{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3MIL2FNSWXUAYKKEMWKQM5Y5ZK","short_pith_number":"pith:3MIL2FNS","schema_version":"1.0","canonical_sha256":"db10bd15b2b5e80c2944659506771dcaacb3d0bc29d5534c9ad0ea54ef3f5538","source":{"kind":"arxiv","id":"2410.23186","version":2},"attestation_state":"computed","paper":{"title":"Reliability of Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kayla Schroeder, Zach Wood-Doughty","submitted_at":"2024-10-30T16:42:04Z","abstract_excerpt":"Topic models allow researchers to extract latent factors from text data and use those variables in downstream statistical analyses. However, these methodologies can vary significantly due to initialization differences, randomness in sampling procedures, or noisy data. Reliability of these methods is of particular concern as many researchers treat learned topic models as ground truth for subsequent analyses. In this work, we show that the standard practice for quantifying topic model reliability fails to capture essential aspects of the variation in two widely-used topic models. Drawing from a "},"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":"2410.23186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T16:42:04Z","cross_cats_sorted":[],"title_canon_sha256":"f5be2b8e948761bf83248cb7d4bac845e6a640300527418178e8f62eab0b8dbf","abstract_canon_sha256":"ab8c3a9bff769ace06d52d39f1151f145612509cb466cd63e9d0e2af02aa4f50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:12.036608Z","signature_b64":"T2r+8nKqVybhDLtYAAzin/8odnVujzBz8WNQrl5DjmyilnrLqvOFu5jwhQSiTHt6urdaqq5wwPSWjWIiI+lKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db10bd15b2b5e80c2944659506771dcaacb3d0bc29d5534c9ad0ea54ef3f5538","last_reissued_at":"2026-07-05T09:49:12.036121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:12.036121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliability of Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kayla Schroeder, Zach Wood-Doughty","submitted_at":"2024-10-30T16:42:04Z","abstract_excerpt":"Topic models allow researchers to extract latent factors from text data and use those variables in downstream statistical analyses. However, these methodologies can vary significantly due to initialization differences, randomness in sampling procedures, or noisy data. Reliability of these methods is of particular concern as many researchers treat learned topic models as ground truth for subsequent analyses. In this work, we show that the standard practice for quantifying topic model reliability fails to capture essential aspects of the variation in two widely-used topic models. Drawing from a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23186","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/2410.23186/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":"2410.23186","created_at":"2026-07-05T09:49:12.036182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23186v2","created_at":"2026-07-05T09:49:12.036182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23186","created_at":"2026-07-05T09:49:12.036182+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MIL2FNSWXUA","created_at":"2026-07-05T09:49:12.036182+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MIL2FNSWXUAYKKE","created_at":"2026-07-05T09:49:12.036182+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MIL2FNS","created_at":"2026-07-05T09:49:12.036182+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12509","citing_title":"Can You Trust LLM Judgments? Reliability of LLM-as-a-Judge","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK","json":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK.json","graph_json":"https://pith.science/api/pith-number/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/graph.json","events_json":"https://pith.science/api/pith-number/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/events.json","paper":"https://pith.science/paper/3MIL2FNS"},"agent_actions":{"view_html":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK","download_json":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK.json","view_paper":"https://pith.science/paper/3MIL2FNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23186&json=true","fetch_graph":"https://pith.science/api/pith-number/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/graph.json","fetch_events":"https://pith.science/api/pith-number/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/action/storage_attestation","attest_author":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/action/author_attestation","sign_citation":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/action/citation_signature","submit_replication":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/action/replication_record"}},"created_at":"2026-07-05T09:49:12.036182+00:00","updated_at":"2026-07-05T09:49:12.036182+00:00"}