{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:45QPBUBCFLRYJ5ETDHEWXHYMZ6","short_pith_number":"pith:45QPBUBC","schema_version":"1.0","canonical_sha256":"e760f0d0222ae384f49319c96b9f0ccf881aeafd44b2e38dd86ed4b2a9d1f224","source":{"kind":"arxiv","id":"2204.06758","version":1},"attestation_state":"computed","paper":{"title":"Multi-label topic classification for COVID-19 literature with Bioformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Kai Wang, Li Fang","submitted_at":"2022-04-14T05:24:54Z","abstract_excerpt":"We describe Bioformer team's participation in the multi-label topic classification task for COVID-19 literature (track 5 of BioCreative VII). Topic classification is performed using different BERT models (BioBERT, PubMedBERT, and Bioformer). We formulate the topic classification task as a sentence pair classification problem, where the title is the first sentence, and the abstract is the second sentence. Our results show that Bioformer outperforms BioBERT and PubMedBERT in this task. Compared to the baseline results, our best model increased micro, macro, and instance-based F1 score by 8.8%, 1"},"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":"2204.06758","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-14T05:24:54Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"6885efc1e441a1867c0ee0d6c109e42ccbe4921b42ef1c72e7248eaef07f1bf2","abstract_canon_sha256":"582e8f069cedb2fdd7d1b9e0108784eecb90ca260454b859659b05e8d9eeab41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:45.876101Z","signature_b64":"eqVxjl3f2nFkAesngFHbelRZuC0FXI33NEOuSgNG3WLzLnI1LQXsmVbP1MZ4xj7iJTFip2VnQ9L2w0Voc0EODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e760f0d0222ae384f49319c96b9f0ccf881aeafd44b2e38dd86ed4b2a9d1f224","last_reissued_at":"2026-07-05T04:14:45.875679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:45.875679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-label topic classification for COVID-19 literature with Bioformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Kai Wang, Li Fang","submitted_at":"2022-04-14T05:24:54Z","abstract_excerpt":"We describe Bioformer team's participation in the multi-label topic classification task for COVID-19 literature (track 5 of BioCreative VII). Topic classification is performed using different BERT models (BioBERT, PubMedBERT, and Bioformer). We formulate the topic classification task as a sentence pair classification problem, where the title is the first sentence, and the abstract is the second sentence. Our results show that Bioformer outperforms BioBERT and PubMedBERT in this task. Compared to the baseline results, our best model increased micro, macro, and instance-based F1 score by 8.8%, 1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06758","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/2204.06758/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":"2204.06758","created_at":"2026-07-05T04:14:45.875733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.06758v1","created_at":"2026-07-05T04:14:45.875733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06758","created_at":"2026-07-05T04:14:45.875733+00:00"},{"alias_kind":"pith_short_12","alias_value":"45QPBUBCFLRY","created_at":"2026-07-05T04:14:45.875733+00:00"},{"alias_kind":"pith_short_16","alias_value":"45QPBUBCFLRYJ5ET","created_at":"2026-07-05T04:14:45.875733+00:00"},{"alias_kind":"pith_short_8","alias_value":"45QPBUBC","created_at":"2026-07-05T04:14:45.875733+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/45QPBUBCFLRYJ5ETDHEWXHYMZ6","json":"https://pith.science/pith/45QPBUBCFLRYJ5ETDHEWXHYMZ6.json","graph_json":"https://pith.science/api/pith-number/45QPBUBCFLRYJ5ETDHEWXHYMZ6/graph.json","events_json":"https://pith.science/api/pith-number/45QPBUBCFLRYJ5ETDHEWXHYMZ6/events.json","paper":"https://pith.science/paper/45QPBUBC"},"agent_actions":{"view_html":"https://pith.science/pith/45QPBUBCFLRYJ5ETDHEWXHYMZ6","download_json":"https://pith.science/pith/45QPBUBCFLRYJ5ETDHEWXHYMZ6.json","view_paper":"https://pith.science/paper/45QPBUBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.06758&json=true","fetch_graph":"https://pith.science/api/pith-number/45QPBUBCFLRYJ5ETDHEWXHYMZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/45QPBUBCFLRYJ5ETDHEWXHYMZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45QPBUBCFLRYJ5ETDHEWXHYMZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45QPBUBCFLRYJ5ETDHEWXHYMZ6/action/storage_attestation","attest_author":"https://pith.science/pith/45QPBUBCFLRYJ5ETDHEWXHYMZ6/action/author_attestation","sign_citation":"https://pith.science/pith/45QPBUBCFLRYJ5ETDHEWXHYMZ6/action/citation_signature","submit_replication":"https://pith.science/pith/45QPBUBCFLRYJ5ETDHEWXHYMZ6/action/replication_record"}},"created_at":"2026-07-05T04:14:45.875733+00:00","updated_at":"2026-07-05T04:14:45.875733+00:00"}