{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SFNWCJ236YINBIKUGXKTV6ZQFU","short_pith_number":"pith:SFNWCJ23","schema_version":"1.0","canonical_sha256":"915b61275bf610d0a15435d53afb302d370c426c2e6775f46b4a46f8b02a6b72","source":{"kind":"arxiv","id":"1912.05308","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Transfer Learning via BERT Neuron Selection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Carolina Bessega, En-Shiun Annie Lee, Jaime R. Jamacaro, Mehrdad Valipour","submitted_at":"2019-12-10T16:08:26Z","abstract_excerpt":"Recent advancements in language representation models such as BERT have led to a rapid improvement in numerous natural language processing tasks. However, language models usually consist of a few hundred million trainable parameters with embedding space distributed across multiple layers, thus making them challenging to be fine-tuned for a specific task or to be transferred to a new domain. To determine whether there are task-specific neurons that can be exploited for unsupervised transfer learning, we introduce a method for selecting the most important neurons to solve a specific classificati"},"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":"1912.05308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-12-10T16:08:26Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"1a89d50dbe15a349689ba18feacac0feddd46b8e6dae4b1877d2867354bb8899","abstract_canon_sha256":"a467b02371e801360b2fed97bd6d510bf632ada4110bb368d355721b95c9f9ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:34.216423Z","signature_b64":"jlYUsFZ1zPsJJVZXW+UYoDxtKbwGIPqyEyoRQhyCKZMVI3tazKNC03qlGIlOGzvblkmzxs8TStz/Hy6Mp8EzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"915b61275bf610d0a15435d53afb302d370c426c2e6775f46b4a46f8b02a6b72","last_reissued_at":"2026-07-05T00:25:34.216015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:34.216015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Transfer Learning via BERT Neuron Selection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Carolina Bessega, En-Shiun Annie Lee, Jaime R. Jamacaro, Mehrdad Valipour","submitted_at":"2019-12-10T16:08:26Z","abstract_excerpt":"Recent advancements in language representation models such as BERT have led to a rapid improvement in numerous natural language processing tasks. However, language models usually consist of a few hundred million trainable parameters with embedding space distributed across multiple layers, thus making them challenging to be fine-tuned for a specific task or to be transferred to a new domain. To determine whether there are task-specific neurons that can be exploited for unsupervised transfer learning, we introduce a method for selecting the most important neurons to solve a specific classificati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05308","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/1912.05308/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":"1912.05308","created_at":"2026-07-05T00:25:34.216074+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.05308v1","created_at":"2026-07-05T00:25:34.216074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05308","created_at":"2026-07-05T00:25:34.216074+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFNWCJ236YIN","created_at":"2026-07-05T00:25:34.216074+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFNWCJ236YINBIKU","created_at":"2026-07-05T00:25:34.216074+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFNWCJ23","created_at":"2026-07-05T00:25:34.216074+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/SFNWCJ236YINBIKUGXKTV6ZQFU","json":"https://pith.science/pith/SFNWCJ236YINBIKUGXKTV6ZQFU.json","graph_json":"https://pith.science/api/pith-number/SFNWCJ236YINBIKUGXKTV6ZQFU/graph.json","events_json":"https://pith.science/api/pith-number/SFNWCJ236YINBIKUGXKTV6ZQFU/events.json","paper":"https://pith.science/paper/SFNWCJ23"},"agent_actions":{"view_html":"https://pith.science/pith/SFNWCJ236YINBIKUGXKTV6ZQFU","download_json":"https://pith.science/pith/SFNWCJ236YINBIKUGXKTV6ZQFU.json","view_paper":"https://pith.science/paper/SFNWCJ23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.05308&json=true","fetch_graph":"https://pith.science/api/pith-number/SFNWCJ236YINBIKUGXKTV6ZQFU/graph.json","fetch_events":"https://pith.science/api/pith-number/SFNWCJ236YINBIKUGXKTV6ZQFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFNWCJ236YINBIKUGXKTV6ZQFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFNWCJ236YINBIKUGXKTV6ZQFU/action/storage_attestation","attest_author":"https://pith.science/pith/SFNWCJ236YINBIKUGXKTV6ZQFU/action/author_attestation","sign_citation":"https://pith.science/pith/SFNWCJ236YINBIKUGXKTV6ZQFU/action/citation_signature","submit_replication":"https://pith.science/pith/SFNWCJ236YINBIKUGXKTV6ZQFU/action/replication_record"}},"created_at":"2026-07-05T00:25:34.216074+00:00","updated_at":"2026-07-05T00:25:34.216074+00:00"}