{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:S3FGFOCAUVS7336JBR3CDZLXSL","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":"277ef4fd57b5ea5791951322f18ff0f18a460e1da91966137c8e10c821ce82cf","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-11T19:39:56Z","title_canon_sha256":"2bace4d1414c41d1e8bb8da318e90791986a22e7c234211aec12c74d9eb3fc8f"},"schema_version":"1.0","source":{"id":"2103.06922","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.06922","created_at":"2026-07-05T02:32:04Z"},{"alias_kind":"arxiv_version","alias_value":"2103.06922v3","created_at":"2026-07-05T02:32:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06922","created_at":"2026-07-05T02:32:04Z"},{"alias_kind":"pith_short_12","alias_value":"S3FGFOCAUVS7","created_at":"2026-07-05T02:32:04Z"},{"alias_kind":"pith_short_16","alias_value":"S3FGFOCAUVS7336J","created_at":"2026-07-05T02:32:04Z"},{"alias_kind":"pith_short_8","alias_value":"S3FGFOCA","created_at":"2026-07-05T02:32:04Z"}],"graph_snapshots":[{"event_id":"sha256:5b609e4bd6cb54eec28b686ab04b21cb0771961a63aa8e72f7f5e0fb90efcb48","target":"graph","created_at":"2026-07-05T02:32:04Z","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/2103.06922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies indicate that NLU models are prone to rely on shortcut features for prediction, without achieving true language understanding. As a result, these models fail to generalize to real-world out-of-distribution data. In this work, we show that the words in the NLU training set can be modeled as a long-tailed distribution. There are two findings: 1) NLU models have strong preference for features located at the head of the long-tailed distribution, and 2) Shortcut features are picked up during very early few iterations of the model training. These two observations are further employed ","authors_text":"Franck Dernoncourt, Jiuxiang Gu, Mengnan Du, Rajiv Jain, Ruchi Deshpande, Tong Sun, Varun Manjunatha, Xia Hu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-11T19:39:56Z","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06922","kind":"arxiv","version":3},"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:aee250d9b6fcd7ceb137cce1ea2c8f4a1253ee12399dc1097befbb0751b825ab","target":"record","created_at":"2026-07-05T02:32:04Z","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":"277ef4fd57b5ea5791951322f18ff0f18a460e1da91966137c8e10c821ce82cf","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-11T19:39:56Z","title_canon_sha256":"2bace4d1414c41d1e8bb8da318e90791986a22e7c234211aec12c74d9eb3fc8f"},"schema_version":"1.0","source":{"id":"2103.06922","kind":"arxiv","version":3}},"canonical_sha256":"96ca62b840a565fdefc90c7621e57792f0d5082f245145bf61b91a27065895b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96ca62b840a565fdefc90c7621e57792f0d5082f245145bf61b91a27065895b2","first_computed_at":"2026-07-05T02:32:04.559556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:04.559556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kB6iAyeINRtkBG0fyZ04JT1jgrW0KM1R4uGtGD1eaz/s83S072X8A+bMS2oF8uiXJME7AWfgF+Qcn+o0iLG+BA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:04.560051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.06922","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aee250d9b6fcd7ceb137cce1ea2c8f4a1253ee12399dc1097befbb0751b825ab","sha256:5b609e4bd6cb54eec28b686ab04b21cb0771961a63aa8e72f7f5e0fb90efcb48"],"state_sha256":"7343b136a770d0005ba539627c83b01ff9c428810276d2c5006d35a8a1bcc534"}