{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WJSWF46AN53OK4OMDJSIIWKDAV","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":"d91a40858d62184076c06a5d666b3b16ccf0781b8680ca8074787e6df033c223","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-24T11:14:13Z","title_canon_sha256":"df848c11879be299a8b1c814e0840d78e7e860ea0ea88d7169b9c7da9b012161"},"schema_version":"1.0","source":{"id":"2504.17445","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17445","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17445v1","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17445","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"WJSWF46AN53O","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"WJSWF46AN53OK4OM","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"WJSWF46A","created_at":"2026-07-05T10:53:28Z"}],"graph_snapshots":[{"event_id":"sha256:4106a87cedd1e025bdb9a8b9eb031994d565e442f6e543b527ef5428e731dfeb","target":"graph","created_at":"2026-07-05T10:53:28Z","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/2504.17445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised machine learning techniques, such as topic modeling and clustering, are often used to identify latent patterns in unstructured text data in fields such as political science and sociology. These methods overcome common concerns about reproducibility and costliness involved in the labor-intensive process of human qualitative analysis. However, two major limitations of topic models are their interpretability and their practicality for answering targeted, domain-specific social science research questions. In this work, we investigate opportunities for using LLM-generated text augmenta","authors_text":"Anna Lieb, Eni Mustafaraj, Maneesh Arora","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-24T11:14:13Z","title":"Creating Targeted, Interpretable Topic Models with LLM-Generated Text Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17445","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:d4c94fcd45df2b3daee51a463e14caa38830c577aed237e52ee777788caeef75","target":"record","created_at":"2026-07-05T10:53:28Z","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":"d91a40858d62184076c06a5d666b3b16ccf0781b8680ca8074787e6df033c223","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-24T11:14:13Z","title_canon_sha256":"df848c11879be299a8b1c814e0840d78e7e860ea0ea88d7169b9c7da9b012161"},"schema_version":"1.0","source":{"id":"2504.17445","kind":"arxiv","version":1}},"canonical_sha256":"b26562f3c06f76e571cc1a6484594305702772678fee2fc5bc580d1b5a3d2ef2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b26562f3c06f76e571cc1a6484594305702772678fee2fc5bc580d1b5a3d2ef2","first_computed_at":"2026-07-05T10:53:28.853383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:28.853383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oRdKP6dPOuBqk6ST475T6V11ufMMWpmC0Sxah62+tQ+ung3gld39G5vWNDGSAo4JBFRKZKqNc1jNzaWHEMjpDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:28.853945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.17445","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4c94fcd45df2b3daee51a463e14caa38830c577aed237e52ee777788caeef75","sha256:4106a87cedd1e025bdb9a8b9eb031994d565e442f6e543b527ef5428e731dfeb"],"state_sha256":"69c4a6624925aa9a372505905c7250f154718c523df51beb8d45afadf254682a"}