{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:U5C2QETCWSMU4YRHLNI7S4SX2D","short_pith_number":"pith:U5C2QETC","schema_version":"1.0","canonical_sha256":"a745a81262b4994e62275b51f97257d0de4e206aeeaead9cb00181cdb07c7920","source":{"kind":"arxiv","id":"1809.03664","version":1},"attestation_state":"computed","paper":{"title":"Topic Memory Networks for Short Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cuiyun Gao, Irwin King, Jichuan Zeng, Jing Li, Michael R. Lyu, Yan Song","submitted_at":"2018-09-11T03:03:37Z","abstract_excerpt":"Many classification models work poorly on short texts due to data sparsity. To address this issue, we propose topic memory networks for short text classification with a novel topic memory mechanism to encode latent topic representations indicative of class labels. Different from most prior work that focuses on extending features with external knowledge or pre-trained topics, our model jointly explores topic inference and text classification with memory networks in an end-to-end manner. Experimental results on four benchmark datasets show that our model outperforms state-of-the-art models on sh"},"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":"1809.03664","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-11T03:03:37Z","cross_cats_sorted":[],"title_canon_sha256":"f94ba7c5470069cacf8bf3417603652073671c009f8736b70c7b2feceda73775","abstract_canon_sha256":"e88267c32d184244310fb7a4f68076f589b2b3b6bf0b1143b4b0e1105d530da1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:00.159595Z","signature_b64":"BtI2nLuBpmaDSOZzzBVvfeuD89NgyOR6b2Lw4IfqhUqYo3Ittj8u8GBUs09JbMyWY5s1f/9hFrJGlBhX0731CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a745a81262b4994e62275b51f97257d0de4e206aeeaead9cb00181cdb07c7920","last_reissued_at":"2026-05-18T00:06:00.158996Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:00.158996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topic Memory Networks for Short Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cuiyun Gao, Irwin King, Jichuan Zeng, Jing Li, Michael R. Lyu, Yan Song","submitted_at":"2018-09-11T03:03:37Z","abstract_excerpt":"Many classification models work poorly on short texts due to data sparsity. To address this issue, we propose topic memory networks for short text classification with a novel topic memory mechanism to encode latent topic representations indicative of class labels. Different from most prior work that focuses on extending features with external knowledge or pre-trained topics, our model jointly explores topic inference and text classification with memory networks in an end-to-end manner. Experimental results on four benchmark datasets show that our model outperforms state-of-the-art models on sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03664","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":""},"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":"1809.03664","created_at":"2026-05-18T00:06:00.159080+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.03664v1","created_at":"2026-05-18T00:06:00.159080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03664","created_at":"2026-05-18T00:06:00.159080+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5C2QETCWSMU","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5C2QETCWSMU4YRH","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5C2QETC","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2109.10616","citing_title":"Enriching and Controlling Global Semantics for Text Summarization","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5C2QETCWSMU4YRHLNI7S4SX2D","json":"https://pith.science/pith/U5C2QETCWSMU4YRHLNI7S4SX2D.json","graph_json":"https://pith.science/api/pith-number/U5C2QETCWSMU4YRHLNI7S4SX2D/graph.json","events_json":"https://pith.science/api/pith-number/U5C2QETCWSMU4YRHLNI7S4SX2D/events.json","paper":"https://pith.science/paper/U5C2QETC"},"agent_actions":{"view_html":"https://pith.science/pith/U5C2QETCWSMU4YRHLNI7S4SX2D","download_json":"https://pith.science/pith/U5C2QETCWSMU4YRHLNI7S4SX2D.json","view_paper":"https://pith.science/paper/U5C2QETC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.03664&json=true","fetch_graph":"https://pith.science/api/pith-number/U5C2QETCWSMU4YRHLNI7S4SX2D/graph.json","fetch_events":"https://pith.science/api/pith-number/U5C2QETCWSMU4YRHLNI7S4SX2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5C2QETCWSMU4YRHLNI7S4SX2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5C2QETCWSMU4YRHLNI7S4SX2D/action/storage_attestation","attest_author":"https://pith.science/pith/U5C2QETCWSMU4YRHLNI7S4SX2D/action/author_attestation","sign_citation":"https://pith.science/pith/U5C2QETCWSMU4YRHLNI7S4SX2D/action/citation_signature","submit_replication":"https://pith.science/pith/U5C2QETCWSMU4YRHLNI7S4SX2D/action/replication_record"}},"created_at":"2026-05-18T00:06:00.159080+00:00","updated_at":"2026-05-18T00:06:00.159080+00:00"}