{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HAU4ZNHVUC5CQB2UZK6RHB7VKV","short_pith_number":"pith:HAU4ZNHV","schema_version":"1.0","canonical_sha256":"3829ccb4f5a0ba280754cabd1387f55552828878933f479e518fc4629d8c5b7d","source":{"kind":"arxiv","id":"2007.04239","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Transfer Learning in Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Irfan Ahmad, Maged Saeed AlShaibani, Zaid Alyafeai","submitted_at":"2020-05-31T21:52:31Z","abstract_excerpt":"Deep learning models usually require a huge amount of data. However, these large datasets are not always attainable. This is common in many challenging NLP tasks. Consider Neural Machine Translation, for instance, where curating such large datasets may not be possible specially for low resource languages. Another limitation of deep learning models is the demand for huge computing resources. These obstacles motivate research to question the possibility of knowledge transfer using large trained models. The demand for transfer learning is increasing as many large models are emerging. In this surv"},"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":"2007.04239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-31T21:52:31Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"3a4490a8321baad0067e88b464204390d98d81daa3218544cd47fb46ecf0d509","abstract_canon_sha256":"e17f1b31a65651d452610a01dd883059e53eadda78e10deb952a95e501981296"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:22.362302Z","signature_b64":"wfT2xSMF1CxBOt1a5hjrTdAkSSbibNgRQtdwsDtPWRu3Vy/54lBu9M//jLwANlp3m1rcAN2TGWoCAThmWY2FDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3829ccb4f5a0ba280754cabd1387f55552828878933f479e518fc4629d8c5b7d","last_reissued_at":"2026-07-05T01:17:22.361899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:22.361899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Transfer Learning in Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Irfan Ahmad, Maged Saeed AlShaibani, Zaid Alyafeai","submitted_at":"2020-05-31T21:52:31Z","abstract_excerpt":"Deep learning models usually require a huge amount of data. However, these large datasets are not always attainable. This is common in many challenging NLP tasks. Consider Neural Machine Translation, for instance, where curating such large datasets may not be possible specially for low resource languages. Another limitation of deep learning models is the demand for huge computing resources. These obstacles motivate research to question the possibility of knowledge transfer using large trained models. The demand for transfer learning is increasing as many large models are emerging. In this surv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04239","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.04239/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":"2007.04239","created_at":"2026-07-05T01:17:22.361955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.04239v1","created_at":"2026-07-05T01:17:22.361955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04239","created_at":"2026-07-05T01:17:22.361955+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAU4ZNHVUC5C","created_at":"2026-07-05T01:17:22.361955+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAU4ZNHVUC5CQB2U","created_at":"2026-07-05T01:17:22.361955+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAU4ZNHV","created_at":"2026-07-05T01:17:22.361955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20256","citing_title":"RADS: Reinforcement Learning-Based Sample Selection Improves Transfer Learning in Low-resource and Imbalanced Clinical Settings","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HAU4ZNHVUC5CQB2UZK6RHB7VKV","json":"https://pith.science/pith/HAU4ZNHVUC5CQB2UZK6RHB7VKV.json","graph_json":"https://pith.science/api/pith-number/HAU4ZNHVUC5CQB2UZK6RHB7VKV/graph.json","events_json":"https://pith.science/api/pith-number/HAU4ZNHVUC5CQB2UZK6RHB7VKV/events.json","paper":"https://pith.science/paper/HAU4ZNHV"},"agent_actions":{"view_html":"https://pith.science/pith/HAU4ZNHVUC5CQB2UZK6RHB7VKV","download_json":"https://pith.science/pith/HAU4ZNHVUC5CQB2UZK6RHB7VKV.json","view_paper":"https://pith.science/paper/HAU4ZNHV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.04239&json=true","fetch_graph":"https://pith.science/api/pith-number/HAU4ZNHVUC5CQB2UZK6RHB7VKV/graph.json","fetch_events":"https://pith.science/api/pith-number/HAU4ZNHVUC5CQB2UZK6RHB7VKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAU4ZNHVUC5CQB2UZK6RHB7VKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAU4ZNHVUC5CQB2UZK6RHB7VKV/action/storage_attestation","attest_author":"https://pith.science/pith/HAU4ZNHVUC5CQB2UZK6RHB7VKV/action/author_attestation","sign_citation":"https://pith.science/pith/HAU4ZNHVUC5CQB2UZK6RHB7VKV/action/citation_signature","submit_replication":"https://pith.science/pith/HAU4ZNHVUC5CQB2UZK6RHB7VKV/action/replication_record"}},"created_at":"2026-07-05T01:17:22.361955+00:00","updated_at":"2026-07-05T01:17:22.361955+00:00"}