{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A6BJG3MDFGRHVEARUPMICE2PCY","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":"972a57118a72b69185af5e21234e99ddefc0cb67cfb9160c736bc23c372c1bb7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T07:54:25Z","title_canon_sha256":"47d77fbb04572837095ff536c087d4867f891f2d7dbe86dbf7c143911fa0037e"},"schema_version":"1.0","source":{"id":"2606.08496","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08496","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08496v1","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08496","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"A6BJG3MDFGRH","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"A6BJG3MDFGRHVEAR","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"A6BJG3MD","created_at":"2026-06-09T01:05:38Z"}],"graph_snapshots":[{"event_id":"sha256:bf1f4cba2d438acf1f853ac5c0a8725c2196c59f9bb38a76e9ea01d219bf9d9c","target":"graph","created_at":"2026-06-09T01:05:38Z","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/2606.08496/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although Sparse Autoencoders (SAEs) have mitigated the opacity of large language models (LLMs) by decomposing dense representations into sparse features, explaining these features still remains a central challenge. Current explanation methods, however, typically operate within an open-loop paradigm, failing to leverage mechanistic feedback for further refinement. In this paper, we propose SAEExplainer, a training framework utilizes activation scores as an objective reward signal to train the model for self-correction and iterative bootstrapping. By iteratively verifying and correcting foundati","authors_text":"Fei Sun, Haiyan Zhao, Jingyi He, Mengnan Du, Ruxue Shi, Xin Wang, Yanguang Liu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T07:54:25Z","title":"SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08496","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":"sha256:5793fd2ed22ff46f251587b06abf468dc174beae0b68ab4a506c25bb286724e6","target":"record","created_at":"2026-06-09T01:05:38Z","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":"972a57118a72b69185af5e21234e99ddefc0cb67cfb9160c736bc23c372c1bb7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T07:54:25Z","title_canon_sha256":"47d77fbb04572837095ff536c087d4867f891f2d7dbe86dbf7c143911fa0037e"},"schema_version":"1.0","source":{"id":"2606.08496","kind":"arxiv","version":1}},"canonical_sha256":"0782936d8329a27a9011a3d881134f161cb9d7d73301a570cc0c14a08be6a1e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0782936d8329a27a9011a3d881134f161cb9d7d73301a570cc0c14a08be6a1e4","first_computed_at":"2026-06-09T01:05:38.339533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:38.339533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lWs5k3rJFLyKw60PT5pZuh1OK9rOiqouPUBB2TtW/0vfCQplGHaxbvwV6MV+5GPiPs8cAXNBr7w208yST5JeBA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:38.339971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08496","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5793fd2ed22ff46f251587b06abf468dc174beae0b68ab4a506c25bb286724e6","sha256:bf1f4cba2d438acf1f853ac5c0a8725c2196c59f9bb38a76e9ea01d219bf9d9c"],"state_sha256":"f37dff478c16ffc28ccf1aa1026f10417f520e887d521f6437bdc6add715e1f8"}