{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:MUD3CD2WAM46WA5YJBW4T4ALJN","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":"6af562250e3a5cad24af27a326e269fd1c8646a623f5d9c37396203c49695f68","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-11T15:30:09Z","title_canon_sha256":"68d8b475edb61bfa637d0f8a6e7493c4a948c5604986471f35f35a01e5575897"},"schema_version":"1.0","source":{"id":"1605.03481","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.03481","created_at":"2026-05-18T01:14:38Z"},{"alias_kind":"arxiv_version","alias_value":"1605.03481v2","created_at":"2026-05-18T01:14:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.03481","created_at":"2026-05-18T01:14:38Z"},{"alias_kind":"pith_short_12","alias_value":"MUD3CD2WAM46","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MUD3CD2WAM46WA5Y","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MUD3CD2W","created_at":"2026-05-18T12:30:32Z"}],"graph_snapshots":[{"event_id":"sha256:cd9a62262a64ea8bd0bb168a9fb8c575f6b80511605426059c7dbacabc14deb8","target":"graph","created_at":"2026-05-18T01:14:38Z","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":"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","authors_text":"Bhuwan Dhingra, Dylan Fitzpatrick, Michael Muehl, William W. Cohen, Zhong Zhou","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-11T15:30:09Z","title":"Tweet2Vec: Character-Based Distributed Representations for Social Media"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.03481","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":"sha256:5a008c63698269f011a98f5b41fb0456839a48685fdc842eb6b0c1a23bcf7810","target":"record","created_at":"2026-05-18T01:14:38Z","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":"6af562250e3a5cad24af27a326e269fd1c8646a623f5d9c37396203c49695f68","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-11T15:30:09Z","title_canon_sha256":"68d8b475edb61bfa637d0f8a6e7493c4a948c5604986471f35f35a01e5575897"},"schema_version":"1.0","source":{"id":"1605.03481","kind":"arxiv","version":2}},"canonical_sha256":"6507b10f560339eb03b8486dc9f00b4b7c014ab6bfb76435f8312dfe6924db79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6507b10f560339eb03b8486dc9f00b4b7c014ab6bfb76435f8312dfe6924db79","first_computed_at":"2026-05-18T01:14:38.175183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:14:38.175183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oB3iyncMDokzC6YOs5y/Fjn2Wt2SfMFR51RPzLow6XynWlCIxpvkQajuXMPo8ZDLE78VREZv1twmXqp16mhZDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:14:38.176015Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.03481","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a008c63698269f011a98f5b41fb0456839a48685fdc842eb6b0c1a23bcf7810","sha256:cd9a62262a64ea8bd0bb168a9fb8c575f6b80511605426059c7dbacabc14deb8"],"state_sha256":"54ff76fbc3853b63ed4352f6475d1b8878fe534ffee38659ca7967f698ee1c99"}