{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AZABBCY4BM3K7RSUXTYE34G6PV","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":"5b1511dbdc34c4b0086ba36ad1a44405b1e35b7af298556ef7d20cffe9f9ba5d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T07:42:48Z","title_canon_sha256":"a423546942d3364fe136e60761da9d9c45aace867c25ce27a37ec47abbaab0ba"},"schema_version":"1.0","source":{"id":"2407.14085","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.14085","created_at":"2026-07-05T08:45:58Z"},{"alias_kind":"arxiv_version","alias_value":"2407.14085v1","created_at":"2026-07-05T08:45:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14085","created_at":"2026-07-05T08:45:58Z"},{"alias_kind":"pith_short_12","alias_value":"AZABBCY4BM3K","created_at":"2026-07-05T08:45:58Z"},{"alias_kind":"pith_short_16","alias_value":"AZABBCY4BM3K7RSU","created_at":"2026-07-05T08:45:58Z"},{"alias_kind":"pith_short_8","alias_value":"AZABBCY4","created_at":"2026-07-05T08:45:58Z"}],"graph_snapshots":[{"event_id":"sha256:182c194e698916caea48eacd62ae2fb47b369e1a8c05e28cfe041acd6640a768","target":"graph","created_at":"2026-07-05T08:45:58Z","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/2407.14085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The task of $\\textit{keyword extraction}$ is often an important initial step in unsupervised information extraction, forming the basis for tasks such as topic modeling or document classification. While recent methods have proven to be quite effective in the extraction of keywords, the identification of $\\textit{class-specific}$ keywords, or only those pertaining to a predefined class, remains challenging. In this work, we propose an improved method for class-specific keyword extraction, which builds upon the popular $\\textbf{KeyBERT}$ library to identify only keywords related to a class descri","authors_text":"Florian Matthes, Patrick Holl, Stephen Meisenbacher, Tim Schopf, Weixin Yan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T07:42:48Z","title":"An Improved Method for Class-specific Keyword Extraction: A Case Study in the German Business Registry"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14085","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":"sha256:5050b61fa3cc3ac2d3284c20945ccabad0f8c73ad5caa191ee63433d06ceb579","target":"record","created_at":"2026-07-05T08:45:58Z","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":"5b1511dbdc34c4b0086ba36ad1a44405b1e35b7af298556ef7d20cffe9f9ba5d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T07:42:48Z","title_canon_sha256":"a423546942d3364fe136e60761da9d9c45aace867c25ce27a37ec47abbaab0ba"},"schema_version":"1.0","source":{"id":"2407.14085","kind":"arxiv","version":1}},"canonical_sha256":"0640108b1c0b36afc654bcf04df0de7d51f35d902ca4a2a49c43991f9b005212","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0640108b1c0b36afc654bcf04df0de7d51f35d902ca4a2a49c43991f9b005212","first_computed_at":"2026-07-05T08:45:58.173467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:58.173467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4V8myoASL3x+DcFscpUVxJ2bg6+kp1KdziLkqPI/zLJBrvJzMaftQCOuiUc56luwf0CqjhTvu0Ds/Adg6m17DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:58.174008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.14085","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5050b61fa3cc3ac2d3284c20945ccabad0f8c73ad5caa191ee63433d06ceb579","sha256:182c194e698916caea48eacd62ae2fb47b369e1a8c05e28cfe041acd6640a768"],"state_sha256":"b732995c5f3f88480f25ea215432df63a272200455310ffcef4fda43feb3b499"}