{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:N2BYTL3CD3SWV3CU2ASNFGXMQ2","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":"b5b0b5748c89ae7f3bba9d8d8a47eea2acd86b520f19ab4f68113ac3b5cd78ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T19:16:59Z","title_canon_sha256":"a5ba4cf2595dd9304ed0a3eaac7d431cb8c9576b0b3c59d69b6ec8953a73aff4"},"schema_version":"1.0","source":{"id":"2010.12626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12626","created_at":"2026-07-05T01:45:46Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12626v1","created_at":"2026-07-05T01:45:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12626","created_at":"2026-07-05T01:45:46Z"},{"alias_kind":"pith_short_12","alias_value":"N2BYTL3CD3SW","created_at":"2026-07-05T01:45:46Z"},{"alias_kind":"pith_short_16","alias_value":"N2BYTL3CD3SWV3CU","created_at":"2026-07-05T01:45:46Z"},{"alias_kind":"pith_short_8","alias_value":"N2BYTL3C","created_at":"2026-07-05T01:45:46Z"}],"graph_snapshots":[{"event_id":"sha256:9bfcc7771c69ea53c93eb28f5a91d87fb4e86f0bb0d0e1b6459b854a3fb3f5ea","target":"graph","created_at":"2026-07-05T01:45:46Z","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/2010.12626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clustering token-level contextualized word representations produces output that shares many similarities with topic models for English text collections. Unlike clusterings of vocabulary-level word embeddings, the resulting models more naturally capture polysemy and can be used as a way of organizing documents. We evaluate token clusterings trained from several different output layers of popular contextualized language models. We find that BERT and GPT-2 produce high quality clusterings, but RoBERTa does not. These cluster models are simple, reliable, and can perform as well as, if not better t","authors_text":"David Mimno, Laure Thompson","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T19:16:59Z","title":"Topic Modeling with Contextualized Word Representation Clusters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12626","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:c1e9c36e7d12570633c6203bd7b63582b3385fffd078fa78bef452859351137d","target":"record","created_at":"2026-07-05T01:45:46Z","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":"b5b0b5748c89ae7f3bba9d8d8a47eea2acd86b520f19ab4f68113ac3b5cd78ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T19:16:59Z","title_canon_sha256":"a5ba4cf2595dd9304ed0a3eaac7d431cb8c9576b0b3c59d69b6ec8953a73aff4"},"schema_version":"1.0","source":{"id":"2010.12626","kind":"arxiv","version":1}},"canonical_sha256":"6e8389af621ee56aec54d024d29aec86b4745a485a9324d648ebcbb5a0c41643","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e8389af621ee56aec54d024d29aec86b4745a485a9324d648ebcbb5a0c41643","first_computed_at":"2026-07-05T01:45:46.578117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:46.578117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7cPP7Ke0v6EZ8RjGbZlqdhwRx64Hh0e04JOqgm9qrA1nSku2UibcS9/uEgr3c/iN/azBH9SNg0G/c9d0XYbVCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:46.578521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1e9c36e7d12570633c6203bd7b63582b3385fffd078fa78bef452859351137d","sha256:9bfcc7771c69ea53c93eb28f5a91d87fb4e86f0bb0d0e1b6459b854a3fb3f5ea"],"state_sha256":"598d98ddbe2ada32cd2527f24e6d9fa1b89e33429cf185f020cae73225352c2c"}