{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UMAXAUBJPG6FEYTMPQYKQCTBW7","short_pith_number":"pith:UMAXAUBJ","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"},"canonical_sha256":"a30170502979bc52626c7c30a80a61b7f058625df5259c72f8307dd5c1affdd4","source":{"kind":"arxiv","id":"2209.07562","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.07562","created_at":"2026-07-05T06:44:46Z"},{"alias_kind":"arxiv_version","alias_value":"2209.07562v3","created_at":"2026-07-05T06:44:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07562","created_at":"2026-07-05T06:44:46Z"},{"alias_kind":"pith_short_12","alias_value":"UMAXAUBJPG6F","created_at":"2026-07-05T06:44:46Z"},{"alias_kind":"pith_short_16","alias_value":"UMAXAUBJPG6FEYTM","created_at":"2026-07-05T06:44:46Z"},{"alias_kind":"pith_short_8","alias_value":"UMAXAUBJ","created_at":"2026-07-05T06:44:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UMAXAUBJPG6FEYTMPQYKQCTBW7","target":"record","payload":{"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"},"canonical_sha256":"a30170502979bc52626c7c30a80a61b7f058625df5259c72f8307dd5c1affdd4","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"},"source_kind":"arxiv","source_id":"2209.07562","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:44:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QI3vH3LLoJqfl42IYML6tzmJcn6kADbBE/bS9HdFUgsqb2JCN9WyvwacHMWngr3UeVxmYBG7Lk5dctKM8z+CBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:20:53.660108Z"},"content_sha256":"46f13b84fc8b9e5e3ae2f268d3aea5e0f363783cbe38aeef832dbbcd9f0ac7f8","schema_version":"1.0","event_id":"sha256:46f13b84fc8b9e5e3ae2f268d3aea5e0f363783cbe38aeef832dbbcd9f0ac7f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UMAXAUBJPG6FEYTMPQYKQCTBW7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:44:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q5lzXIErqoeUJQu8L60ZZhDjVMk439qaU0v0eehdBTcGVByA5o7oUy2HuHk0O6d+rkflud9vOEaaC8IO3IUOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:20:53.660661Z"},"content_sha256":"5b446dc7b7d048b2e1e10fc5eefb4567217c6170f47005d26172bdcd2b4d9535","schema_version":"1.0","event_id":"sha256:5b446dc7b7d048b2e1e10fc5eefb4567217c6170f47005d26172bdcd2b4d9535"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7/bundle.json","state_url":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T06:20:53Z","links":{"resolver":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7","bundle":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7/bundle.json","state":"https://pith.science/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UMAXAUBJPG6FEYTMPQYKQCTBW7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UMAXAUBJPG6FEYTMPQYKQCTBW7","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":"3d2719bd85933d77d3ef767c945b4c1b45bb912fa7b0adbc5630dd1053a6bfff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-15T19:01:21Z","title_canon_sha256":"9c618b8df779078701bb79090faebd715e4dfccd0ee8f9212e5d496e0e42cc27"},"schema_version":"1.0","source":{"id":"2209.07562","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.07562","created_at":"2026-07-05T06:44:46Z"},{"alias_kind":"arxiv_version","alias_value":"2209.07562v3","created_at":"2026-07-05T06:44:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07562","created_at":"2026-07-05T06:44:46Z"},{"alias_kind":"pith_short_12","alias_value":"UMAXAUBJPG6F","created_at":"2026-07-05T06:44:46Z"},{"alias_kind":"pith_short_16","alias_value":"UMAXAUBJPG6FEYTM","created_at":"2026-07-05T06:44:46Z"},{"alias_kind":"pith_short_8","alias_value":"UMAXAUBJ","created_at":"2026-07-05T06:44:46Z"}],"graph_snapshots":[{"event_id":"sha256:5b446dc7b7d048b2e1e10fc5eefb4567217c6170f47005d26172bdcd2b4d9535","target":"graph","created_at":"2026-07-05T06:44:46Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2209.07562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ahmed El-Kishky, Brian McWilliams, Jiawei Han, Omar Florez, Serim Park, Xinyang Zhang, Yury Malkov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-15T19:01:21Z","title":"TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twitter"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07562","kind":"arxiv","version":3},"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":"sha256:46f13b84fc8b9e5e3ae2f268d3aea5e0f363783cbe38aeef832dbbcd9f0ac7f8","target":"record","created_at":"2026-07-05T06:44:46Z","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":"3d2719bd85933d77d3ef767c945b4c1b45bb912fa7b0adbc5630dd1053a6bfff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-15T19:01:21Z","title_canon_sha256":"9c618b8df779078701bb79090faebd715e4dfccd0ee8f9212e5d496e0e42cc27"},"schema_version":"1.0","source":{"id":"2209.07562","kind":"arxiv","version":3}},"canonical_sha256":"a30170502979bc52626c7c30a80a61b7f058625df5259c72f8307dd5c1affdd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a30170502979bc52626c7c30a80a61b7f058625df5259c72f8307dd5c1affdd4","first_computed_at":"2026-07-05T06:44:46.475106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:44:46.475106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EoVQGyVg/ITxts4sBgDg0vR8nj0I3V2q0vcr2VvxkeeQQT/oLuaO4+udmM17C32maWjK9RxbKlRSMF4NfuZLAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:44:46.475597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.07562","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46f13b84fc8b9e5e3ae2f268d3aea5e0f363783cbe38aeef832dbbcd9f0ac7f8","sha256:5b446dc7b7d048b2e1e10fc5eefb4567217c6170f47005d26172bdcd2b4d9535"],"state_sha256":"f94e865c24e02d3588df72e38b557c4df8a94708b4e12f3ec3270112754743c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YC+Z5xfT8T3ptYo5zKTBXYFvfAPvTLtnBfNJvvDOcJtm6sUUQ35Csg8s+eYcJZN/zA+dJFZ1LotXEzNRUDzFBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T06:20:53.665211Z","bundle_sha256":"245554322ca4a970c29205a106c5c2865e71d8969d38c6d0e6e8ebcbe4bc7e03"}}