{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CSJGJ2OBAEIFQQG6CBQMH3JM7G","short_pith_number":"pith:CSJGJ2OB","schema_version":"1.0","canonical_sha256":"149264e9c101105840de1060c3ed2cf9b6098d9cdab4b3757ab4e4f7f06460a8","source":{"kind":"arxiv","id":"2104.12250","version":2},"attestation_state":"computed","paper":{"title":"XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Francesco Barbieri, Jose Camacho-Collados, Luis Espinosa Anke","submitted_at":"2021-04-25T20:28:53Z","abstract_excerpt":"Language models are ubiquitous in current NLP, and their multilingual capacity has recently attracted considerable attention. However, current analyses have almost exclusively focused on (multilingual variants of) standard benchmarks, and have relied on clean pre-training and task-specific corpora as multilingual signals. In this paper, we introduce XLM-T, a model to train and evaluate multilingual language models in Twitter. In this paper we provide: (1) a new strong multilingual baseline consisting of an XLM-R (Conneau et al. 2020) model pre-trained on millions of tweets in over thirty langu"},"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":"2104.12250","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-25T20:28:53Z","cross_cats_sorted":[],"title_canon_sha256":"6a413a4fce9d30a5f368471155cca1a53c1f4bf8767f3741c2fa610f5b76bf86","abstract_canon_sha256":"236305791a6b66bc2901cfb0b8e1da7617d52cc5a889165649ad7efd2ebc278a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:15.868850Z","signature_b64":"UcfOyfHcp7gAppRtLk1MEuzC1HeKVCLaA/dYjjFGNJPYvr9V6Y6F5y5GXyM+wql4JZWGLskRrQBiqCJiN3n1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"149264e9c101105840de1060c3ed2cf9b6098d9cdab4b3757ab4e4f7f06460a8","last_reissued_at":"2026-07-05T04:22:15.868438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:15.868438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Francesco Barbieri, Jose Camacho-Collados, Luis Espinosa Anke","submitted_at":"2021-04-25T20:28:53Z","abstract_excerpt":"Language models are ubiquitous in current NLP, and their multilingual capacity has recently attracted considerable attention. However, current analyses have almost exclusively focused on (multilingual variants of) standard benchmarks, and have relied on clean pre-training and task-specific corpora as multilingual signals. In this paper, we introduce XLM-T, a model to train and evaluate multilingual language models in Twitter. In this paper we provide: (1) a new strong multilingual baseline consisting of an XLM-R (Conneau et al. 2020) model pre-trained on millions of tweets in over thirty langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.12250","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.12250/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2104.12250","created_at":"2026-07-05T04:22:15.868494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.12250v2","created_at":"2026-07-05T04:22:15.868494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.12250","created_at":"2026-07-05T04:22:15.868494+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSJGJ2OBAEIF","created_at":"2026-07-05T04:22:15.868494+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSJGJ2OBAEIFQQG6","created_at":"2026-07-05T04:22:15.868494+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSJGJ2OB","created_at":"2026-07-05T04:22:15.868494+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20796","citing_title":"Speech Emotion Recognition via Entropy-Aware Score Selection","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CSJGJ2OBAEIFQQG6CBQMH3JM7G","json":"https://pith.science/pith/CSJGJ2OBAEIFQQG6CBQMH3JM7G.json","graph_json":"https://pith.science/api/pith-number/CSJGJ2OBAEIFQQG6CBQMH3JM7G/graph.json","events_json":"https://pith.science/api/pith-number/CSJGJ2OBAEIFQQG6CBQMH3JM7G/events.json","paper":"https://pith.science/paper/CSJGJ2OB"},"agent_actions":{"view_html":"https://pith.science/pith/CSJGJ2OBAEIFQQG6CBQMH3JM7G","download_json":"https://pith.science/pith/CSJGJ2OBAEIFQQG6CBQMH3JM7G.json","view_paper":"https://pith.science/paper/CSJGJ2OB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.12250&json=true","fetch_graph":"https://pith.science/api/pith-number/CSJGJ2OBAEIFQQG6CBQMH3JM7G/graph.json","fetch_events":"https://pith.science/api/pith-number/CSJGJ2OBAEIFQQG6CBQMH3JM7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSJGJ2OBAEIFQQG6CBQMH3JM7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSJGJ2OBAEIFQQG6CBQMH3JM7G/action/storage_attestation","attest_author":"https://pith.science/pith/CSJGJ2OBAEIFQQG6CBQMH3JM7G/action/author_attestation","sign_citation":"https://pith.science/pith/CSJGJ2OBAEIFQQG6CBQMH3JM7G/action/citation_signature","submit_replication":"https://pith.science/pith/CSJGJ2OBAEIFQQG6CBQMH3JM7G/action/replication_record"}},"created_at":"2026-07-05T04:22:15.868494+00:00","updated_at":"2026-07-05T04:22:15.868494+00:00"}