{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3S3ARMOV5MOASUK2N7Z6LI4VC6","short_pith_number":"pith:3S3ARMOV","schema_version":"1.0","canonical_sha256":"dcb608b1d5eb1c09515a6ff3e5a3951795c2781690ec1f090da3969cee2ba901","source":{"kind":"arxiv","id":"2004.08097","version":1},"attestation_state":"computed","paper":{"title":"Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Joongbo Shin, Kyomin Jung, Seunghyun Yoon, Yoonhyung Lee","submitted_at":"2020-04-17T07:43:38Z","abstract_excerpt":"Even though BERT achieves successful performance improvements in various supervised learning tasks, applying BERT for unsupervised tasks still holds a limitation that it requires repetitive inference for computing contextual language representations. To resolve the limitation, we propose a novel deep bidirectional language model called Transformer-based Text Autoencoder (T-TA). The T-TA computes contextual language representations without repetition and has benefits of the deep bidirectional architecture like BERT. In run-time experiments on CPU environments, the proposed T-TA performs over si"},"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":"2004.08097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-17T07:43:38Z","cross_cats_sorted":[],"title_canon_sha256":"c7c92b6396cca6fbae9855bd23ef840fdc558fe3c0ad4dac7ec212600bd98f43","abstract_canon_sha256":"659943717eb706dc0318d015e1b8a125c16c07205ae6072a1e58874b253b6de3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:55:50.122900Z","signature_b64":"g1DCD/YzEuUXByXcHtRS6YGScXft6fHqR26Psdph9Gk9FXH/nd/DOqXVs45f5QZA9S/mXtweBO3Mv1TlcjoLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcb608b1d5eb1c09515a6ff3e5a3951795c2781690ec1f090da3969cee2ba901","last_reissued_at":"2026-07-05T00:55:50.122472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:55:50.122472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Joongbo Shin, Kyomin Jung, Seunghyun Yoon, Yoonhyung Lee","submitted_at":"2020-04-17T07:43:38Z","abstract_excerpt":"Even though BERT achieves successful performance improvements in various supervised learning tasks, applying BERT for unsupervised tasks still holds a limitation that it requires repetitive inference for computing contextual language representations. To resolve the limitation, we propose a novel deep bidirectional language model called Transformer-based Text Autoencoder (T-TA). The T-TA computes contextual language representations without repetition and has benefits of the deep bidirectional architecture like BERT. In run-time experiments on CPU environments, the proposed T-TA performs over si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.08097","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/2004.08097/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":"2004.08097","created_at":"2026-07-05T00:55:50.122532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.08097v1","created_at":"2026-07-05T00:55:50.122532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.08097","created_at":"2026-07-05T00:55:50.122532+00:00"},{"alias_kind":"pith_short_12","alias_value":"3S3ARMOV5MOA","created_at":"2026-07-05T00:55:50.122532+00:00"},{"alias_kind":"pith_short_16","alias_value":"3S3ARMOV5MOASUK2","created_at":"2026-07-05T00:55:50.122532+00:00"},{"alias_kind":"pith_short_8","alias_value":"3S3ARMOV","created_at":"2026-07-05T00:55:50.122532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13397","citing_title":"ExLM: Rethinking the Impact of [MASK] Tokens in Masked Language Models","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3S3ARMOV5MOASUK2N7Z6LI4VC6","json":"https://pith.science/pith/3S3ARMOV5MOASUK2N7Z6LI4VC6.json","graph_json":"https://pith.science/api/pith-number/3S3ARMOV5MOASUK2N7Z6LI4VC6/graph.json","events_json":"https://pith.science/api/pith-number/3S3ARMOV5MOASUK2N7Z6LI4VC6/events.json","paper":"https://pith.science/paper/3S3ARMOV"},"agent_actions":{"view_html":"https://pith.science/pith/3S3ARMOV5MOASUK2N7Z6LI4VC6","download_json":"https://pith.science/pith/3S3ARMOV5MOASUK2N7Z6LI4VC6.json","view_paper":"https://pith.science/paper/3S3ARMOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.08097&json=true","fetch_graph":"https://pith.science/api/pith-number/3S3ARMOV5MOASUK2N7Z6LI4VC6/graph.json","fetch_events":"https://pith.science/api/pith-number/3S3ARMOV5MOASUK2N7Z6LI4VC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3S3ARMOV5MOASUK2N7Z6LI4VC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3S3ARMOV5MOASUK2N7Z6LI4VC6/action/storage_attestation","attest_author":"https://pith.science/pith/3S3ARMOV5MOASUK2N7Z6LI4VC6/action/author_attestation","sign_citation":"https://pith.science/pith/3S3ARMOV5MOASUK2N7Z6LI4VC6/action/citation_signature","submit_replication":"https://pith.science/pith/3S3ARMOV5MOASUK2N7Z6LI4VC6/action/replication_record"}},"created_at":"2026-07-05T00:55:50.122532+00:00","updated_at":"2026-07-05T00:55:50.122532+00:00"}