{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YG3TYSW7TAIF3ATMUEIXW55VNJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d8aaf9c382e6b1d079b0ba6f1cebe4471bcc2a6d3e7fcf8343a69996555eb066","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T07:13:41Z","title_canon_sha256":"fe35f51fdf18c5d088d57a6d54f715fab7992bee6c30133c60140a6b827d049b"},"schema_version":"1.0","source":{"id":"2101.00389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.00389","created_at":"2026-07-05T02:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2101.00389v1","created_at":"2026-07-05T02:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00389","created_at":"2026-07-05T02:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"YG3TYSW7TAIF","created_at":"2026-07-05T02:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"YG3TYSW7TAIF3ATM","created_at":"2026-07-05T02:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"YG3TYSW7","created_at":"2026-07-05T02:04:18Z"}],"graph_snapshots":[{"event_id":"sha256:1d4118877f712af20cf473177ae7092c64cb53057f612c06c67563b7fbc39a54","target":"graph","created_at":"2026-07-05T02:04:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2101.00389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Spangher, Jonathan May, Lingjia Deng, Sz-rung Shiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T07:13:41Z","title":"Multitask Learning for Class-Imbalanced Discourse Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00389","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:30fe0736db8c2235fc7e5a3596aa14ed40ab627ffcfd1e7942dc2f44621c59fc","target":"record","created_at":"2026-07-05T02:04:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d8aaf9c382e6b1d079b0ba6f1cebe4471bcc2a6d3e7fcf8343a69996555eb066","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T07:13:41Z","title_canon_sha256":"fe35f51fdf18c5d088d57a6d54f715fab7992bee6c30133c60140a6b827d049b"},"schema_version":"1.0","source":{"id":"2101.00389","kind":"arxiv","version":1}},"canonical_sha256":"c1b73c4adf98105d826ca1117b77b56a6e7e83df4ed66f5ac0df2671b00cce81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1b73c4adf98105d826ca1117b77b56a6e7e83df4ed66f5ac0df2671b00cce81","first_computed_at":"2026-07-05T02:04:18.029725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:04:18.029725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PHk89bWueEcP6znTmTKZY/Qp7Sds8t4dgg+B3tvUDYZO4Op2idrajwVbRuit8C9bJFQv//Gi5dH+Q1gt+lnsBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:04:18.030113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.00389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30fe0736db8c2235fc7e5a3596aa14ed40ab627ffcfd1e7942dc2f44621c59fc","sha256:1d4118877f712af20cf473177ae7092c64cb53057f612c06c67563b7fbc39a54"],"state_sha256":"72f7f2f585f44f13999ecb373dfd5324d57eb2d8a47b42c56d0bb93fa8d543ce"}