{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VQX6BF2IRGLINQH52PZBOHNN6I","short_pith_number":"pith:VQX6BF2I","schema_version":"1.0","canonical_sha256":"ac2fe09748899686c0fdd3f2171dadf215e98dde77f0be20c49df1b86e99a807","source":{"kind":"arxiv","id":"2209.05741","version":2},"attestation_state":"computed","paper":{"title":"SkIn: Skimming-Intensive Long-Text Classification Using BERT for Medical Corpus","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haiying Che, Yufeng Zhao","submitted_at":"2022-09-13T05:49:10Z","abstract_excerpt":"BERT is a widely used pre-trained model in natural language processing. However, since BERT is quadratic to the text length, the BERT model is difficult to be used directly on the long-text corpus. In some fields, the collected text data may be quite long, such as in the health care field. Therefore, to apply the pre-trained language knowledge of BERT to long text, in this paper, imitating the skimming-intensive reading method used by humans when reading a long paragraph, the Skimming-Intensive Model (SkIn) is proposed. It can dynamically select the critical information in the text so that the"},"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":"2209.05741","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-13T05:49:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa895fb3e4787e3a8225d75b441f2b818fb01ac34382478fd2556ca7e3233afd","abstract_canon_sha256":"0c9fe72d49d39e54b055db7b9cd8352b9b0e2fe18b92e743f8f4b174623a3d5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:45.449593Z","signature_b64":"zgJeWB32iKkEs7AezaEFe//PKe5Gf87J0dSQ/J0wF+edJoPmJ1H86MZsKWbV4MJnpDqkZdnjskSJQHjomWOrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac2fe09748899686c0fdd3f2171dadf215e98dde77f0be20c49df1b86e99a807","last_reissued_at":"2026-07-05T05:00:45.449099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:45.449099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkIn: Skimming-Intensive Long-Text Classification Using BERT for Medical Corpus","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haiying Che, Yufeng Zhao","submitted_at":"2022-09-13T05:49:10Z","abstract_excerpt":"BERT is a widely used pre-trained model in natural language processing. However, since BERT is quadratic to the text length, the BERT model is difficult to be used directly on the long-text corpus. In some fields, the collected text data may be quite long, such as in the health care field. Therefore, to apply the pre-trained language knowledge of BERT to long text, in this paper, imitating the skimming-intensive reading method used by humans when reading a long paragraph, the Skimming-Intensive Model (SkIn) is proposed. It can dynamically select the critical information in the text so that the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.05741","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.05741/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":"2209.05741","created_at":"2026-07-05T05:00:45.449160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.05741v2","created_at":"2026-07-05T05:00:45.449160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.05741","created_at":"2026-07-05T05:00:45.449160+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQX6BF2IRGLI","created_at":"2026-07-05T05:00:45.449160+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQX6BF2IRGLINQH5","created_at":"2026-07-05T05:00:45.449160+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQX6BF2I","created_at":"2026-07-05T05:00:45.449160+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/VQX6BF2IRGLINQH52PZBOHNN6I","json":"https://pith.science/pith/VQX6BF2IRGLINQH52PZBOHNN6I.json","graph_json":"https://pith.science/api/pith-number/VQX6BF2IRGLINQH52PZBOHNN6I/graph.json","events_json":"https://pith.science/api/pith-number/VQX6BF2IRGLINQH52PZBOHNN6I/events.json","paper":"https://pith.science/paper/VQX6BF2I"},"agent_actions":{"view_html":"https://pith.science/pith/VQX6BF2IRGLINQH52PZBOHNN6I","download_json":"https://pith.science/pith/VQX6BF2IRGLINQH52PZBOHNN6I.json","view_paper":"https://pith.science/paper/VQX6BF2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.05741&json=true","fetch_graph":"https://pith.science/api/pith-number/VQX6BF2IRGLINQH52PZBOHNN6I/graph.json","fetch_events":"https://pith.science/api/pith-number/VQX6BF2IRGLINQH52PZBOHNN6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQX6BF2IRGLINQH52PZBOHNN6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQX6BF2IRGLINQH52PZBOHNN6I/action/storage_attestation","attest_author":"https://pith.science/pith/VQX6BF2IRGLINQH52PZBOHNN6I/action/author_attestation","sign_citation":"https://pith.science/pith/VQX6BF2IRGLINQH52PZBOHNN6I/action/citation_signature","submit_replication":"https://pith.science/pith/VQX6BF2IRGLINQH52PZBOHNN6I/action/replication_record"}},"created_at":"2026-07-05T05:00:45.449160+00:00","updated_at":"2026-07-05T05:00:45.449160+00:00"}