{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:M3WGTPSRRSR6N7AJTZ2BORLKLJ","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":"6a12e0a3fccbc9a4054da570e21b02230ab585ab57783cbd5961e1a64fe9b301","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-02-22T14:55:26Z","title_canon_sha256":"05c54a85e406ea2e7dc9e77e801b66f71fb90a57113e328554ccb1f5cbfa1bb4"},"schema_version":"1.0","source":{"id":"1602.06797","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.06797","created_at":"2026-05-18T00:40:17Z"},{"alias_kind":"arxiv_version","alias_value":"1602.06797v2","created_at":"2026-05-18T00:40:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.06797","created_at":"2026-05-18T00:40:17Z"},{"alias_kind":"pith_short_12","alias_value":"M3WGTPSRRSR6","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"M3WGTPSRRSR6N7AJ","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"M3WGTPSR","created_at":"2026-05-18T12:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:0cb724d5091cb2f788c263c2a1e1505a7814ad960d972abe15c5d4ed6ccacbf8","target":"graph","created_at":"2026-05-18T00:40:17Z","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"},"paper":{"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 ","authors_text":"Abraham Ittycheriah, Haitao Mi, Zhiguo Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-02-22T14:55:26Z","title":"Semi-supervised Clustering for Short Text via Deep Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.06797","kind":"arxiv","version":2},"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:c859816dac4add6567639b11b9f59e3ab9fc497c08f640c00dadacbcd6fbc109","target":"record","created_at":"2026-05-18T00:40:17Z","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":"6a12e0a3fccbc9a4054da570e21b02230ab585ab57783cbd5961e1a64fe9b301","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-02-22T14:55:26Z","title_canon_sha256":"05c54a85e406ea2e7dc9e77e801b66f71fb90a57113e328554ccb1f5cbfa1bb4"},"schema_version":"1.0","source":{"id":"1602.06797","kind":"arxiv","version":2}},"canonical_sha256":"66ec69be518ca3e6fc099e7417456a5a58c4a9b688cced7d25f9ecf4d90ecb01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66ec69be518ca3e6fc099e7417456a5a58c4a9b688cced7d25f9ecf4d90ecb01","first_computed_at":"2026-05-18T00:40:17.572190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:17.572190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LNQL1PqHyi6u72yEcD0lEMFp+ZYar7ZoxFaPX8HYtt2bkB5BEubRo/9zXw6TSubD9fcuB+/CkEje4JTqAZ7CCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:17.572807Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.06797","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c859816dac4add6567639b11b9f59e3ab9fc497c08f640c00dadacbcd6fbc109","sha256:0cb724d5091cb2f788c263c2a1e1505a7814ad960d972abe15c5d4ed6ccacbf8"],"state_sha256":"b622f20f4bfae3041c2c33d4a145a13e8243c3e84dfc0026831104d9f45f7839"}