{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JTXKMJMQT75XRSSNQAH7VAMRRY","short_pith_number":"pith:JTXKMJMQ","schema_version":"1.0","canonical_sha256":"4ceea625909ffb78ca4d800ffa81918e30a2cbd668c0d0e338b8067531166622","source":{"kind":"arxiv","id":"2205.12593","version":2},"attestation_state":"computed","paper":{"title":"Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, HaiFeng Wang, Hua Wu, Jing Liu, Jing Yan, Qiaoqiao She, Sendong Zhao, Yan Chen, Yanrui Du","submitted_at":"2022-05-25T09:08:35Z","abstract_excerpt":"Recent research has revealed that deep neural networks often take dataset biases as a shortcut to make decisions rather than understand tasks, leading to failures in real-world applications. In this study, we focus on the spurious correlation between word features and labels that models learn from the biased data distribution of training data. In particular, we define the word highly co-occurring with a specific label as biased word, and the example containing biased word as biased example. Our analysis shows that biased examples are easier for models to learn, while at the time of prediction,"},"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":"2205.12593","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T09:08:35Z","cross_cats_sorted":[],"title_canon_sha256":"e67cd503467ebdd05cabec86c1a958e1fbfc726e28120d2a0d7a7ad13b445149","abstract_canon_sha256":"5ba314c17b029147bb6865aecfac239908b8b25740833545b1c2b07bc2969b1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:44.258906Z","signature_b64":"vu3blYPI+DDwYR7wJtzDMBU6++Ecxsc9pe3bY9nU5z5c2OB7IWrMieEhGqsTlSFNRxTxeXQkT/hGINH3jVBHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ceea625909ffb78ca4d800ffa81918e30a2cbd668c0d0e338b8067531166622","last_reissued_at":"2026-07-05T06:23:44.258417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:44.258417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, HaiFeng Wang, Hua Wu, Jing Liu, Jing Yan, Qiaoqiao She, Sendong Zhao, Yan Chen, Yanrui Du","submitted_at":"2022-05-25T09:08:35Z","abstract_excerpt":"Recent research has revealed that deep neural networks often take dataset biases as a shortcut to make decisions rather than understand tasks, leading to failures in real-world applications. In this study, we focus on the spurious correlation between word features and labels that models learn from the biased data distribution of training data. In particular, we define the word highly co-occurring with a specific label as biased word, and the example containing biased word as biased example. Our analysis shows that biased examples are easier for models to learn, while at the time of prediction,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12593","kind":"arxiv","version":2},"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/2205.12593/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":"2205.12593","created_at":"2026-07-05T06:23:44.258475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12593v2","created_at":"2026-07-05T06:23:44.258475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12593","created_at":"2026-07-05T06:23:44.258475+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTXKMJMQT75X","created_at":"2026-07-05T06:23:44.258475+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTXKMJMQT75XRSSN","created_at":"2026-07-05T06:23:44.258475+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTXKMJMQ","created_at":"2026-07-05T06:23:44.258475+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/JTXKMJMQT75XRSSNQAH7VAMRRY","json":"https://pith.science/pith/JTXKMJMQT75XRSSNQAH7VAMRRY.json","graph_json":"https://pith.science/api/pith-number/JTXKMJMQT75XRSSNQAH7VAMRRY/graph.json","events_json":"https://pith.science/api/pith-number/JTXKMJMQT75XRSSNQAH7VAMRRY/events.json","paper":"https://pith.science/paper/JTXKMJMQ"},"agent_actions":{"view_html":"https://pith.science/pith/JTXKMJMQT75XRSSNQAH7VAMRRY","download_json":"https://pith.science/pith/JTXKMJMQT75XRSSNQAH7VAMRRY.json","view_paper":"https://pith.science/paper/JTXKMJMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12593&json=true","fetch_graph":"https://pith.science/api/pith-number/JTXKMJMQT75XRSSNQAH7VAMRRY/graph.json","fetch_events":"https://pith.science/api/pith-number/JTXKMJMQT75XRSSNQAH7VAMRRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTXKMJMQT75XRSSNQAH7VAMRRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTXKMJMQT75XRSSNQAH7VAMRRY/action/storage_attestation","attest_author":"https://pith.science/pith/JTXKMJMQT75XRSSNQAH7VAMRRY/action/author_attestation","sign_citation":"https://pith.science/pith/JTXKMJMQT75XRSSNQAH7VAMRRY/action/citation_signature","submit_replication":"https://pith.science/pith/JTXKMJMQT75XRSSNQAH7VAMRRY/action/replication_record"}},"created_at":"2026-07-05T06:23:44.258475+00:00","updated_at":"2026-07-05T06:23:44.258475+00:00"}