{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:66RJEVQMM3B76HZTXWBSV44CCS","short_pith_number":"pith:66RJEVQM","schema_version":"1.0","canonical_sha256":"f7a292560c66c3ff1f33bd832af38214905e935641e2aad07047504d364e0113","source":{"kind":"arxiv","id":"2202.03829","version":2},"attestation_state":"computed","paper":{"title":"TimeLMs: Diachronic Language Models from Twitter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daniel Loureiro, Francesco Barbieri, Jose Camacho-Collados, Leonardo Neves, Luis Espinosa Anke","submitted_at":"2022-02-08T12:47:38Z","abstract_excerpt":"Despite its importance, the time variable has been largely neglected in the NLP and language model literature. In this paper, we present TimeLMs, a set of language models specialized on diachronic Twitter data. We show that a continual learning strategy contributes to enhancing Twitter-based language models' capacity to deal with future and out-of-distribution tweets, while making them competitive with standardized and more monolithic benchmarks. We also perform a number of qualitative analyses showing how they cope with trends and peaks in activity involving specific named entities or concept"},"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":"2202.03829","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-08T12:47:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"51f6cdb6d365297fe3dcd98dc7262f8fdf6277c0af862343edbab25f604a984e","abstract_canon_sha256":"cbffd1f0120efa091512b0bba138036e781f1fe8a819d6e897585f60ee10303a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:39.567855Z","signature_b64":"ofpcR8Ekmwk2K9CuoAIclRiC0mWKld2P/KE78Yp1S5NS+gdc+MuwXhlq4Hmxwc3gtD/qCcJn3psa+IpShj/wBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7a292560c66c3ff1f33bd832af38214905e935641e2aad07047504d364e0113","last_reissued_at":"2026-07-05T04:10:39.567397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:39.567397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TimeLMs: Diachronic Language Models from Twitter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daniel Loureiro, Francesco Barbieri, Jose Camacho-Collados, Leonardo Neves, Luis Espinosa Anke","submitted_at":"2022-02-08T12:47:38Z","abstract_excerpt":"Despite its importance, the time variable has been largely neglected in the NLP and language model literature. In this paper, we present TimeLMs, a set of language models specialized on diachronic Twitter data. We show that a continual learning strategy contributes to enhancing Twitter-based language models' capacity to deal with future and out-of-distribution tweets, while making them competitive with standardized and more monolithic benchmarks. We also perform a number of qualitative analyses showing how they cope with trends and peaks in activity involving specific named entities or concept"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03829","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/2202.03829/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":"2202.03829","created_at":"2026-07-05T04:10:39.567450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03829v2","created_at":"2026-07-05T04:10:39.567450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03829","created_at":"2026-07-05T04:10:39.567450+00:00"},{"alias_kind":"pith_short_12","alias_value":"66RJEVQMM3B7","created_at":"2026-07-05T04:10:39.567450+00:00"},{"alias_kind":"pith_short_16","alias_value":"66RJEVQMM3B76HZT","created_at":"2026-07-05T04:10:39.567450+00:00"},{"alias_kind":"pith_short_8","alias_value":"66RJEVQM","created_at":"2026-07-05T04:10:39.567450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2205.00445","citing_title":"MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09469","citing_title":"FinMoji: A Framework for Emoji-driven Sentiment Analysis in Financial Social Media","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66RJEVQMM3B76HZTXWBSV44CCS","json":"https://pith.science/pith/66RJEVQMM3B76HZTXWBSV44CCS.json","graph_json":"https://pith.science/api/pith-number/66RJEVQMM3B76HZTXWBSV44CCS/graph.json","events_json":"https://pith.science/api/pith-number/66RJEVQMM3B76HZTXWBSV44CCS/events.json","paper":"https://pith.science/paper/66RJEVQM"},"agent_actions":{"view_html":"https://pith.science/pith/66RJEVQMM3B76HZTXWBSV44CCS","download_json":"https://pith.science/pith/66RJEVQMM3B76HZTXWBSV44CCS.json","view_paper":"https://pith.science/paper/66RJEVQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03829&json=true","fetch_graph":"https://pith.science/api/pith-number/66RJEVQMM3B76HZTXWBSV44CCS/graph.json","fetch_events":"https://pith.science/api/pith-number/66RJEVQMM3B76HZTXWBSV44CCS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66RJEVQMM3B76HZTXWBSV44CCS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66RJEVQMM3B76HZTXWBSV44CCS/action/storage_attestation","attest_author":"https://pith.science/pith/66RJEVQMM3B76HZTXWBSV44CCS/action/author_attestation","sign_citation":"https://pith.science/pith/66RJEVQMM3B76HZTXWBSV44CCS/action/citation_signature","submit_replication":"https://pith.science/pith/66RJEVQMM3B76HZTXWBSV44CCS/action/replication_record"}},"created_at":"2026-07-05T04:10:39.567450+00:00","updated_at":"2026-07-05T04:10:39.567450+00:00"}