{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:S7L3EO7TBFIIGC3UPBXWXC5PXI","short_pith_number":"pith:S7L3EO7T","schema_version":"1.0","canonical_sha256":"97d7b23bf30950830b74786f6b8bafba1ef3c9904137620b711fd9a51d2b54d2","source":{"kind":"arxiv","id":"1905.06638","version":1},"attestation_state":"computed","paper":{"title":"Latent Universal Task-Specific BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Alon Rozental, Daniel Fleischer, Zohar Kelrich","submitted_at":"2019-05-16T10:21:51Z","abstract_excerpt":"This paper describes a language representation model which combines the Bidirectional Encoder Representations from Transformers (BERT) learning mechanism described in Devlin et al. (2018) with a generalization of the Universal Transformer model described in Dehghani et al. (2018). We further improve this model by adding a latent variable that represents the persona and topics of interests of the writer for each training example. We also describe a simple method to improve the usefulness of our language representation for solving problems in a specific domain at the expense of its ability to ge"},"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":"1905.06638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-16T10:21:51Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"520c1096c4f1953781aee942216a61586a1f0e34ee122a0964f8b379028a5c18","abstract_canon_sha256":"ab75392ed9bd260d6dfcd4d1cf32e08763af2713db193bc661ed6df18bbb4634"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:01.589889Z","signature_b64":"nOFxLiRBuOjPlwDqrzm7BFbM8pWRS5jgDtMGuEvFL4sgExPVvPyQVrOa5xUS9MPEA7HVgruUG3JxbSeA9k8lCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97d7b23bf30950830b74786f6b8bafba1ef3c9904137620b711fd9a51d2b54d2","last_reissued_at":"2026-05-17T23:46:01.589186Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:01.589186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Universal Task-Specific BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Alon Rozental, Daniel Fleischer, Zohar Kelrich","submitted_at":"2019-05-16T10:21:51Z","abstract_excerpt":"This paper describes a language representation model which combines the Bidirectional Encoder Representations from Transformers (BERT) learning mechanism described in Devlin et al. (2018) with a generalization of the Universal Transformer model described in Dehghani et al. (2018). We further improve this model by adding a latent variable that represents the persona and topics of interests of the writer for each training example. We also describe a simple method to improve the usefulness of our language representation for solving problems in a specific domain at the expense of its ability to ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06638","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1905.06638","created_at":"2026-05-17T23:46:01.589303+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.06638v1","created_at":"2026-05-17T23:46:01.589303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06638","created_at":"2026-05-17T23:46:01.589303+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7L3EO7TBFII","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7L3EO7TBFIIGC3U","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7L3EO7T","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S7L3EO7TBFIIGC3UPBXWXC5PXI","json":"https://pith.science/pith/S7L3EO7TBFIIGC3UPBXWXC5PXI.json","graph_json":"https://pith.science/api/pith-number/S7L3EO7TBFIIGC3UPBXWXC5PXI/graph.json","events_json":"https://pith.science/api/pith-number/S7L3EO7TBFIIGC3UPBXWXC5PXI/events.json","paper":"https://pith.science/paper/S7L3EO7T"},"agent_actions":{"view_html":"https://pith.science/pith/S7L3EO7TBFIIGC3UPBXWXC5PXI","download_json":"https://pith.science/pith/S7L3EO7TBFIIGC3UPBXWXC5PXI.json","view_paper":"https://pith.science/paper/S7L3EO7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.06638&json=true","fetch_graph":"https://pith.science/api/pith-number/S7L3EO7TBFIIGC3UPBXWXC5PXI/graph.json","fetch_events":"https://pith.science/api/pith-number/S7L3EO7TBFIIGC3UPBXWXC5PXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7L3EO7TBFIIGC3UPBXWXC5PXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7L3EO7TBFIIGC3UPBXWXC5PXI/action/storage_attestation","attest_author":"https://pith.science/pith/S7L3EO7TBFIIGC3UPBXWXC5PXI/action/author_attestation","sign_citation":"https://pith.science/pith/S7L3EO7TBFIIGC3UPBXWXC5PXI/action/citation_signature","submit_replication":"https://pith.science/pith/S7L3EO7TBFIIGC3UPBXWXC5PXI/action/replication_record"}},"created_at":"2026-05-17T23:46:01.589303+00:00","updated_at":"2026-05-17T23:46:01.589303+00:00"}