{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:MUD3CD2WAM46WA5YJBW4T4ALJN","short_pith_number":"pith:MUD3CD2W","schema_version":"1.0","canonical_sha256":"6507b10f560339eb03b8486dc9f00b4b7c014ab6bfb76435f8312dfe6924db79","source":{"kind":"arxiv","id":"1605.03481","version":2},"attestation_state":"computed","paper":{"title":"Tweet2Vec: Character-Based Distributed Representations for Social Media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bhuwan Dhingra, Dylan Fitzpatrick, Michael Muehl, William W. Cohen, Zhong Zhou","submitted_at":"2016-05-11T15:30:09Z","abstract_excerpt":"Text from social media provides a set of challenges that can cause traditional NLP approaches to fail. Informal language, spelling errors, abbreviations, and special characters are all commonplace in these posts, leading to a prohibitively large vocabulary size for word-level approaches. We propose a character composition model, tweet2vec, which finds vector-space representations of whole tweets by learning complex, non-local dependencies in character sequences. The proposed model outperforms a word-level baseline at predicting user-annotated hashtags associated with the posts, doing significa"},"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":"1605.03481","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-11T15:30:09Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"68d8b475edb61bfa637d0f8a6e7493c4a948c5604986471f35f35a01e5575897","abstract_canon_sha256":"6af562250e3a5cad24af27a326e269fd1c8646a623f5d9c37396203c49695f68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:38.176015Z","signature_b64":"oB3iyncMDokzC6YOs5y/Fjn2Wt2SfMFR51RPzLow6XynWlCIxpvkQajuXMPo8ZDLE78VREZv1twmXqp16mhZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6507b10f560339eb03b8486dc9f00b4b7c014ab6bfb76435f8312dfe6924db79","last_reissued_at":"2026-05-18T01:14:38.175183Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:38.175183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tweet2Vec: Character-Based Distributed Representations for Social Media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bhuwan Dhingra, Dylan Fitzpatrick, Michael Muehl, William W. Cohen, Zhong Zhou","submitted_at":"2016-05-11T15:30:09Z","abstract_excerpt":"Text from social media provides a set of challenges that can cause traditional NLP approaches to fail. Informal language, spelling errors, abbreviations, and special characters are all commonplace in these posts, leading to a prohibitively large vocabulary size for word-level approaches. We propose a character composition model, tweet2vec, which finds vector-space representations of whole tweets by learning complex, non-local dependencies in character sequences. The proposed model outperforms a word-level baseline at predicting user-annotated hashtags associated with the posts, doing significa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.03481","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":"1605.03481","created_at":"2026-05-18T01:14:38.175332+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.03481v2","created_at":"2026-05-18T01:14:38.175332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.03481","created_at":"2026-05-18T01:14:38.175332+00:00"},{"alias_kind":"pith_short_12","alias_value":"MUD3CD2WAM46","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"MUD3CD2WAM46WA5Y","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"MUD3CD2W","created_at":"2026-05-18T12:30:32.724797+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/MUD3CD2WAM46WA5YJBW4T4ALJN","json":"https://pith.science/pith/MUD3CD2WAM46WA5YJBW4T4ALJN.json","graph_json":"https://pith.science/api/pith-number/MUD3CD2WAM46WA5YJBW4T4ALJN/graph.json","events_json":"https://pith.science/api/pith-number/MUD3CD2WAM46WA5YJBW4T4ALJN/events.json","paper":"https://pith.science/paper/MUD3CD2W"},"agent_actions":{"view_html":"https://pith.science/pith/MUD3CD2WAM46WA5YJBW4T4ALJN","download_json":"https://pith.science/pith/MUD3CD2WAM46WA5YJBW4T4ALJN.json","view_paper":"https://pith.science/paper/MUD3CD2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.03481&json=true","fetch_graph":"https://pith.science/api/pith-number/MUD3CD2WAM46WA5YJBW4T4ALJN/graph.json","fetch_events":"https://pith.science/api/pith-number/MUD3CD2WAM46WA5YJBW4T4ALJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MUD3CD2WAM46WA5YJBW4T4ALJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MUD3CD2WAM46WA5YJBW4T4ALJN/action/storage_attestation","attest_author":"https://pith.science/pith/MUD3CD2WAM46WA5YJBW4T4ALJN/action/author_attestation","sign_citation":"https://pith.science/pith/MUD3CD2WAM46WA5YJBW4T4ALJN/action/citation_signature","submit_replication":"https://pith.science/pith/MUD3CD2WAM46WA5YJBW4T4ALJN/action/replication_record"}},"created_at":"2026-05-18T01:14:38.175332+00:00","updated_at":"2026-05-18T01:14:38.175332+00:00"}