{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FUM6QLJX2NOOWPRC4L37XUE3RY","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":"37ac9065a68be5aa2301227117527340d781c52b964d73e9cb194f5b3fa25ff2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T18:53:00Z","title_canon_sha256":"7cefc6dee2a4ae8f7daf899180dee7ccef20cd813f471f592a9f31e4b679769b"},"schema_version":"1.0","source":{"id":"2501.08319","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08319","created_at":"2026-07-05T11:11:39Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08319v2","created_at":"2026-07-05T11:11:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08319","created_at":"2026-07-05T11:11:39Z"},{"alias_kind":"pith_short_12","alias_value":"FUM6QLJX2NOO","created_at":"2026-07-05T11:11:39Z"},{"alias_kind":"pith_short_16","alias_value":"FUM6QLJX2NOOWPRC","created_at":"2026-07-05T11:11:39Z"},{"alias_kind":"pith_short_8","alias_value":"FUM6QLJX","created_at":"2026-07-05T11:11:39Z"}],"graph_snapshots":[{"event_id":"sha256:a373c06fdd069395aa0f79537772c8aaf7137c31570f1279d8e0a54cf9fa6244","target":"graph","created_at":"2026-07-05T11:11:39Z","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/2501.08319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated interpretability pipelines generate natural language descriptions for the concepts represented by features in large language models (LLMs), such as plants or the first word in a sentence. These descriptions are derived using inputs that activate the feature, which may be a dimension or a direction in the model's representation space. However, identifying activating inputs is costly, and the mechanistic role of a feature in model behavior is determined both by how inputs cause a feature to activate and by how feature activation affects outputs. Using steering evaluations, we reveal th","authors_text":"Atticus Geiger, Chen Agassy, Mor Geva, Roy Mayan, Yoav Gur-Arieh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T18:53:00Z","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08319","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":"sha256:6a22d223b354fa373afb9c5e4b2b1fdb2c56849168bcb6d7ae148891bcb992b4","target":"record","created_at":"2026-07-05T11:11:39Z","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":"37ac9065a68be5aa2301227117527340d781c52b964d73e9cb194f5b3fa25ff2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T18:53:00Z","title_canon_sha256":"7cefc6dee2a4ae8f7daf899180dee7ccef20cd813f471f592a9f31e4b679769b"},"schema_version":"1.0","source":{"id":"2501.08319","kind":"arxiv","version":2}},"canonical_sha256":"2d19e82d37d35ceb3e22e2f7fbd09b8e2aa315346592747d0e0f1569940a5a54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d19e82d37d35ceb3e22e2f7fbd09b8e2aa315346592747d0e0f1569940a5a54","first_computed_at":"2026-07-05T11:11:39.715624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:39.715624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"44SiAz6yidn6yek3gJjEKKaNFj/9mesIIfeQE/JPdrWzJNOnjOsPtzFBTNZRSrnjtWrgWn2xdV/LJamDFr5DCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:39.716173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08319","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a22d223b354fa373afb9c5e4b2b1fdb2c56849168bcb6d7ae148891bcb992b4","sha256:a373c06fdd069395aa0f79537772c8aaf7137c31570f1279d8e0a54cf9fa6244"],"state_sha256":"07a922edb68eb21d889b8ea11996a14df2c5627eb762d8207a1c1f0d6a0b3098"}