{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:75UUPW26FACR4ADH7TCBTJXLZF","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":"96624b45d11753140e1d0983ad687a36a0db79171cc76d9b790d82b4759c2f73","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T18:58:02Z","title_canon_sha256":"08b3d7064a2ddbbb54e5ab1d60e074039749ece3718f04f1e71f7160ffc4846a"},"schema_version":"1.0","source":{"id":"2502.04382","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04382","created_at":"2026-07-05T11:17:40Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04382v3","created_at":"2026-07-05T11:17:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04382","created_at":"2026-07-05T11:17:40Z"},{"alias_kind":"pith_short_12","alias_value":"75UUPW26FACR","created_at":"2026-07-05T11:17:40Z"},{"alias_kind":"pith_short_16","alias_value":"75UUPW26FACR4ADH","created_at":"2026-07-05T11:17:40Z"},{"alias_kind":"pith_short_8","alias_value":"75UUPW26","created_at":"2026-07-05T11:17:40Z"}],"graph_snapshots":[{"event_id":"sha256:71fdcc991d57c6eb8548206995b74270b6acc1013af9c7c9ef92b7183c61d778","target":"graph","created_at":"2026-07-05T11:17:40Z","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/2502.04382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We describe HypotheSAEs, a general method to hypothesize interpretable relationships between text data (e.g., headlines) and a target variable (e.g., clicks). HypotheSAEs has three steps: (1) train a sparse autoencoder on text embeddings to produce interpretable features describing the data distribution, (2) select features that predict the target variable, and (3) generate a natural language interpretation of each feature (e.g., \"mentions being surprised or shocked\") using an LLM. Each interpretation serves as a hypothesis about what predicts the target variable. Compared to baselines, our me","authors_text":"Emma Pierson, Jon Kleinberg, Kenny Peng, Nikhil Garg, Rajiv Movva","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T18:58:02Z","title":"Sparse Autoencoders for Hypothesis Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04382","kind":"arxiv","version":3},"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:a22fddb5ce39736bcc1153fb9669ab3d36a58790c77eadaaaf3b525be1b6f684","target":"record","created_at":"2026-07-05T11:17:40Z","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":"96624b45d11753140e1d0983ad687a36a0db79171cc76d9b790d82b4759c2f73","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T18:58:02Z","title_canon_sha256":"08b3d7064a2ddbbb54e5ab1d60e074039749ece3718f04f1e71f7160ffc4846a"},"schema_version":"1.0","source":{"id":"2502.04382","kind":"arxiv","version":3}},"canonical_sha256":"ff6947db5e28051e0067fcc419a6ebc952488f5debac262c1411a3670affac38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff6947db5e28051e0067fcc419a6ebc952488f5debac262c1411a3670affac38","first_computed_at":"2026-07-05T11:17:40.944079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:40.944079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+KY7pStu84A0Q9qLSc8e2J/+dmsVDpVXH4MORfC9fEF6wMOcVMHkQUr6bdD4qecKKZ1P85coh3Y8k5y9rYGPCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:40.944576Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04382","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a22fddb5ce39736bcc1153fb9669ab3d36a58790c77eadaaaf3b525be1b6f684","sha256:71fdcc991d57c6eb8548206995b74270b6acc1013af9c7c9ef92b7183c61d778"],"state_sha256":"a61e2186301738e0eeede0e4a5e76a78d5069e4f9cbbd74a2d03cefba0eb2193"}