{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:JQ4RHTVZOA7JUHZLFEHBYYAZQT","short_pith_number":"pith:JQ4RHTVZ","schema_version":"1.0","canonical_sha256":"4c3913ceb9703e9a1f2b290e1c601984d24fa3249c17dc7b3599eaba55292c04","source":{"kind":"arxiv","id":"1607.07514","version":1},"attestation_state":"computed","paper":{"title":"Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.SI"],"primary_cat":"cs.CL","authors_text":"Deb Roy, Prashanth Vijayaraghavan, Soroush Vosoughi","submitted_at":"2016-07-26T00:58:14Z","abstract_excerpt":"We present Tweet2Vec, a novel method for generating general-purpose vector representation of tweets. The model learns tweet embeddings using character-level CNN-LSTM encoder-decoder. We trained our model on 3 million, randomly selected English-language tweets. The model was evaluated using two methods: tweet semantic similarity and tweet sentiment categorization, outperforming the previous state-of-the-art in both tasks. The evaluations demonstrate the power of the tweet embeddings generated by our model for various tweet categorization tasks. The vector representations generated by our model "},"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":"1607.07514","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-26T00:58:14Z","cross_cats_sorted":["cs.AI","cs.NE","cs.SI"],"title_canon_sha256":"833954a1759005a69a45a36d7e14a3f31f57b0ba21f0e1d6c8dd4f1e38e762a4","abstract_canon_sha256":"408affef87f1fc62e38c5102e226e6b014b7193b72d1ba6e40a97496b0b5f4e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:28.377487Z","signature_b64":"AXdmo21HAKbAA4A3edMa+bS9g0H2IQ3p97ULNqsQf1L93RkkVFyJ1+HTlBBrSv9e3QcJMSeGmRdPr+TlhkrIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c3913ceb9703e9a1f2b290e1c601984d24fa3249c17dc7b3599eaba55292c04","last_reissued_at":"2026-05-18T01:10:28.376963Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:28.376963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.SI"],"primary_cat":"cs.CL","authors_text":"Deb Roy, Prashanth Vijayaraghavan, Soroush Vosoughi","submitted_at":"2016-07-26T00:58:14Z","abstract_excerpt":"We present Tweet2Vec, a novel method for generating general-purpose vector representation of tweets. The model learns tweet embeddings using character-level CNN-LSTM encoder-decoder. We trained our model on 3 million, randomly selected English-language tweets. The model was evaluated using two methods: tweet semantic similarity and tweet sentiment categorization, outperforming the previous state-of-the-art in both tasks. The evaluations demonstrate the power of the tweet embeddings generated by our model for various tweet categorization tasks. The vector representations generated by our model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.07514","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":"1607.07514","created_at":"2026-05-18T01:10:28.377039+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.07514v1","created_at":"2026-05-18T01:10:28.377039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.07514","created_at":"2026-05-18T01:10:28.377039+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQ4RHTVZOA7J","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQ4RHTVZOA7JUHZL","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQ4RHTVZ","created_at":"2026-05-18T12:30:25.849896+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/JQ4RHTVZOA7JUHZLFEHBYYAZQT","json":"https://pith.science/pith/JQ4RHTVZOA7JUHZLFEHBYYAZQT.json","graph_json":"https://pith.science/api/pith-number/JQ4RHTVZOA7JUHZLFEHBYYAZQT/graph.json","events_json":"https://pith.science/api/pith-number/JQ4RHTVZOA7JUHZLFEHBYYAZQT/events.json","paper":"https://pith.science/paper/JQ4RHTVZ"},"agent_actions":{"view_html":"https://pith.science/pith/JQ4RHTVZOA7JUHZLFEHBYYAZQT","download_json":"https://pith.science/pith/JQ4RHTVZOA7JUHZLFEHBYYAZQT.json","view_paper":"https://pith.science/paper/JQ4RHTVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.07514&json=true","fetch_graph":"https://pith.science/api/pith-number/JQ4RHTVZOA7JUHZLFEHBYYAZQT/graph.json","fetch_events":"https://pith.science/api/pith-number/JQ4RHTVZOA7JUHZLFEHBYYAZQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQ4RHTVZOA7JUHZLFEHBYYAZQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQ4RHTVZOA7JUHZLFEHBYYAZQT/action/storage_attestation","attest_author":"https://pith.science/pith/JQ4RHTVZOA7JUHZLFEHBYYAZQT/action/author_attestation","sign_citation":"https://pith.science/pith/JQ4RHTVZOA7JUHZLFEHBYYAZQT/action/citation_signature","submit_replication":"https://pith.science/pith/JQ4RHTVZOA7JUHZLFEHBYYAZQT/action/replication_record"}},"created_at":"2026-05-18T01:10:28.377039+00:00","updated_at":"2026-05-18T01:10:28.377039+00:00"}