{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PP5S4JVGGZLNZAE4FIRULFA4BK","short_pith_number":"pith:PP5S4JVG","schema_version":"1.0","canonical_sha256":"7bfb2e26a63656dc809c2a2345941c0aaf1e402ea276a483a7012c39afde6752","source":{"kind":"arxiv","id":"2208.08010","version":1},"attestation_state":"computed","paper":{"title":"ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.HC","authors_text":"Chunhui Sun, Furui Cheng, Huamin Qu, Qun Liu, Xingbo Wang, Zhihua Jin","submitted_at":"2022-08-17T01:24:55Z","abstract_excerpt":"Benchmark datasets play an important role in evaluating Natural Language Understanding (NLU) models. However, shortcuts -- unwanted biases in the benchmark datasets -- can damage the effectiveness of benchmark datasets in revealing models' real capabilities. Since shortcuts vary in coverage, productivity, and semantic meaning, it is challenging for NLU experts to systematically understand and avoid them when creating benchmark datasets. In this paper, we develop a visual analytics system, ShortcutLens, to help NLU experts explore shortcuts in NLU benchmark datasets. The system allows users to "},"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":"2208.08010","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2022-08-17T01:24:55Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"6ebc7dde4485f5e638a90e6b6b019338495dd1f62f1af99f11bf4ef469ceb56a","abstract_canon_sha256":"de736163f33d64d520b8cfb436af507cec038a84e159f3d9c7e6748d30616c70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:46.971473Z","signature_b64":"UAwSm60LeSQG0B75WIhdPa7X1YV3YM/ErB/9Sp0e/oChB7o/Te5/Ua4XeJegj77SPtf6VPbrKVp2BJzQkNi2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bfb2e26a63656dc809c2a2345941c0aaf1e402ea276a483a7012c39afde6752","last_reissued_at":"2026-07-05T05:32:46.971034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:46.971034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.HC","authors_text":"Chunhui Sun, Furui Cheng, Huamin Qu, Qun Liu, Xingbo Wang, Zhihua Jin","submitted_at":"2022-08-17T01:24:55Z","abstract_excerpt":"Benchmark datasets play an important role in evaluating Natural Language Understanding (NLU) models. However, shortcuts -- unwanted biases in the benchmark datasets -- can damage the effectiveness of benchmark datasets in revealing models' real capabilities. Since shortcuts vary in coverage, productivity, and semantic meaning, it is challenging for NLU experts to systematically understand and avoid them when creating benchmark datasets. In this paper, we develop a visual analytics system, ShortcutLens, to help NLU experts explore shortcuts in NLU benchmark datasets. The system allows users to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.08010","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/2208.08010/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":"2208.08010","created_at":"2026-07-05T05:32:46.971103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.08010v1","created_at":"2026-07-05T05:32:46.971103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.08010","created_at":"2026-07-05T05:32:46.971103+00:00"},{"alias_kind":"pith_short_12","alias_value":"PP5S4JVGGZLN","created_at":"2026-07-05T05:32:46.971103+00:00"},{"alias_kind":"pith_short_16","alias_value":"PP5S4JVGGZLNZAE4","created_at":"2026-07-05T05:32:46.971103+00:00"},{"alias_kind":"pith_short_8","alias_value":"PP5S4JVG","created_at":"2026-07-05T05:32:46.971103+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/PP5S4JVGGZLNZAE4FIRULFA4BK","json":"https://pith.science/pith/PP5S4JVGGZLNZAE4FIRULFA4BK.json","graph_json":"https://pith.science/api/pith-number/PP5S4JVGGZLNZAE4FIRULFA4BK/graph.json","events_json":"https://pith.science/api/pith-number/PP5S4JVGGZLNZAE4FIRULFA4BK/events.json","paper":"https://pith.science/paper/PP5S4JVG"},"agent_actions":{"view_html":"https://pith.science/pith/PP5S4JVGGZLNZAE4FIRULFA4BK","download_json":"https://pith.science/pith/PP5S4JVGGZLNZAE4FIRULFA4BK.json","view_paper":"https://pith.science/paper/PP5S4JVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.08010&json=true","fetch_graph":"https://pith.science/api/pith-number/PP5S4JVGGZLNZAE4FIRULFA4BK/graph.json","fetch_events":"https://pith.science/api/pith-number/PP5S4JVGGZLNZAE4FIRULFA4BK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PP5S4JVGGZLNZAE4FIRULFA4BK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PP5S4JVGGZLNZAE4FIRULFA4BK/action/storage_attestation","attest_author":"https://pith.science/pith/PP5S4JVGGZLNZAE4FIRULFA4BK/action/author_attestation","sign_citation":"https://pith.science/pith/PP5S4JVGGZLNZAE4FIRULFA4BK/action/citation_signature","submit_replication":"https://pith.science/pith/PP5S4JVGGZLNZAE4FIRULFA4BK/action/replication_record"}},"created_at":"2026-07-05T05:32:46.971103+00:00","updated_at":"2026-07-05T05:32:46.971103+00:00"}