{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ASWJJAAYB3NBVPYLXMFACS4O34","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":"99e3926c4275b51ca477a9b1290b26d2bd279ee6e4de9a0b1246524d568a3dc0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T22:21:18Z","title_canon_sha256":"c97eb238ac0356ed5ad701a9f2c3f122adb6adc4e8cb0e816f07799e6e70c014"},"schema_version":"1.0","source":{"id":"2507.11771","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11771","created_at":"2026-07-05T11:37:50Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11771v1","created_at":"2026-07-05T11:37:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11771","created_at":"2026-07-05T11:37:50Z"},{"alias_kind":"pith_short_12","alias_value":"ASWJJAAYB3NB","created_at":"2026-07-05T11:37:50Z"},{"alias_kind":"pith_short_16","alias_value":"ASWJJAAYB3NBVPYL","created_at":"2026-07-05T11:37:50Z"},{"alias_kind":"pith_short_8","alias_value":"ASWJJAAY","created_at":"2026-07-05T11:37:50Z"}],"graph_snapshots":[{"event_id":"sha256:a896329eecb80e106b72b9dc520f87769d3e31bce892b52bc2ba4e1afd00071c","target":"graph","created_at":"2026-07-05T11:37:50Z","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/2507.11771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) evolve in complexity and capability, the efficacy of less widely deployed alignment techniques are uncertain. Building on previous work on activation steering and contrastive activation addition (CAA), this paper explores the effectiveness of CAA with model scale using the family of Llama 2 models (7B, 13B, and 70B). CAA works by finding desirable 'directions' in the model's residual stream vector space using contrastive pairs (for example, hate to love) and adding this direction to the residual stream during the forward pass. It directly manipulates the residua","authors_text":"Ayse Arslan, Clark Benham, Ivory Yang, Jasmine Xinze Li, Justin Xu, Sheikh Abdur Raheem Ali","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T22:21:18Z","title":"Scaling laws for activation steering with Llama 2 models and refusal mechanisms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11771","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":"sha256:0d58d8756f69fd0dd5ea3f43aa2e6ac05c521d384fe7ed9ac04256aef4fd0510","target":"record","created_at":"2026-07-05T11:37:50Z","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":"99e3926c4275b51ca477a9b1290b26d2bd279ee6e4de9a0b1246524d568a3dc0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T22:21:18Z","title_canon_sha256":"c97eb238ac0356ed5ad701a9f2c3f122adb6adc4e8cb0e816f07799e6e70c014"},"schema_version":"1.0","source":{"id":"2507.11771","kind":"arxiv","version":1}},"canonical_sha256":"04ac9480180eda1abf0bbb0a014b8edf2a3b36ebc3b2740116f0664b44f87511","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04ac9480180eda1abf0bbb0a014b8edf2a3b36ebc3b2740116f0664b44f87511","first_computed_at":"2026-07-05T11:37:50.559204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:50.559204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Jhv8xJm0ioPVhRJ5iHeNEB7sBcGHDwrKf7QRxmB3vbi4Ii0FlkT73B8d1uRocGJ/YpKBqzviRwhtt/SUvG5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:50.559745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.11771","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d58d8756f69fd0dd5ea3f43aa2e6ac05c521d384fe7ed9ac04256aef4fd0510","sha256:a896329eecb80e106b72b9dc520f87769d3e31bce892b52bc2ba4e1afd00071c"],"state_sha256":"21d9737f83f412b5efc939fc783069841c330f4065594f7039f263f49ec86160"}