{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IKJMA223JJOMC7VB3FLR5545YS","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":"9ee341dd972a34f211f69dc6546f0c8469b3ea7c452925cdb73abc6b4d04cc6b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-25T21:40:26Z","title_canon_sha256":"d46774c8fa21c102bae28605f6f628f9ff2ad43bc3dae12284977746796b3ea2"},"schema_version":"1.0","source":{"id":"2505.19333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19333","created_at":"2026-07-05T11:09:28Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19333v1","created_at":"2026-07-05T11:09:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19333","created_at":"2026-07-05T11:09:28Z"},{"alias_kind":"pith_short_12","alias_value":"IKJMA223JJOM","created_at":"2026-07-05T11:09:28Z"},{"alias_kind":"pith_short_16","alias_value":"IKJMA223JJOMC7VB","created_at":"2026-07-05T11:09:28Z"},{"alias_kind":"pith_short_8","alias_value":"IKJMA223","created_at":"2026-07-05T11:09:28Z"}],"graph_snapshots":[{"event_id":"sha256:3326d418d76939abebd92f793d4edbd9fa25f11c3a48d8dc0c4691a3549d57f6","target":"graph","created_at":"2026-07-05T11:09:28Z","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/2505.19333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current evaluations of Large Language Model (LLM) steering techniques focus on task-specific performance, overlooking how well steered representations align with human cognition. Using a well-established triadic similarity judgment task, we assessed steered LLMs on their ability to flexibly judge similarity between concepts based on size or kind. We found that prompt-based steering methods outperformed other methods both in terms of steering accuracy and model-to-human alignment. We also found LLMs were biased towards 'kind' similarity and struggled with 'size' alignment. This evaluation appro","authors_text":"Kushin Mukherjee, Siddharth Suresh, Timothy T. Rogers, Zach Studdiford","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-25T21:40:26Z","title":"Evaluating Steering Techniques using Human Similarity Judgments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19333","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":"sha256:6c1b49c23a057cd83a12c30fc3e075809a3055caf92877ac62b4f9e5cd23ea7a","target":"record","created_at":"2026-07-05T11:09:28Z","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":"9ee341dd972a34f211f69dc6546f0c8469b3ea7c452925cdb73abc6b4d04cc6b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-25T21:40:26Z","title_canon_sha256":"d46774c8fa21c102bae28605f6f628f9ff2ad43bc3dae12284977746796b3ea2"},"schema_version":"1.0","source":{"id":"2505.19333","kind":"arxiv","version":1}},"canonical_sha256":"4292c06b5b4a5cc17ea1d9571ef79dc4b36f7fca5840fbdf2906739200d92c7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4292c06b5b4a5cc17ea1d9571ef79dc4b36f7fca5840fbdf2906739200d92c7f","first_computed_at":"2026-07-05T11:09:28.534913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:28.534913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cHoMRgOWfTy5qfbCR3faT1+4jAJnCOE34xKWCSM7vRKCBz4G7gtYhffce5X2wiCGvau2jX/aZd/cGkjaAZxvDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:28.535471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c1b49c23a057cd83a12c30fc3e075809a3055caf92877ac62b4f9e5cd23ea7a","sha256:3326d418d76939abebd92f793d4edbd9fa25f11c3a48d8dc0c4691a3549d57f6"],"state_sha256":"2ccd4b2433a85249623a3d6bd495cf14b45973c806ad98bc100da3d7464171bc"}