{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LTYYWV7HUGW6V2XDFSMP2O4654","short_pith_number":"pith:LTYYWV7H","schema_version":"1.0","canonical_sha256":"5cf18b57e7a1adeaeae32c98fd3b9eef09596afec315f53d991ef69e07a9ff4d","source":{"kind":"arxiv","id":"1905.07504","version":2},"attestation_state":"computed","paper":{"title":"Story Ending Prediction by Transferable BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ting Liu, Xiao Ding, Zhongyang Li","submitted_at":"2019-05-17T23:52:08Z","abstract_excerpt":"Recent advances, such as GPT and BERT, have shown success in incorporating a pre-trained transformer language model and fine-tuning operation to improve downstream NLP systems. However, this framework still has some fundamental problems in effectively incorporating supervised knowledge from other related tasks. In this study, we investigate a transferable BERT (TransBERT) training framework, which can transfer not only general language knowledge from large-scale unlabeled data but also specific kinds of knowledge from various semantically related supervised tasks, for a target task. Particular"},"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":"1905.07504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-17T23:52:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e7e8f1eda0b6f6b25cfb3c6e89bc9ad68dddda0845371bf601be3a12975de4b2","abstract_canon_sha256":"6be32a1e1b5b6965424734388ec8169ba36fd2696912ac7ebf66c758a09a38c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:43.909159Z","signature_b64":"TkGhfqaOE1RG3e7eB4tkzPw1oWOzdvM9pDzNYOzW1yKY2iuyrmdsFIK2XFWNgNfoQnT7fs1R0m0c2Vyc8Xi2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cf18b57e7a1adeaeae32c98fd3b9eef09596afec315f53d991ef69e07a9ff4d","last_reissued_at":"2026-05-17T23:45:43.908657Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:43.908657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Story Ending Prediction by Transferable BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ting Liu, Xiao Ding, Zhongyang Li","submitted_at":"2019-05-17T23:52:08Z","abstract_excerpt":"Recent advances, such as GPT and BERT, have shown success in incorporating a pre-trained transformer language model and fine-tuning operation to improve downstream NLP systems. However, this framework still has some fundamental problems in effectively incorporating supervised knowledge from other related tasks. In this study, we investigate a transferable BERT (TransBERT) training framework, which can transfer not only general language knowledge from large-scale unlabeled data but also specific kinds of knowledge from various semantically related supervised tasks, for a target task. Particular"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07504","kind":"arxiv","version":2},"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":"1905.07504","created_at":"2026-05-17T23:45:43.908739+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.07504v2","created_at":"2026-05-17T23:45:43.908739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07504","created_at":"2026-05-17T23:45:43.908739+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTYYWV7HUGW6","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTYYWV7HUGW6V2XD","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTYYWV7H","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.02052","citing_title":"Patent Claim Generation by Fine-Tuning OpenAI GPT-2","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2005.14165","citing_title":"Language Models are Few-Shot Learners","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTYYWV7HUGW6V2XDFSMP2O4654","json":"https://pith.science/pith/LTYYWV7HUGW6V2XDFSMP2O4654.json","graph_json":"https://pith.science/api/pith-number/LTYYWV7HUGW6V2XDFSMP2O4654/graph.json","events_json":"https://pith.science/api/pith-number/LTYYWV7HUGW6V2XDFSMP2O4654/events.json","paper":"https://pith.science/paper/LTYYWV7H"},"agent_actions":{"view_html":"https://pith.science/pith/LTYYWV7HUGW6V2XDFSMP2O4654","download_json":"https://pith.science/pith/LTYYWV7HUGW6V2XDFSMP2O4654.json","view_paper":"https://pith.science/paper/LTYYWV7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.07504&json=true","fetch_graph":"https://pith.science/api/pith-number/LTYYWV7HUGW6V2XDFSMP2O4654/graph.json","fetch_events":"https://pith.science/api/pith-number/LTYYWV7HUGW6V2XDFSMP2O4654/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTYYWV7HUGW6V2XDFSMP2O4654/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTYYWV7HUGW6V2XDFSMP2O4654/action/storage_attestation","attest_author":"https://pith.science/pith/LTYYWV7HUGW6V2XDFSMP2O4654/action/author_attestation","sign_citation":"https://pith.science/pith/LTYYWV7HUGW6V2XDFSMP2O4654/action/citation_signature","submit_replication":"https://pith.science/pith/LTYYWV7HUGW6V2XDFSMP2O4654/action/replication_record"}},"created_at":"2026-05-17T23:45:43.908739+00:00","updated_at":"2026-05-17T23:45:43.908739+00:00"}