae36910d15cb8b285","target":"graph","created_at":"2026-07-05T11:34:04Z","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/2502.12446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.g., improving helpfulness) by intervening on token representations without costly updates to the LLM's parameters. However, existing ITI approaches fail to scale to multi-attribute settings with conflicts, such as enhancing helpfulness while also reducing toxicity. To address this, we introduce Multi-Attribute Targeted Steering (MAT-Steer), a novel steering framework designed for selective token-level intervention across multiple attributes. MAT-Stee","authors_text":"Archiki Prasad, Duy Nguyen, Elias Stengel-Eskin, Mohit Bansal","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T02:27:23Z","title":"Multi-Attribute Steering of Language Models via Targeted Intervention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12446","kind":"arxiv","version":2},"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":"sha256:045d3b3ddb6159e857408893a304a8fb6e50599888cdbc6ea7e8d6b1c4540b63","target":"record","created_at":"2026-07-05T11:34:04Z","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":"19b71764724bb64ed456ec4271908cba40826cc1d7b9efbc79cea27ac2fc1d4f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T02:27:23Z","title_canon_sha256":"aa4f10204e7d2c2cb5d4df3246813ca6dca0a705e461dbc58e1987e8a31c49ba"},"schema_version":"1.0","source":{"id":"2502.12446","kind":"arxiv","version":2}},"canonical_sha256":"c9dc0403e18dc45d2031531a7c46376e2c0344b71220775cc4a1461fafac99b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9dc0403e18dc45d2031531a7c46376e2c0344b71220775cc4a1461fafac99b3","first_computed_at":"2026-07-05T11:34:04.596187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:04.596187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WSXjP/TD3qAoTktKWenFcHHNhmYqkDsx6enNp+vKf/qflgu7ohSKbgpLiC8fHJUGErVgqBwzrDsPimh5xrOfBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:04.596637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12446","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:045d3b3ddb6159e857408893a304a8fb6e50599888cdbc6ea7e8d6b1c4540b63","sha256:134a6cd7ccefad66de4e673fe3dd630ff5f183b730f6cdeae36910d15cb8b285"],"state_sha256":"f46967c50829b9b7da44a69e7dabc97316f8953b29418d2b983df7191bf01638"}