{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YG3TYSW7TAIF3ATMUEIXW55VNJ","short_pith_number":"pith:YG3TYSW7","schema_version":"1.0","canonical_sha256":"c1b73c4adf98105d826ca1117b77b56a6e7e83df4ed66f5ac0df2671b00cce81","source":{"kind":"arxiv","id":"2101.00389","version":1},"attestation_state":"computed","paper":{"title":"Multitask Learning for Class-Imbalanced Discourse Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Spangher, Jonathan May, Lingjia Deng, Sz-rung Shiang","submitted_at":"2021-01-02T07:13:41Z","abstract_excerpt":"Small class-imbalanced datasets, common in many high-level semantic tasks like discourse analysis, present a particular challenge to current deep-learning architectures. In this work, we perform an extensive analysis on sentence-level classification approaches for the News Discourse dataset, one of the largest high-level semantic discourse datasets recently published. We show that a multitask approach can improve 7% Micro F1-score upon current state-of-the-art benchmarks, due in part to label corrections across tasks, which improve performance for underrepresented classes. We also offer a comp"},"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":"2101.00389","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T07:13:41Z","cross_cats_sorted":[],"title_canon_sha256":"fe35f51fdf18c5d088d57a6d54f715fab7992bee6c30133c60140a6b827d049b","abstract_canon_sha256":"d8aaf9c382e6b1d079b0ba6f1cebe4471bcc2a6d3e7fcf8343a69996555eb066"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:04:18.030113Z","signature_b64":"PHk89bWueEcP6znTmTKZY/Qp7Sds8t4dgg+B3tvUDYZO4Op2idrajwVbRuit8C9bJFQv//Gi5dH+Q1gt+lnsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1b73c4adf98105d826ca1117b77b56a6e7e83df4ed66f5ac0df2671b00cce81","last_reissued_at":"2026-07-05T02:04:18.029725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:04:18.029725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multitask Learning for Class-Imbalanced Discourse Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Spangher, Jonathan May, Lingjia Deng, Sz-rung Shiang","submitted_at":"2021-01-02T07:13:41Z","abstract_excerpt":"Small class-imbalanced datasets, common in many high-level semantic tasks like discourse analysis, present a particular challenge to current deep-learning architectures. In this work, we perform an extensive analysis on sentence-level classification approaches for the News Discourse dataset, one of the largest high-level semantic discourse datasets recently published. We show that a multitask approach can improve 7% Micro F1-score upon current state-of-the-art benchmarks, due in part to label corrections across tasks, which improve performance for underrepresented classes. We also offer a comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00389","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/2101.00389/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":"2101.00389","created_at":"2026-07-05T02:04:18.029779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.00389v1","created_at":"2026-07-05T02:04:18.029779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00389","created_at":"2026-07-05T02:04:18.029779+00:00"},{"alias_kind":"pith_short_12","alias_value":"YG3TYSW7TAIF","created_at":"2026-07-05T02:04:18.029779+00:00"},{"alias_kind":"pith_short_16","alias_value":"YG3TYSW7TAIF3ATM","created_at":"2026-07-05T02:04:18.029779+00:00"},{"alias_kind":"pith_short_8","alias_value":"YG3TYSW7","created_at":"2026-07-05T02:04:18.029779+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/YG3TYSW7TAIF3ATMUEIXW55VNJ","json":"https://pith.science/pith/YG3TYSW7TAIF3ATMUEIXW55VNJ.json","graph_json":"https://pith.science/api/pith-number/YG3TYSW7TAIF3ATMUEIXW55VNJ/graph.json","events_json":"https://pith.science/api/pith-number/YG3TYSW7TAIF3ATMUEIXW55VNJ/events.json","paper":"https://pith.science/paper/YG3TYSW7"},"agent_actions":{"view_html":"https://pith.science/pith/YG3TYSW7TAIF3ATMUEIXW55VNJ","download_json":"https://pith.science/pith/YG3TYSW7TAIF3ATMUEIXW55VNJ.json","view_paper":"https://pith.science/paper/YG3TYSW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.00389&json=true","fetch_graph":"https://pith.science/api/pith-number/YG3TYSW7TAIF3ATMUEIXW55VNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YG3TYSW7TAIF3ATMUEIXW55VNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YG3TYSW7TAIF3ATMUEIXW55VNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YG3TYSW7TAIF3ATMUEIXW55VNJ/action/storage_attestation","attest_author":"https://pith.science/pith/YG3TYSW7TAIF3ATMUEIXW55VNJ/action/author_attestation","sign_citation":"https://pith.science/pith/YG3TYSW7TAIF3ATMUEIXW55VNJ/action/citation_signature","submit_replication":"https://pith.science/pith/YG3TYSW7TAIF3ATMUEIXW55VNJ/action/replication_record"}},"created_at":"2026-07-05T02:04:18.029779+00:00","updated_at":"2026-07-05T02:04:18.029779+00:00"}