{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:NUPTW5GMTKERSSRE6G3CLI5PQ4","short_pith_number":"pith:NUPTW5GM","canonical_record":{"source":{"id":"2004.14914","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T16:18:18Z","cross_cats_sorted":[],"title_canon_sha256":"dec80dd73ec8b2d6ffb7fe751c8025d35eb8ea93a428206405d060643110c6bf","abstract_canon_sha256":"aec9d24152a5f81a09d518c3a008a2115c7d1385e39c5f310a638dd2f1fb7220"},"schema_version":"1.0"},"canonical_sha256":"6d1f3b74cc9a89194a24f1b625a3af87320bb56c1b15eca3d902e2b3ac63289a","source":{"kind":"arxiv","id":"2004.14914","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14914","created_at":"2026-07-05T01:40:56Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14914v2","created_at":"2026-07-05T01:40:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14914","created_at":"2026-07-05T01:40:56Z"},{"alias_kind":"pith_short_12","alias_value":"NUPTW5GMTKER","created_at":"2026-07-05T01:40:56Z"},{"alias_kind":"pith_short_16","alias_value":"NUPTW5GMTKERSSRE","created_at":"2026-07-05T01:40:56Z"},{"alias_kind":"pith_short_8","alias_value":"NUPTW5GM","created_at":"2026-07-05T01:40:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:NUPTW5GMTKERSSRE6G3CLI5PQ4","target":"record","payload":{"canonical_record":{"source":{"id":"2004.14914","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T16:18:18Z","cross_cats_sorted":[],"title_canon_sha256":"dec80dd73ec8b2d6ffb7fe751c8025d35eb8ea93a428206405d060643110c6bf","abstract_canon_sha256":"aec9d24152a5f81a09d518c3a008a2115c7d1385e39c5f310a638dd2f1fb7220"},"schema_version":"1.0"},"canonical_sha256":"6d1f3b74cc9a89194a24f1b625a3af87320bb56c1b15eca3d902e2b3ac63289a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:56.673135Z","signature_b64":"P4Elms14gyFQTeTxcWrf7AxvhL0cRZn2ToyUW0iiqv6f/zsd9AmpusOFcDc7QObW08Uq/mFKNZsAAZKKVHg1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d1f3b74cc9a89194a24f1b625a3af87320bb56c1b15eca3d902e2b3ac63289a","last_reissued_at":"2026-07-05T01:40:56.672726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:56.672726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.14914","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:40:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qIl6K1cVs25rm1yCcOoXYaJryzXV3JmQzxduzXRRKyVs7laLmFJknx5Ag5wZer5eFVYvHLqcBJLqHXI1u//EBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:54:54.090191Z"},"content_sha256":"35ea324149bb3b61c584852185e026a0ab0561786b9558cfc4f1fb1e2ca26517","schema_version":"1.0","event_id":"sha256:35ea324149bb3b61c584852185e026a0ab0561786b9558cfc4f1fb1e2ca26517"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:NUPTW5GMTKERSSRE6G3CLI5PQ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ayush Dalmia, Sabrina J. Mielke, Suzanna Sia","submitted_at":"2020-04-30T16:18:18Z","abstract_excerpt":"Topic models are a useful analysis tool to uncover the underlying themes within document collections. The dominant approach is to use probabilistic topic models that posit a generative story, but in this paper we propose an alternative way to obtain topics: clustering pre-trained word embeddings while incorporating document information for weighted clustering and reranking top words. We provide benchmarks for the combination of different word embeddings and clustering algorithms, and analyse their performance under dimensionality reduction with PCA. The best performing combination for our appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14914","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/2004.14914/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:40:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M+JcRGjMIDXUUuO/rzGV+VghSgJ/lSE7KyM94hVle7v1doI4dK1CjsXlqrYqR3RrUjjDlp8ve8TZGKiPErv0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:54:54.090800Z"},"content_sha256":"c34313bc32ac87ff4ec7b4c44cd019be06a4dae6737ba1b87a8e00db35d57af8","schema_version":"1.0","event_id":"sha256:c34313bc32ac87ff4ec7b4c44cd019be06a4dae6737ba1b87a8e00db35d57af8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NUPTW5GMTKERSSRE6G3CLI5PQ4/bundle.json","state_url":"https://pith.science/pith/NUPTW5GMTKERSSRE6G3CLI5PQ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NUPTW5GMTKERSSRE6G3CLI5PQ4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T12:54:54Z","links":{"resolver":"https://pith.science/pith/NUPTW5GMTKERSSRE6G3CLI5PQ4","bundle":"https://pith.science/pith/NUPTW5GMTKERSSRE6G3CLI5PQ4/bundle.json","state":"https://pith.science/pith/NUPTW5GMTKERSSRE6G3CLI5PQ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NUPTW5GMTKERSSRE6G3CLI5PQ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NUPTW5GMTKERSSRE6G3CLI5PQ4","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":"aec9d24152a5f81a09d518c3a008a2115c7d1385e39c5f310a638dd2f1fb7220","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T16:18:18Z","title_canon_sha256":"dec80dd73ec8b2d6ffb7fe751c8025d35eb8ea93a428206405d060643110c6bf"},"schema_version":"1.0","source":{"id":"2004.14914","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14914","created_at":"2026-07-05T01:40:56Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14914v2","created_at":"2026-07-05T01:40:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14914","created_at":"2026-07-05T01:40:56Z"},{"alias_kind":"pith_short_12","alias_value":"NUPTW5GMTKER","created_at":"2026-07-05T01:40:56Z"},{"alias_kind":"pith_short_16","alias_value":"NUPTW5GMTKERSSRE","created_at":"2026-07-05T01:40:56Z"},{"alias_kind":"pith_short_8","alias_value":"NUPTW5GM","created_at":"2026-07-05T01:40:56Z"}],"graph_snapshots":[{"event_id":"sha256:c34313bc32ac87ff4ec7b4c44cd019be06a4dae6737ba1b87a8e00db35d57af8","target":"graph","created_at":"2026-07-05T01:40:56Z","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/2004.14914/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Topic models are a useful analysis tool to uncover the underlying themes within document collections. The dominant approach is to use probabilistic topic models that posit a generative story, but in this paper we propose an alternative way to obtain topics: clustering pre-trained word embeddings while incorporating document information for weighted clustering and reranking top words. We provide benchmarks for the combination of different word embeddings and clustering algorithms, and analyse their performance under dimensionality reduction with PCA. The best performing combination for our appr","authors_text":"Ayush Dalmia, Sabrina J. Mielke, Suzanna Sia","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T16:18:18Z","title":"Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14914","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":"sha256:35ea324149bb3b61c584852185e026a0ab0561786b9558cfc4f1fb1e2ca26517","target":"record","created_at":"2026-07-05T01:40:56Z","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":"aec9d24152a5f81a09d518c3a008a2115c7d1385e39c5f310a638dd2f1fb7220","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T16:18:18Z","title_canon_sha256":"dec80dd73ec8b2d6ffb7fe751c8025d35eb8ea93a428206405d060643110c6bf"},"schema_version":"1.0","source":{"id":"2004.14914","kind":"arxiv","version":2}},"canonical_sha256":"6d1f3b74cc9a89194a24f1b625a3af87320bb56c1b15eca3d902e2b3ac63289a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d1f3b74cc9a89194a24f1b625a3af87320bb56c1b15eca3d902e2b3ac63289a","first_computed_at":"2026-07-05T01:40:56.672726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:40:56.672726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P4Elms14gyFQTeTxcWrf7AxvhL0cRZn2ToyUW0iiqv6f/zsd9AmpusOFcDc7QObW08Uq/mFKNZsAAZKKVHg1DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:40:56.673135Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14914","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35ea324149bb3b61c584852185e026a0ab0561786b9558cfc4f1fb1e2ca26517","sha256:c34313bc32ac87ff4ec7b4c44cd019be06a4dae6737ba1b87a8e00db35d57af8"],"state_sha256":"4e10ed64b37f9b94ba7b5289785dd4d8f254b2a80514bb9e92bfae432dc31115"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"om5qwH4m8M0w2tVqQt0txfJYdyUwFdTVgkdtXp8oq2iGpTJzgghEH1w5/ZKjYbh/mlXWb0JIIXgb0t+X6dOYBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T12:54:54.095605Z","bundle_sha256":"b16757a5ca1367ef408b434d72b164d93691fdbe6c53d21e16d4e14eda7ba594"}}