{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4JIXRPUIHRUGMIVX3GTZMAI7XT","short_pith_number":"pith:4JIXRPUI","schema_version":"1.0","canonical_sha256":"e25178be883c686622b7d9a796011fbcdee730fa12e045dab13b204a640cbf42","source":{"kind":"arxiv","id":"2211.12878","version":1},"attestation_state":"computed","paper":{"title":"Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Tuan Luu, Xiaobao Wu, Xinshuai Dong","submitted_at":"2022-11-23T11:33:43Z","abstract_excerpt":"To overcome the data sparsity issue in short text topic modeling, existing methods commonly rely on data augmentation or the data characteristic of short texts to introduce more word co-occurrence information. However, most of them do not make full use of the augmented data or the data characteristic: they insufficiently learn the relations among samples in data, leading to dissimilar topic distributions of semantically similar text pairs. To better address data sparsity, in this paper we propose a novel short text topic modeling framework, Topic-Semantic Contrastive Topic Model (TSCTM). To su"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2211.12878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-23T11:33:43Z","cross_cats_sorted":[],"title_canon_sha256":"e9e81b160cc566dd624e376bcf9f9733ae560819664a16333e9d2d31a81d7c8c","abstract_canon_sha256":"b492f26e79076ca02a2a19a29297434c985923e0d185e5fcfde4f1654eb3e639"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:55.943718Z","signature_b64":"XfzmKumBcMZUHfKH1BBYUEMJbnwX0r0kvJouZt3Q2/zZV5zHQz0j8WOsJXbyIhEJiKbv2IwzWeGDBMHZfXbYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e25178be883c686622b7d9a796011fbcdee730fa12e045dab13b204a640cbf42","last_reissued_at":"2026-07-05T05:18:55.943330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:55.943330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Tuan Luu, Xiaobao Wu, Xinshuai Dong","submitted_at":"2022-11-23T11:33:43Z","abstract_excerpt":"To overcome the data sparsity issue in short text topic modeling, existing methods commonly rely on data augmentation or the data characteristic of short texts to introduce more word co-occurrence information. However, most of them do not make full use of the augmented data or the data characteristic: they insufficiently learn the relations among samples in data, leading to dissimilar topic distributions of semantically similar text pairs. To better address data sparsity, in this paper we propose a novel short text topic modeling framework, Topic-Semantic Contrastive Topic Model (TSCTM). To su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12878","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/2211.12878/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.12878","created_at":"2026-07-05T05:18:55.943388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12878v1","created_at":"2026-07-05T05:18:55.943388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12878","created_at":"2026-07-05T05:18:55.943388+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JIXRPUIHRUG","created_at":"2026-07-05T05:18:55.943388+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JIXRPUIHRUGMIVX","created_at":"2026-07-05T05:18:55.943388+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JIXRPUI","created_at":"2026-07-05T05:18:55.943388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17338","citing_title":"Enhancing Topic Interpretability for Neural Topic Modeling through Topic-wise Contrastive Learning","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT","json":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT.json","graph_json":"https://pith.science/api/pith-number/4JIXRPUIHRUGMIVX3GTZMAI7XT/graph.json","events_json":"https://pith.science/api/pith-number/4JIXRPUIHRUGMIVX3GTZMAI7XT/events.json","paper":"https://pith.science/paper/4JIXRPUI"},"agent_actions":{"view_html":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT","download_json":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT.json","view_paper":"https://pith.science/paper/4JIXRPUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12878&json=true","fetch_graph":"https://pith.science/api/pith-number/4JIXRPUIHRUGMIVX3GTZMAI7XT/graph.json","fetch_events":"https://pith.science/api/pith-number/4JIXRPUIHRUGMIVX3GTZMAI7XT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT/action/storage_attestation","attest_author":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT/action/author_attestation","sign_citation":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT/action/citation_signature","submit_replication":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT/action/replication_record"}},"created_at":"2026-07-05T05:18:55.943388+00:00","updated_at":"2026-07-05T05:18:55.943388+00:00"}