{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7YVOF52MV33DW3JRMRKFDNJF2A","short_pith_number":"pith:7YVOF52M","schema_version":"1.0","canonical_sha256":"fe2ae2f74caef63b6d31645451b525d03a9e5297b604a1d7554c036c5f64f87c","source":{"kind":"arxiv","id":"2010.06351","version":4},"attestation_state":"computed","paper":{"title":"CAPT: Contrastive Pre-Training for Learning Denoised Sequence Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fuli Luo, Pengcheng Yang, Shicheng Li, Xuancheng Ren, Xu Sun","submitted_at":"2020-10-13T13:08:34Z","abstract_excerpt":"Pre-trained self-supervised models such as BERT have achieved striking success in learning sequence representations, especially for natural language processing. These models typically corrupt the given sequences with certain types of noise, such as masking, shuffling, or substitution, and then try to recover the original input. However, such pre-training approaches are prone to learning representations that are covariant with the noise, leading to the discrepancy between the pre-training and fine-tuning stage. To remedy this, we present ContrAstive Pre-Training (CAPT) to learn noise invariant "},"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":"2010.06351","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-13T13:08:34Z","cross_cats_sorted":[],"title_canon_sha256":"85e60186ab59d9d633be893fdc4f0c382fd39643e4a1126b2f72e0a3b76c649b","abstract_canon_sha256":"97885303538ae583c4c3b478858033f141f2c2611d0c65f1b4f95cb15908f4f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:45.918660Z","signature_b64":"hBAzfX8va3ELeNaHUSYf0zyD7speIj9CNuDe8NXwhIYhdkAqgCrSK4Clt9RgfMjhBGfYWc7ot1q0b6nMBUhvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe2ae2f74caef63b6d31645451b525d03a9e5297b604a1d7554c036c5f64f87c","last_reissued_at":"2026-07-05T01:47:45.918257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:45.918257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAPT: Contrastive Pre-Training for Learning Denoised Sequence Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fuli Luo, Pengcheng Yang, Shicheng Li, Xuancheng Ren, Xu Sun","submitted_at":"2020-10-13T13:08:34Z","abstract_excerpt":"Pre-trained self-supervised models such as BERT have achieved striking success in learning sequence representations, especially for natural language processing. These models typically corrupt the given sequences with certain types of noise, such as masking, shuffling, or substitution, and then try to recover the original input. However, such pre-training approaches are prone to learning representations that are covariant with the noise, leading to the discrepancy between the pre-training and fine-tuning stage. To remedy this, we present ContrAstive Pre-Training (CAPT) to learn noise invariant "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.06351","kind":"arxiv","version":4},"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/2010.06351/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":"2010.06351","created_at":"2026-07-05T01:47:45.918322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.06351v4","created_at":"2026-07-05T01:47:45.918322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.06351","created_at":"2026-07-05T01:47:45.918322+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YVOF52MV33D","created_at":"2026-07-05T01:47:45.918322+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YVOF52MV33DW3JR","created_at":"2026-07-05T01:47:45.918322+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YVOF52M","created_at":"2026-07-05T01:47:45.918322+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/7YVOF52MV33DW3JRMRKFDNJF2A","json":"https://pith.science/pith/7YVOF52MV33DW3JRMRKFDNJF2A.json","graph_json":"https://pith.science/api/pith-number/7YVOF52MV33DW3JRMRKFDNJF2A/graph.json","events_json":"https://pith.science/api/pith-number/7YVOF52MV33DW3JRMRKFDNJF2A/events.json","paper":"https://pith.science/paper/7YVOF52M"},"agent_actions":{"view_html":"https://pith.science/pith/7YVOF52MV33DW3JRMRKFDNJF2A","download_json":"https://pith.science/pith/7YVOF52MV33DW3JRMRKFDNJF2A.json","view_paper":"https://pith.science/paper/7YVOF52M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.06351&json=true","fetch_graph":"https://pith.science/api/pith-number/7YVOF52MV33DW3JRMRKFDNJF2A/graph.json","fetch_events":"https://pith.science/api/pith-number/7YVOF52MV33DW3JRMRKFDNJF2A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YVOF52MV33DW3JRMRKFDNJF2A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YVOF52MV33DW3JRMRKFDNJF2A/action/storage_attestation","attest_author":"https://pith.science/pith/7YVOF52MV33DW3JRMRKFDNJF2A/action/author_attestation","sign_citation":"https://pith.science/pith/7YVOF52MV33DW3JRMRKFDNJF2A/action/citation_signature","submit_replication":"https://pith.science/pith/7YVOF52MV33DW3JRMRKFDNJF2A/action/replication_record"}},"created_at":"2026-07-05T01:47:45.918322+00:00","updated_at":"2026-07-05T01:47:45.918322+00:00"}