{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FSLJZQXSN4NPKJVPDOTMPCPN6T","short_pith_number":"pith:FSLJZQXS","canonical_record":{"source":{"id":"2602.06941","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T18:41:12Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0e0340754280d833c21176fafedad039417ef09f42f1e56213519c0373759272","abstract_canon_sha256":"283d474a2aa49a59d89c3a6bbd4b1b27738a66a9891f67913bab0f57540e02f7"},"schema_version":"1.0"},"canonical_sha256":"2c969cc2f26f1af526af1ba6c789edf4eab82f08aefbc91dc453a06ad9522a07","source":{"kind":"arxiv","id":"2602.06941","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.06941","created_at":"2026-06-08T01:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2602.06941v2","created_at":"2026-06-08T01:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06941","created_at":"2026-06-08T01:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"FSLJZQXSN4NP","created_at":"2026-06-08T01:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"FSLJZQXSN4NPKJVP","created_at":"2026-06-08T01:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"FSLJZQXS","created_at":"2026-06-08T01:03:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FSLJZQXSN4NPKJVPDOTMPCPN6T","target":"record","payload":{"canonical_record":{"source":{"id":"2602.06941","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T18:41:12Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0e0340754280d833c21176fafedad039417ef09f42f1e56213519c0373759272","abstract_canon_sha256":"283d474a2aa49a59d89c3a6bbd4b1b27738a66a9891f67913bab0f57540e02f7"},"schema_version":"1.0"},"canonical_sha256":"2c969cc2f26f1af526af1ba6c789edf4eab82f08aefbc91dc453a06ad9522a07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:58.019788Z","signature_b64":"mQ6uJ3glpV9sbxy+Rao7a1wq4aHtAdrJP8bq4z130h3PGVR9u1HRXjen5c9zEiZPBytjBa4VW4++ZRajER/uDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c969cc2f26f1af526af1ba6c789edf4eab82f08aefbc91dc453a06ad9522a07","last_reissued_at":"2026-06-08T01:03:58.018854Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:58.018854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.06941","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:03:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"INjs30GLcEhemvugwqMI4PUHFF1N8Bz9zO2Ab4hBIu6Z464OrqRfLykAOrWlhQ9SpI0tffJ0mfl208V0I6KVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T08:43:40.473983Z"},"content_sha256":"7a44933b383f5a0adb11da046bbb3652ff8d38321a8704a7d6310fc8bef24988","schema_version":"1.0","event_id":"sha256:7a44933b383f5a0adb11da046bbb3652ff8d38321a8704a7d6310fc8bef24988"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FSLJZQXSN4NPKJVPDOTMPCPN6T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Endogenous Resistance to Activation Steering in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alex McKenzie, Diogo de Lucena, Judd Rosenblatt, Keenan Pepper, Martin Leitgab, Michael S. A. Graziano, Mike Vaiana, Murat Cubuktepe, Stijn Servaes","submitted_at":"2026-02-06T18:41:12Z","abstract_excerpt":"Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.g., ``wait, that's not right'') and continuing on-topic even while the steering perturbation remains active. We term this Endogenous Steering Resistance (ESR). Using sparse autoencoder (SAE) latents to steer model activations, we find that Llama-3.3-70B exhibits explicit ESR at \\llamaseventyEsrRate\\%, with smaller models from the Llama-3 and Gemma-2 families showing the explicit form less frequently. Two controls dissociate ESR into a detection event and a sustained-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06941","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.06941/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:03:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v0bYLJutN9wJ/UJkDRnSAQSfkd2O568aA3TiiY+fRqs+Ad1sh60rL9UAHVGOlSjo8tKA1pJpLe4VJ3QliRdwCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T08:43:40.474666Z"},"content_sha256":"d2e9d32955e787686525d74ef52a7c198b2b4bcb996f7e79128600f0ec01c24d","schema_version":"1.0","event_id":"sha256:d2e9d32955e787686525d74ef52a7c198b2b4bcb996f7e79128600f0ec01c24d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FSLJZQXSN4NPKJVPDOTMPCPN6T/bundle.json","state_url":"https://pith.science/pith/FSLJZQXSN4NPKJVPDOTMPCPN6T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FSLJZQXSN4NPKJVPDOTMPCPN6T/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T08:43:40Z","links":{"resolver":"https://pith.science/pith/FSLJZQXSN4NPKJVPDOTMPCPN6T","bundle":"https://pith.science/pith/FSLJZQXSN4NPKJVPDOTMPCPN6T/bundle.json","state":"https://pith.science/pith/FSLJZQXSN4NPKJVPDOTMPCPN6T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FSLJZQXSN4NPKJVPDOTMPCPN6T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FSLJZQXSN4NPKJVPDOTMPCPN6T","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":"283d474a2aa49a59d89c3a6bbd4b1b27738a66a9891f67913bab0f57540e02f7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T18:41:12Z","title_canon_sha256":"0e0340754280d833c21176fafedad039417ef09f42f1e56213519c0373759272"},"schema_version":"1.0","source":{"id":"2602.06941","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.06941","created_at":"2026-06-08T01:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2602.06941v2","created_at":"2026-06-08T01:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06941","created_at":"2026-06-08T01:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"FSLJZQXSN4NP","created_at":"2026-06-08T01:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"FSLJZQXSN4NPKJVP","created_at":"2026-06-08T01:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"FSLJZQXS","created_at":"2026-06-08T01:03:58Z"}],"graph_snapshots":[{"event_id":"sha256:d2e9d32955e787686525d74ef52a7c198b2b4bcb996f7e79128600f0ec01c24d","target":"graph","created_at":"2026-06-08T01:03:58Z","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/2602.06941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.g., ``wait, that's not right'') and continuing on-topic even while the steering perturbation remains active. We term this Endogenous Steering Resistance (ESR). Using sparse autoencoder (SAE) latents to steer model activations, we find that Llama-3.3-70B exhibits explicit ESR at \\llamaseventyEsrRate\\%, with smaller models from the Llama-3 and Gemma-2 families showing the explicit form less frequently. Two controls dissociate ESR into a detection event and a sustained-","authors_text":"Alex McKenzie, Diogo de Lucena, Judd Rosenblatt, Keenan Pepper, Martin Leitgab, Michael S. A. Graziano, Mike Vaiana, Murat Cubuktepe, Stijn Servaes","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T18:41:12Z","title":"Endogenous Resistance to Activation Steering in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06941","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":"sha256:7a44933b383f5a0adb11da046bbb3652ff8d38321a8704a7d6310fc8bef24988","target":"record","created_at":"2026-06-08T01:03:58Z","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":"283d474a2aa49a59d89c3a6bbd4b1b27738a66a9891f67913bab0f57540e02f7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T18:41:12Z","title_canon_sha256":"0e0340754280d833c21176fafedad039417ef09f42f1e56213519c0373759272"},"schema_version":"1.0","source":{"id":"2602.06941","kind":"arxiv","version":2}},"canonical_sha256":"2c969cc2f26f1af526af1ba6c789edf4eab82f08aefbc91dc453a06ad9522a07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c969cc2f26f1af526af1ba6c789edf4eab82f08aefbc91dc453a06ad9522a07","first_computed_at":"2026-06-08T01:03:58.018854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:03:58.018854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mQ6uJ3glpV9sbxy+Rao7a1wq4aHtAdrJP8bq4z130h3PGVR9u1HRXjen5c9zEiZPBytjBa4VW4++ZRajER/uDQ==","signature_status":"signed_v1","signed_at":"2026-06-08T01:03:58.019788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.06941","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a44933b383f5a0adb11da046bbb3652ff8d38321a8704a7d6310fc8bef24988","sha256:d2e9d32955e787686525d74ef52a7c198b2b4bcb996f7e79128600f0ec01c24d"],"state_sha256":"d12229699cf04fd21e32cf68e8c1144015bb4f6c4c6c722603634daf1753a333"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wYP4QHGOi1+FtonbCw3jjVWYwH2p0SEXS0T+dgcBJjzWQKg3wLKdROe2KPwalgqUWPuFalaVl/Afl0kHbYjkBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T08:43:40.478524Z","bundle_sha256":"b17be27e5c42016a5589706bde6c84a8ea3dc204ee78db9885f7383fb9460403"}}