{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:M3WGTPSRRSR6N7AJTZ2BORLKLJ","short_pith_number":"pith:M3WGTPSR","schema_version":"1.0","canonical_sha256":"66ec69be518ca3e6fc099e7417456a5a58c4a9b688cced7d25f9ecf4d90ecb01","source":{"kind":"arxiv","id":"1602.06797","version":2},"attestation_state":"computed","paper":{"title":"Semi-supervised Clustering for Short Text via Deep Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abraham Ittycheriah, Haitao Mi, Zhiguo Wang","submitted_at":"2016-02-22T14:55:26Z","abstract_excerpt":"In this work, we propose a semi-supervised method for short text clustering, where we represent texts as distributed vectors with neural networks, and use a small amount of labeled data to specify our intention for clustering. We design a novel objective to combine the representation learning process and the k-means clustering process together, and optimize the objective with both labeled data and unlabeled data iteratively until convergence through three steps: (1) assign each short text to its nearest centroid based on its representation from the current neural networks; (2) re-estimate the "},"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":"1602.06797","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-02-22T14:55:26Z","cross_cats_sorted":[],"title_canon_sha256":"05c54a85e406ea2e7dc9e77e801b66f71fb90a57113e328554ccb1f5cbfa1bb4","abstract_canon_sha256":"6a12e0a3fccbc9a4054da570e21b02230ab585ab57783cbd5961e1a64fe9b301"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:17.572807Z","signature_b64":"LNQL1PqHyi6u72yEcD0lEMFp+ZYar7ZoxFaPX8HYtt2bkB5BEubRo/9zXw6TSubD9fcuB+/CkEje4JTqAZ7CCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66ec69be518ca3e6fc099e7417456a5a58c4a9b688cced7d25f9ecf4d90ecb01","last_reissued_at":"2026-05-18T00:40:17.572190Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:17.572190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised Clustering for Short Text via Deep Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abraham Ittycheriah, Haitao Mi, Zhiguo Wang","submitted_at":"2016-02-22T14:55:26Z","abstract_excerpt":"In this work, we propose a semi-supervised method for short text clustering, where we represent texts as distributed vectors with neural networks, and use a small amount of labeled data to specify our intention for clustering. We design a novel objective to combine the representation learning process and the k-means clustering process together, and optimize the objective with both labeled data and unlabeled data iteratively until convergence through three steps: (1) assign each short text to its nearest centroid based on its representation from the current neural networks; (2) re-estimate the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.06797","kind":"arxiv","version":2},"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":"1602.06797","created_at":"2026-05-18T00:40:17.572286+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.06797v2","created_at":"2026-05-18T00:40:17.572286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.06797","created_at":"2026-05-18T00:40:17.572286+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3WGTPSRRSR6","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3WGTPSRRSR6N7AJ","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3WGTPSR","created_at":"2026-05-18T12:30:29.479603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3WGTPSRRSR6N7AJTZ2BORLKLJ","json":"https://pith.science/pith/M3WGTPSRRSR6N7AJTZ2BORLKLJ.json","graph_json":"https://pith.science/api/pith-number/M3WGTPSRRSR6N7AJTZ2BORLKLJ/graph.json","events_json":"https://pith.science/api/pith-number/M3WGTPSRRSR6N7AJTZ2BORLKLJ/events.json","paper":"https://pith.science/paper/M3WGTPSR"},"agent_actions":{"view_html":"https://pith.science/pith/M3WGTPSRRSR6N7AJTZ2BORLKLJ","download_json":"https://pith.science/pith/M3WGTPSRRSR6N7AJTZ2BORLKLJ.json","view_paper":"https://pith.science/paper/M3WGTPSR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.06797&json=true","fetch_graph":"https://pith.science/api/pith-number/M3WGTPSRRSR6N7AJTZ2BORLKLJ/graph.json","fetch_events":"https://pith.science/api/pith-number/M3WGTPSRRSR6N7AJTZ2BORLKLJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3WGTPSRRSR6N7AJTZ2BORLKLJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3WGTPSRRSR6N7AJTZ2BORLKLJ/action/storage_attestation","attest_author":"https://pith.science/pith/M3WGTPSRRSR6N7AJTZ2BORLKLJ/action/author_attestation","sign_citation":"https://pith.science/pith/M3WGTPSRRSR6N7AJTZ2BORLKLJ/action/citation_signature","submit_replication":"https://pith.science/pith/M3WGTPSRRSR6N7AJTZ2BORLKLJ/action/replication_record"}},"created_at":"2026-05-18T00:40:17.572286+00:00","updated_at":"2026-05-18T00:40:17.572286+00:00"}