{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JX6QOOCGF6IXZCA5MDVAAR6GR3","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":"a0aedf2f164385d49894baf1fff0a6ab132ba0d7338c14147b50c20af627116d","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T00:50:23Z","title_canon_sha256":"80c5246b5a0ff04199e54466e40befb5f214e7dcbdf6b34a143a9ca7c159ba07"},"schema_version":"1.0","source":{"id":"2412.12433","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12433","created_at":"2026-07-05T09:50:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12433v1","created_at":"2026-07-05T09:50:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12433","created_at":"2026-07-05T09:50:14Z"},{"alias_kind":"pith_short_12","alias_value":"JX6QOOCGF6IX","created_at":"2026-07-05T09:50:14Z"},{"alias_kind":"pith_short_16","alias_value":"JX6QOOCGF6IXZCA5","created_at":"2026-07-05T09:50:14Z"},{"alias_kind":"pith_short_8","alias_value":"JX6QOOCG","created_at":"2026-07-05T09:50:14Z"}],"graph_snapshots":[{"event_id":"sha256:c63a6475a9a2855b74dd84a55cfa5eafe4ba9a70fc07214712bdf98a5dd67f2b","target":"graph","created_at":"2026-07-05T09:50:14Z","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/2412.12433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent works in clustering-based topic models perform well in monolingual topic identification by introducing a pipeline to cluster the contextualized representations. However, the pipeline is suboptimal in identifying topics across languages due to the presence of language-dependent dimensions (LDDs) generated by multilingual language models. To address this issue, we introduce a novel, SVD-based dimension refinement component into the pipeline of the clustering-based topic model. This component effectively neutralizes the negative impact of LDDs, enabling the model to accurately identify top","authors_text":"Chia-Hsuan Chang, Chia-Ming Chang, San-Yih Hwang, Tien-Yuan Huang, Yi-Hang Tsai","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T00:50:23Z","title":"Refining Dimensions for Improving Clustering-based Cross-lingual Topic Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12433","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":"sha256:5ee3ba686f2a47ff982a2cccf7518c2ca22e2d37f7b5e35f99539a9474514a0c","target":"record","created_at":"2026-07-05T09:50:14Z","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":"a0aedf2f164385d49894baf1fff0a6ab132ba0d7338c14147b50c20af627116d","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T00:50:23Z","title_canon_sha256":"80c5246b5a0ff04199e54466e40befb5f214e7dcbdf6b34a143a9ca7c159ba07"},"schema_version":"1.0","source":{"id":"2412.12433","kind":"arxiv","version":1}},"canonical_sha256":"4dfd0738462f917c881d60ea0047c68ed745248401e323e40aef2dbd56995985","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4dfd0738462f917c881d60ea0047c68ed745248401e323e40aef2dbd56995985","first_computed_at":"2026-07-05T09:50:14.774601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:14.774601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zzQSCVJK5BD259Nt23dhIDra15mws4dI1nJgGNLpmC5iHJ6vBXM9IuxyaY563ING/NK3WuszDnnV0WEmcWOxCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:14.775093Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12433","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ee3ba686f2a47ff982a2cccf7518c2ca22e2d37f7b5e35f99539a9474514a0c","sha256:c63a6475a9a2855b74dd84a55cfa5eafe4ba9a70fc07214712bdf98a5dd67f2b"],"state_sha256":"db93918126de0110bd1cd9ac16f497ec2faa49281d1857fa0256e01e7043b1d0"}