{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YMB2JT22FY3CKVTKF4FGL6F6UU","short_pith_number":"pith:YMB2JT22","schema_version":"1.0","canonical_sha256":"c303a4cf5a2e3625566a2f0a65f8bea50a99de5bcd93861bc5009a224a615a8f","source":{"kind":"arxiv","id":"2107.07113","version":1},"attestation_state":"computed","paper":{"title":"Robust Learning for Text Classification with Multi-source Noise Simulation and Hard Example Mining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guowei Xu, Weiping Fu, Wenbiao Ding, Zhongqin Wu, Zitao Liu","submitted_at":"2021-07-15T04:39:22Z","abstract_excerpt":"Many real-world applications involve the use of Optical Character Recognition (OCR) engines to transform handwritten images into transcripts on which downstream Natural Language Processing (NLP) models are applied. In this process, OCR engines may introduce errors and inputs to downstream NLP models become noisy. Despite that pre-trained models achieve state-of-the-art performance in many NLP benchmarks, we prove that they are not robust to noisy texts generated by real OCR engines. This greatly limits the application of NLP models in real-world scenarios. In order to improve model performance"},"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":"2107.07113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-15T04:39:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a98defc85064a3a8cba34ba75a813f1e5541a08a5139ace28604e77c8d5ab0e8","abstract_canon_sha256":"704fe69fcdc1c51bcec7e34ef88b32a7130aa3ac145974aff26eba48a2aa6f11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:10.868439Z","signature_b64":"Adm1G1QtoGWEGc/XP3o5FVRvhslE4JSmSqUYxc6RNzgts9D5DA73OjLQ6cc4MI1+smQRYmN/DjzUflSXL/tJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c303a4cf5a2e3625566a2f0a65f8bea50a99de5bcd93861bc5009a224a615a8f","last_reissued_at":"2026-07-05T02:58:10.868017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:10.868017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Learning for Text Classification with Multi-source Noise Simulation and Hard Example Mining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guowei Xu, Weiping Fu, Wenbiao Ding, Zhongqin Wu, Zitao Liu","submitted_at":"2021-07-15T04:39:22Z","abstract_excerpt":"Many real-world applications involve the use of Optical Character Recognition (OCR) engines to transform handwritten images into transcripts on which downstream Natural Language Processing (NLP) models are applied. In this process, OCR engines may introduce errors and inputs to downstream NLP models become noisy. Despite that pre-trained models achieve state-of-the-art performance in many NLP benchmarks, we prove that they are not robust to noisy texts generated by real OCR engines. This greatly limits the application of NLP models in real-world scenarios. In order to improve model performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07113","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/2107.07113/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":"2107.07113","created_at":"2026-07-05T02:58:10.868080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.07113v1","created_at":"2026-07-05T02:58:10.868080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07113","created_at":"2026-07-05T02:58:10.868080+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMB2JT22FY3C","created_at":"2026-07-05T02:58:10.868080+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMB2JT22FY3CKVTK","created_at":"2026-07-05T02:58:10.868080+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMB2JT22","created_at":"2026-07-05T02:58:10.868080+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/YMB2JT22FY3CKVTKF4FGL6F6UU","json":"https://pith.science/pith/YMB2JT22FY3CKVTKF4FGL6F6UU.json","graph_json":"https://pith.science/api/pith-number/YMB2JT22FY3CKVTKF4FGL6F6UU/graph.json","events_json":"https://pith.science/api/pith-number/YMB2JT22FY3CKVTKF4FGL6F6UU/events.json","paper":"https://pith.science/paper/YMB2JT22"},"agent_actions":{"view_html":"https://pith.science/pith/YMB2JT22FY3CKVTKF4FGL6F6UU","download_json":"https://pith.science/pith/YMB2JT22FY3CKVTKF4FGL6F6UU.json","view_paper":"https://pith.science/paper/YMB2JT22","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.07113&json=true","fetch_graph":"https://pith.science/api/pith-number/YMB2JT22FY3CKVTKF4FGL6F6UU/graph.json","fetch_events":"https://pith.science/api/pith-number/YMB2JT22FY3CKVTKF4FGL6F6UU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMB2JT22FY3CKVTKF4FGL6F6UU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMB2JT22FY3CKVTKF4FGL6F6UU/action/storage_attestation","attest_author":"https://pith.science/pith/YMB2JT22FY3CKVTKF4FGL6F6UU/action/author_attestation","sign_citation":"https://pith.science/pith/YMB2JT22FY3CKVTKF4FGL6F6UU/action/citation_signature","submit_replication":"https://pith.science/pith/YMB2JT22FY3CKVTKF4FGL6F6UU/action/replication_record"}},"created_at":"2026-07-05T02:58:10.868080+00:00","updated_at":"2026-07-05T02:58:10.868080+00:00"}