{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AH3GCSAE2GWXG7QZB2HBKSQSVQ","short_pith_number":"pith:AH3GCSAE","schema_version":"1.0","canonical_sha256":"01f6614804d1ad737e190e8e154a12ac031a92b134a7634cbfc947297db33a98","source":{"kind":"arxiv","id":"2409.08466","version":2},"attestation_state":"computed","paper":{"title":"Explaining Datasets in Words: Statistical Models with Natural Language Parameters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Dan Klein, Heng Wang, Jacob Steinhardt, Ruiqi Zhong","submitted_at":"2024-09-13T01:40:20Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.08466","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-13T01:40:20Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"0b92e86b806102a688c0befdef883d8f4d274ef36b4f20e7ab4717e4538f8ed8","abstract_canon_sha256":"a79151ea2a50e304fce46c906a83488900810dd53059b78a1113cbcd91e2ac99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:52.456988Z","signature_b64":"Xywvq9wS8Z4ti0uOWX09AT2JX6yDXRBzYoJ4y6HyLZcnh3ODnes6Engcgv+QiqwOaxbqXw8xBneO5k8JrACuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01f6614804d1ad737e190e8e154a12ac031a92b134a7634cbfc947297db33a98","last_reissued_at":"2026-07-05T09:59:52.456594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:52.456594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explaining Datasets in Words: Statistical Models with Natural Language Parameters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Dan Klein, Heng Wang, Jacob Steinhardt, Ruiqi Zhong","submitted_at":"2024-09-13T01:40:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08466","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.08466/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.08466","created_at":"2026-07-05T09:59:52.456656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08466v2","created_at":"2026-07-05T09:59:52.456656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08466","created_at":"2026-07-05T09:59:52.456656+00:00"},{"alias_kind":"pith_short_12","alias_value":"AH3GCSAE2GWX","created_at":"2026-07-05T09:59:52.456656+00:00"},{"alias_kind":"pith_short_16","alias_value":"AH3GCSAE2GWXG7QZ","created_at":"2026-07-05T09:59:52.456656+00:00"},{"alias_kind":"pith_short_8","alias_value":"AH3GCSAE","created_at":"2026-07-05T09:59:52.456656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AH3GCSAE2GWXG7QZB2HBKSQSVQ","json":"https://pith.science/pith/AH3GCSAE2GWXG7QZB2HBKSQSVQ.json","graph_json":"https://pith.science/api/pith-number/AH3GCSAE2GWXG7QZB2HBKSQSVQ/graph.json","events_json":"https://pith.science/api/pith-number/AH3GCSAE2GWXG7QZB2HBKSQSVQ/events.json","paper":"https://pith.science/paper/AH3GCSAE"},"agent_actions":{"view_html":"https://pith.science/pith/AH3GCSAE2GWXG7QZB2HBKSQSVQ","download_json":"https://pith.science/pith/AH3GCSAE2GWXG7QZB2HBKSQSVQ.json","view_paper":"https://pith.science/paper/AH3GCSAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08466&json=true","fetch_graph":"https://pith.science/api/pith-number/AH3GCSAE2GWXG7QZB2HBKSQSVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AH3GCSAE2GWXG7QZB2HBKSQSVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AH3GCSAE2GWXG7QZB2HBKSQSVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AH3GCSAE2GWXG7QZB2HBKSQSVQ/action/storage_attestation","attest_author":"https://pith.science/pith/AH3GCSAE2GWXG7QZB2HBKSQSVQ/action/author_attestation","sign_citation":"https://pith.science/pith/AH3GCSAE2GWXG7QZB2HBKSQSVQ/action/citation_signature","submit_replication":"https://pith.science/pith/AH3GCSAE2GWXG7QZB2HBKSQSVQ/action/replication_record"}},"created_at":"2026-07-05T09:59:52.456656+00:00","updated_at":"2026-07-05T09:59:52.456656+00:00"}