{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VELJK2NTYLYDVNCSIMJZHIJKVP","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":"dbdc3d9cf24e1fb955904f582ccafc66abaca2b11710e56a6167b3da8cf590b0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-21T10:18:25Z","title_canon_sha256":"8bfed3120f35c470129bcba026536010f5b6aecfb6ee5f33cb1802e764938552"},"schema_version":"1.0","source":{"id":"2506.17673","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17673","created_at":"2026-07-05T11:25:21Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17673v1","created_at":"2026-07-05T11:25:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17673","created_at":"2026-07-05T11:25:21Z"},{"alias_kind":"pith_short_12","alias_value":"VELJK2NTYLYD","created_at":"2026-07-05T11:25:21Z"},{"alias_kind":"pith_short_16","alias_value":"VELJK2NTYLYDVNCS","created_at":"2026-07-05T11:25:21Z"},{"alias_kind":"pith_short_8","alias_value":"VELJK2NT","created_at":"2026-07-05T11:25:21Z"}],"graph_snapshots":[{"event_id":"sha256:304f0c4f016f9024e004249c5cb5df26df30ecea54992268833d90c5569df6f7","target":"graph","created_at":"2026-07-05T11:25:21Z","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/2506.17673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse Autoencoders (SAEs) have emerged as a promising solution for decomposing large language model representations into interpretable features. However, Paulo and Belrose (2025) have highlighted instability across different initialization seeds, and Heap et al. (2025) have pointed out that SAEs may not capture model-internal features. These problems likely stem from training SAEs on external datasets - either collected from the Web or generated by another model - which may contain out-of-distribution (OOD) data beyond the model's generalisation capabilities. This can result in hallucinated S","authors_text":"Andrew Bermingham, Donghyun Lee, Harryn Oh, Luis Eduardo Rodrigues Vieira, Seonglae Cho, Ziad El Sayed","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-21T10:18:25Z","title":"FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17673","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:a993e92f105b91b8ca273b2171bf181220dba5e7499326a21a5a2657bd43e38e","target":"record","created_at":"2026-07-05T11:25:21Z","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":"dbdc3d9cf24e1fb955904f582ccafc66abaca2b11710e56a6167b3da8cf590b0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-21T10:18:25Z","title_canon_sha256":"8bfed3120f35c470129bcba026536010f5b6aecfb6ee5f33cb1802e764938552"},"schema_version":"1.0","source":{"id":"2506.17673","kind":"arxiv","version":1}},"canonical_sha256":"a9169569b3c2f03ab452431393a12aabc87a7014fd95a0632596b8b6813f6dbe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9169569b3c2f03ab452431393a12aabc87a7014fd95a0632596b8b6813f6dbe","first_computed_at":"2026-07-05T11:25:21.565754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:21.565754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xrSQE4fGZSq+L5gb0nuXGZKUhDXQrAwMGtuNVlsXUJHFNrsn3nJ3MVZh38IuOiwVMSphUV4dUOG8TGbnuHfgAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:21.566248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17673","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a993e92f105b91b8ca273b2171bf181220dba5e7499326a21a5a2657bd43e38e","sha256:304f0c4f016f9024e004249c5cb5df26df30ecea54992268833d90c5569df6f7"],"state_sha256":"3106d66ee3900f42aef5567ed8d9c3769e9119043ab7b31e1cbf1728efdb17e2"}