{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2O3KKWFJ4QEUUY3GRBITCN2MCN","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":"10410ca11363cde7a97835f40f5ef45904046011c6c194e87f3fd3685c589a1f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-06T22:19:46Z","title_canon_sha256":"53d57c1d0844de1675edd510c9b8b9bc1eaca485635cbb813a72e320d8c21784"},"schema_version":"1.0","source":{"id":"2504.04635","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04635","created_at":"2026-07-05T10:45:27Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04635v1","created_at":"2026-07-05T10:45:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04635","created_at":"2026-07-05T10:45:27Z"},{"alias_kind":"pith_short_12","alias_value":"2O3KKWFJ4QEU","created_at":"2026-07-05T10:45:27Z"},{"alias_kind":"pith_short_16","alias_value":"2O3KKWFJ4QEUUY3G","created_at":"2026-07-05T10:45:27Z"},{"alias_kind":"pith_short_8","alias_value":"2O3KKWFJ","created_at":"2026-07-05T10:45:27Z"}],"graph_snapshots":[{"event_id":"sha256:4c9334a0cbd03eef9606dbb7639701f6898f23e4f36ff5fa4e2d2253d5205645","target":"graph","created_at":"2026-07-05T10:45:27Z","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/2504.04635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Steering methods for language models (LMs) have gained traction as lightweight alternatives to fine-tuning, enabling targeted modifications to model activations. However, prior studies primarily report results on a few models, leaving critical gaps in understanding the robustness of these methods. In this work, we systematically examine three prominent steering methods -- DoLa, function vectors, and task vectors. In contrast to the original studies, which evaluated a handful of models, we test up to 36 models belonging to 14 families with sizes ranging from 1.5B to 70B parameters. Our experime","authors_text":"Dheeraj Rajagopal, Hannaneh Hajishirzi, Hari Sethuraman, Patrick Queiroz Da Silva, Sachin Kumar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-06T22:19:46Z","title":"Steering off Course: Reliability Challenges in Steering Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04635","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":"sha256:87b8fd9605dd7dcd427bf7eeedf5d627a592eac3f77972e053fd8c5810f6cd2a","target":"record","created_at":"2026-07-05T10:45:27Z","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":"10410ca11363cde7a97835f40f5ef45904046011c6c194e87f3fd3685c589a1f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-06T22:19:46Z","title_canon_sha256":"53d57c1d0844de1675edd510c9b8b9bc1eaca485635cbb813a72e320d8c21784"},"schema_version":"1.0","source":{"id":"2504.04635","kind":"arxiv","version":1}},"canonical_sha256":"d3b6a558a9e4094a6366885131374c137758b5d854f85e571b3d8973db6367e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3b6a558a9e4094a6366885131374c137758b5d854f85e571b3d8973db6367e0","first_computed_at":"2026-07-05T10:45:27.405947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:27.405947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ANLvChZNVtpMBZOsoR4OsPz7gvp/Bw1f8yQC1bMkoRf+IOJE2Ud5r53Z/YlWvUx7bugAsqJkzaPFLRg7daxDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:27.406445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04635","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87b8fd9605dd7dcd427bf7eeedf5d627a592eac3f77972e053fd8c5810f6cd2a","sha256:4c9334a0cbd03eef9606dbb7639701f6898f23e4f36ff5fa4e2d2253d5205645"],"state_sha256":"c68385b4d08506bd35a7cbff43e357b786a2a312097b49aff314cd10f455fec7"}