{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UMAXAUBJPG6FEYTMPQYKQCTBW7","short_pith_number":"pith:UMAXAUBJ","schema_version":"1.0","canonical_sha256":"a30170502979bc52626c7c30a80a61b7f058625df5259c72f8307dd5c1affdd4","source":{"kind":"arxiv","id":"2209.07562","version":3},"attestation_state":"computed","paper":{"title":"TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twitter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed El-Kishky, Brian McWilliams, Jiawei Han, Omar Florez, Serim Park, Xinyang Zhang, Yury Malkov","submitted_at":"2022-09-15T19:01:21Z","abstract_excerpt":"Pre-trained language models (PLMs) are fundamental for natural language processing applications. Most existing PLMs are not tailored to the noisy user-generated text on social media, and the pre-training does not factor in the valuable social engagement logs available in a social network. We present TwHIN-BERT, a multilingual language model productionized at Twitter, trained on in-domain data from the popular social network. TwHIN-BERT differs from prior pre-trained language models as it is trained with not only text-based self-supervision, but also with a social objective based on the rich so"},"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":"2209.07562","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-15T19:01:21Z","cross_cats_sorted":[],"title_canon_sha256":"9c618b8df779078701bb79090faebd715e4dfccd0ee8f9212e5d496e0e42cc27","abstract_canon_sha256":"3d2719bd85933d77d3ef767c945b4c1b45bb912fa7b0adbc5630dd1053a6bfff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:46.475597Z","signature_b64":"EoVQGyVg/ITxts4sBgDg0vR8nj0I3V2q0vcr2VvxkeeQQT/oLuaO4+udmM17C32maWjK9RxbKlRSMF4NfuZLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a30170502979bc52626c7c30a80a61b7f058625df5259c72f8307dd5c1affdd4","last_reissued_at":"2026-07-05T06:44:46.475106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:46.475106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twitter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed El-Kishky, Brian McWilliams, Jiawei Han, Omar Florez, Serim Park, Xinyang Zhang, Yury Malkov","submitted_at":"2022-09-15T19:01:21Z","abstract_excerpt":"Pre-trained language models (PLMs) are fundamental for natural language processing applications. Most existing PLMs are not tailored to the noisy user-generated text on social media, and the pre-training does not factor in the valuable social engagement logs available in a social network. We present TwHIN-BERT, a multilingual language model productionized at Twitter, trained on in-domain data from the popular social network. TwHIN-BERT differs from prior pre-trained language models as it is trained with not only text-based self-supervision, but also with a social objective based on the rich so"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07562","kind":"arxiv","version":3},"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/2209.07562/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":"2209.07562","created_at":"2026-07-05T06:44:46.475164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.07562v3","created_at":"2026-07-05T06:44:46.475164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07562","created_at":"2026-07-05T06:44:46.475164+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMAXAUBJPG6F","created_at":"2026-07-05T06:44:46.475164+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMAXAUBJPG6FEYTM","created_at":"2026-07-05T06:44:46.475164+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMAXAUBJ","created_at":"2026-07-05T06:44:46.475164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04293","citing_title":"Forecasting Political News Engagement on Social Media","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00197","citing_title":"The $\\textit{Silicon Society}$ Cookbook: Design Space of LLM-based Social Simulations","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21536","citing_title":"Pre-trained LLMs Meet Sequential Recommenders: Efficient User-Centric Knowledge Distillation","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7","json":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7.json","graph_json":"https://pith.science/api/pith-number/UMAXAUBJPG6FEYTMPQYKQCTBW7/graph.json","events_json":"https://pith.science/api/pith-number/UMAXAUBJPG6FEYTMPQYKQCTBW7/events.json","paper":"https://pith.science/paper/UMAXAUBJ"},"agent_actions":{"view_html":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7","download_json":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7.json","view_paper":"https://pith.science/paper/UMAXAUBJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.07562&json=true","fetch_graph":"https://pith.science/api/pith-number/UMAXAUBJPG6FEYTMPQYKQCTBW7/graph.json","fetch_events":"https://pith.science/api/pith-number/UMAXAUBJPG6FEYTMPQYKQCTBW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7/action/storage_attestation","attest_author":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7/action/author_attestation","sign_citation":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7/action/citation_signature","submit_replication":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7/action/replication_record"}},"created_at":"2026-07-05T06:44:46.475164+00:00","updated_at":"2026-07-05T06:44:46.475164+00:00"}