{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UJ6SRJAS4JYYX7BFNMJQH2RFDX","short_pith_number":"pith:UJ6SRJAS","canonical_record":{"source":{"id":"2311.02566","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-05T04:44:23Z","cross_cats_sorted":[],"title_canon_sha256":"7a3e141e0d78be2d05c5d728009f6a752401f08c828d68fa0ea8d0db5754db9c","abstract_canon_sha256":"a84554096b02ff39032b1186d361f2e2767cfdc538ab321a0fc0d90ba3657214"},"schema_version":"1.0"},"canonical_sha256":"a27d28a412e2718bfc256b1303ea251dca6d0bfea1b24edc96b47e419405eaf1","source":{"kind":"arxiv","id":"2311.02566","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UJ6SRJAS4JYYX7BFNMJQH2RFDX","target":"record","payload":{"canonical_record":{"source":{"id":"2311.02566","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-05T04:44:23Z","cross_cats_sorted":[],"title_canon_sha256":"7a3e141e0d78be2d05c5d728009f6a752401f08c828d68fa0ea8d0db5754db9c","abstract_canon_sha256":"a84554096b02ff39032b1186d361f2e2767cfdc538ab321a0fc0d90ba3657214"},"schema_version":"1.0"},"canonical_sha256":"a27d28a412e2718bfc256b1303ea251dca6d0bfea1b24edc96b47e419405eaf1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:14.880708Z","signature_b64":"88kM/Hacm/UAaumBxWr8hVLxnKiGn9RWzAXYveb+1eR7t8MfP7v90Yk8kaBhtSZd8pWHROI8XRKV4muqHQDbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a27d28a412e2718bfc256b1303ea251dca6d0bfea1b24edc96b47e419405eaf1","last_reissued_at":"2026-07-05T07:09:14.880225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:14.880225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.02566","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:09:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dSaQnCaEmrSIAUlqTo06pINSCw45QWLsdh9xVMdy2FDG0AuWWl7z8XkzRdh0Q03qmYucL5mhI3HSMKqUxI1rCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:18:55.029192Z"},"content_sha256":"f08d8475ab44cc9bf857466b5c390a00de487525e6a9c0a9e4fd15d987167f06","schema_version":"1.0","event_id":"sha256:f08d8475ab44cc9bf857466b5c390a00de487525e6a9c0a9e4fd15d987167f06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UJ6SRJAS4JYYX7BFNMJQH2RFDX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topic model based on co-occurrence word networks for unbalanced short text datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengjie Ma, Junping Du, Meiyu Liang, Zeli Guan","submitted_at":"2023-11-05T04:44:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02566","kind":"arxiv","version":1},"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/2311.02566/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":"2026-07-05T07:09:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mrxNCzK8i1/ycUg2ZtbUygaM8D8soyxUEH0CTJGHm2ILvPXXyX6ENjQ23LtJ9NBeiOfH6n0HCWxC5jyhw/U0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:18:55.030223Z"},"content_sha256":"a10597cf82a3f173f53d4af29f7eb032e79934a6c7031e8d359babdd553b5622","schema_version":"1.0","event_id":"sha256:a10597cf82a3f173f53d4af29f7eb032e79934a6c7031e8d359babdd553b5622"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UJ6SRJAS4JYYX7BFNMJQH2RFDX/bundle.json","state_url":"https://pith.science/pith/UJ6SRJAS4JYYX7BFNMJQH2RFDX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UJ6SRJAS4JYYX7BFNMJQH2RFDX/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":"2026-08-14T17:18:55Z","links":{"resolver":"https://pith.science/pith/UJ6SRJAS4JYYX7BFNMJQH2RFDX","bundle":"https://pith.science/pith/UJ6SRJAS4JYYX7BFNMJQH2RFDX/bundle.json","state":"https://pith.science/pith/UJ6SRJAS4JYYX7BFNMJQH2RFDX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UJ6SRJAS4JYYX7BFNMJQH2RFDX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5D5S2MbZdmU/4bzyTDAl5fx5iQyufyfm/8gVQlnpWWFOMZS2juUfMZqHQx7ZkuaXeeEfU+sqiHWrNnNxachDAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T17:18:55.047922Z","bundle_sha256":"d6597cb4e4f1e9215f5e9c93a4f1bd647ea3eae486d6bdbaf337894df2597829"}}