{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:YYJKKAZPIIICLZOZ4DEV4ZBZQ2","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":"6cfca1d100829c2576c2e39b005ec895dbb7e813fdb26589687a2c9aa7306999","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-03-15T12:37:22Z","title_canon_sha256":"6dea17ef93fcdd0c077205a51559b7f8f7ec957fb00f259a2ac44a7f3eb006b8"},"schema_version":"1.0","source":{"id":"1703.05123","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.05123","created_at":"2026-05-18T00:48:34Z"},{"alias_kind":"arxiv_version","alias_value":"1703.05123v2","created_at":"2026-05-18T00:48:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.05123","created_at":"2026-05-18T00:48:34Z"},{"alias_kind":"pith_short_12","alias_value":"YYJKKAZPIIIC","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"YYJKKAZPIIICLZOZ","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"YYJKKAZP","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:bff3617a1088e32b95942997bc14e1dd4953c35f101249a8e8baa7e36f3e71ef","target":"graph","created_at":"2026-05-18T00:48:34Z","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 paper we show how the performance of tweet clustering can be improved by leveraging character-based neural networks. The proposed approach overcomes the limitations related to the vocabulary explosion in the word-based models and allows for the seamless processing of the multilingual content. Our evaluation results and code are available on-line at https://github.com/vendi12/tweet2vec_clustering","authors_text":"Lyndon Nixon, Mihai Lupu, Svitlana Vakulenko","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-03-15T12:37:22Z","title":"Character-based Neural Embeddings for Tweet Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.05123","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":"sha256:6bf9748d3ad6e89cc0a6a4f66181d8eccaf805a98012ecfa6834c162abc83ba0","target":"record","created_at":"2026-05-18T00:48:34Z","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":"6cfca1d100829c2576c2e39b005ec895dbb7e813fdb26589687a2c9aa7306999","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-03-15T12:37:22Z","title_canon_sha256":"6dea17ef93fcdd0c077205a51559b7f8f7ec957fb00f259a2ac44a7f3eb006b8"},"schema_version":"1.0","source":{"id":"1703.05123","kind":"arxiv","version":2}},"canonical_sha256":"c612a5032f421025e5d9e0c95e643986a8c96668006f143730492f541e682207","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c612a5032f421025e5d9e0c95e643986a8c96668006f143730492f541e682207","first_computed_at":"2026-05-18T00:48:34.707925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:34.707925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+7A1oXqba/MVYddRZxAXXFAv6IZnHhYz5sct2OSRUOtaRFeAQtFgmXy7BJ4MnicUgJJMTRNhyAwd/Vxzhdm5Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:34.708421Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.05123","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bf9748d3ad6e89cc0a6a4f66181d8eccaf805a98012ecfa6834c162abc83ba0","sha256:bff3617a1088e32b95942997bc14e1dd4953c35f101249a8e8baa7e36f3e71ef"],"state_sha256":"3ff17e7a7b9c8b82d64755b0dd528d92b87eb56f8afb827d13ee397263b8c058"}