{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P2LYGWXFFUXRP243ZPXLN7TJNQ","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":"3a74ab6de8d5ee8b2d1cf3135cb4e5a1da1e73a583107fc1b357b5bd1bcb88f5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T22:57:30Z","title_canon_sha256":"daed49f2292afd0c9091cfbf0fb8b00fe2baf539ad3172fee461d7c4abbc3b28"},"schema_version":"1.0","source":{"id":"2606.08365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08365","created_at":"2026-06-09T01:05:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08365v1","created_at":"2026-06-09T01:05:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08365","created_at":"2026-06-09T01:05:34Z"},{"alias_kind":"pith_short_12","alias_value":"P2LYGWXFFUXR","created_at":"2026-06-09T01:05:34Z"},{"alias_kind":"pith_short_16","alias_value":"P2LYGWXFFUXRP243","created_at":"2026-06-09T01:05:34Z"},{"alias_kind":"pith_short_8","alias_value":"P2LYGWXF","created_at":"2026-06-09T01:05:34Z"}],"graph_snapshots":[{"event_id":"sha256:ece0564822f588bb38b363d6110234ed8182a25d7702c7da65f66eff741a26e3","target":"graph","created_at":"2026-06-09T01:05:34Z","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/2606.08365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse autoencoder (SAE) features are increasingly used to steer language models, but feature steering is rarely clean: the same intervention can behave inconsistently across contexts and perturb unrelated features. We introduce a pre-intervention screening framework for forecasting SAE steering side effects from feature statistics computed before steering. We operationalize side effects along two axes of steering modularity, effect stability and collateral spread, and evaluate GPT-2-small, Pythia-70M-deduped, Gemma-2-2B, and Llama-3.1-8B across ReLU, JumpReLU, and TopK SAE dictionaries. Acros","authors_text":"Evan Duan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T22:57:30Z","title":"Pre-Intervention Prediction of Sparse Autoencoder Steering Side Effects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08365","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":"sha256:9ba8011567f9e6b08026efa716b7f5c31bb983376814b4bf77eaf782926dedf1","target":"record","created_at":"2026-06-09T01:05:34Z","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":"3a74ab6de8d5ee8b2d1cf3135cb4e5a1da1e73a583107fc1b357b5bd1bcb88f5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T22:57:30Z","title_canon_sha256":"daed49f2292afd0c9091cfbf0fb8b00fe2baf539ad3172fee461d7c4abbc3b28"},"schema_version":"1.0","source":{"id":"2606.08365","kind":"arxiv","version":1}},"canonical_sha256":"7e97835ae52d2f17eb9bcbeeb6fe696c2ec1fa5059fd8db8bb4f25ccfeaeaa3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e97835ae52d2f17eb9bcbeeb6fe696c2ec1fa5059fd8db8bb4f25ccfeaeaa3e","first_computed_at":"2026-06-09T01:05:34.792924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:34.792924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/0KOqvsJU+bOUEmgdig62lx1FK5hWt50ERhPqreZlba7QQoLxTS5puAw5T3uEFCgosY0IMfxbZrBchdNE7yoAA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:34.793341Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ba8011567f9e6b08026efa716b7f5c31bb983376814b4bf77eaf782926dedf1","sha256:ece0564822f588bb38b363d6110234ed8182a25d7702c7da65f66eff741a26e3"],"state_sha256":"1ca7e81452628d51e6ded0398d7b3604ce7a071ac174e92d471d6de046277886"}