{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AH3GCSAE2GWXG7QZB2HBKSQSVQ","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":"a79151ea2a50e304fce46c906a83488900810dd53059b78a1113cbcd91e2ac99","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-13T01:40:20Z","title_canon_sha256":"0b92e86b806102a688c0befdef883d8f4d274ef36b4f20e7ab4717e4538f8ed8"},"schema_version":"1.0","source":{"id":"2409.08466","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08466","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08466v2","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08466","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"pith_short_12","alias_value":"AH3GCSAE2GWX","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"pith_short_16","alias_value":"AH3GCSAE2GWXG7QZ","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"pith_short_8","alias_value":"AH3GCSAE","created_at":"2026-07-05T09:59:52Z"}],"graph_snapshots":[{"event_id":"sha256:8e5ed1f26a9e65a7b155bbc4eaa321c5b66c35deac867cba08ebbef6849b71aa","target":"graph","created_at":"2026-07-05T09:59:52Z","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/2409.08466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To make sense of massive data, we often fit simplified models and then interpret the parameters; for example, we cluster the text embeddings and then interpret the mean parameters of each cluster. However, these parameters are often high-dimensional and hard to interpret. To make model parameters directly interpretable, we introduce a family of statistical models -- including clustering, time series, and classification models -- parameterized by natural language predicates. For example, a cluster of text about COVID could be parameterized by the predicate \"discusses COVID\". To learn these stat","authors_text":"Dan Klein, Heng Wang, Jacob Steinhardt, Ruiqi Zhong","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-13T01:40:20Z","title":"Explaining Datasets in Words: Statistical Models with Natural Language Parameters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08466","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:c888aa8c2ed549f63289591213da075aebd088260c241f8fbc492cbfe7da34b5","target":"record","created_at":"2026-07-05T09:59:52Z","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":"a79151ea2a50e304fce46c906a83488900810dd53059b78a1113cbcd91e2ac99","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-13T01:40:20Z","title_canon_sha256":"0b92e86b806102a688c0befdef883d8f4d274ef36b4f20e7ab4717e4538f8ed8"},"schema_version":"1.0","source":{"id":"2409.08466","kind":"arxiv","version":2}},"canonical_sha256":"01f6614804d1ad737e190e8e154a12ac031a92b134a7634cbfc947297db33a98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01f6614804d1ad737e190e8e154a12ac031a92b134a7634cbfc947297db33a98","first_computed_at":"2026-07-05T09:59:52.456594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:52.456594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xywvq9wS8Z4ti0uOWX09AT2JX6yDXRBzYoJ4y6HyLZcnh3ODnes6Engcgv+QiqwOaxbqXw8xBneO5k8JrACuDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:52.456988Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08466","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c888aa8c2ed549f63289591213da075aebd088260c241f8fbc492cbfe7da34b5","sha256:8e5ed1f26a9e65a7b155bbc4eaa321c5b66c35deac867cba08ebbef6849b71aa"],"state_sha256":"176f652efdd8346b673574ede1346b1a6913c8ef0947a55dd5d3c7e372f5adaf"}