{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UJ6SRJAS4JYYX7BFNMJQH2RFDX","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":"a84554096b02ff39032b1186d361f2e2767cfdc538ab321a0fc0d90ba3657214","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-05T04:44:23Z","title_canon_sha256":"7a3e141e0d78be2d05c5d728009f6a752401f08c828d68fa0ea8d0db5754db9c"},"schema_version":"1.0","source":{"id":"2311.02566","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02566","created_at":"2026-07-05T07:09:14Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02566v1","created_at":"2026-07-05T07:09:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02566","created_at":"2026-07-05T07:09:14Z"},{"alias_kind":"pith_short_12","alias_value":"UJ6SRJAS4JYY","created_at":"2026-07-05T07:09:14Z"},{"alias_kind":"pith_short_16","alias_value":"UJ6SRJAS4JYYX7BF","created_at":"2026-07-05T07:09:14Z"},{"alias_kind":"pith_short_8","alias_value":"UJ6SRJAS","created_at":"2026-07-05T07:09:14Z"}],"graph_snapshots":[{"event_id":"sha256:a10597cf82a3f173f53d4af29f7eb032e79934a6c7031e8d359babdd553b5622","target":"graph","created_at":"2026-07-05T07:09:14Z","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/2311.02566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a straightforward solution for detecting scarce topics in unbalanced short-text datasets. Our approach, named CWUTM (Topic model based on co-occurrence word networks for unbalanced short text datasets), Our approach addresses the challenge of sparse and unbalanced short text topics by mitigating the effects of incidental word co-occurrence. This allows our model to prioritize the identification of scarce topics (Low-frequency topics). Unlike previous methods, CWUTM leverages co-occurrence word networks to capture the topic distribution of each word, and we enhanced the sensitivity i","authors_text":"Chengjie Ma, Junping Du, Meiyu Liang, Zeli Guan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-05T04:44:23Z","title":"Topic model based on co-occurrence word networks for unbalanced short text datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02566","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:f08d8475ab44cc9bf857466b5c390a00de487525e6a9c0a9e4fd15d987167f06","target":"record","created_at":"2026-07-05T07:09:14Z","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":"a84554096b02ff39032b1186d361f2e2767cfdc538ab321a0fc0d90ba3657214","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-05T04:44:23Z","title_canon_sha256":"7a3e141e0d78be2d05c5d728009f6a752401f08c828d68fa0ea8d0db5754db9c"},"schema_version":"1.0","source":{"id":"2311.02566","kind":"arxiv","version":1}},"canonical_sha256":"a27d28a412e2718bfc256b1303ea251dca6d0bfea1b24edc96b47e419405eaf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a27d28a412e2718bfc256b1303ea251dca6d0bfea1b24edc96b47e419405eaf1","first_computed_at":"2026-07-05T07:09:14.880225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:14.880225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"88kM/Hacm/UAaumBxWr8hVLxnKiGn9RWzAXYveb+1eR7t8MfP7v90Yk8kaBhtSZd8pWHROI8XRKV4muqHQDbBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:14.880708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.02566","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f08d8475ab44cc9bf857466b5c390a00de487525e6a9c0a9e4fd15d987167f06","sha256:a10597cf82a3f173f53d4af29f7eb032e79934a6c7031e8d359babdd553b5622"],"state_sha256":"f21e7834e3f4e5c5ce0297a1fbe63a8dd2dca74fec602f43d4fbcf91ddffbccd"}