{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EKH73JTPM5U4QVWT2W23L2GKB3","short_pith_number":"pith:EKH73JTP","schema_version":"1.0","canonical_sha256":"228ffda66f6769c856d3d5b5b5e8ca0ef704a7b24c962097b48bfe8e7757301c","source":{"kind":"arxiv","id":"2412.19018","version":4},"attestation_state":"computed","paper":{"title":"Let the Fuzzy Rule Speak: Enhancing In-context Learning Debiasing with Interpretability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ruixi Lin, Yang You","submitted_at":"2024-12-26T01:56:42Z","abstract_excerpt":"Large language models (LLMs) often struggle with balanced class accuracy in text classification tasks using in-context learning (ICL), hindering some practical uses due to user dissatisfaction or safety risks caused by misclassifications. Retraining LLMs to address root causes in data or model priors is neither easy nor cost-effective. This paper delves deeper into the class accuracy imbalance issue, identifying that it arises because certain classes consistently receive disproportionately high ICL probabilities, causing under-prediction and lower accuracy for others. More importantly, probabi"},"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":"2412.19018","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-26T01:56:42Z","cross_cats_sorted":[],"title_canon_sha256":"09e0c5cbf955206fcb2561762ebe8a684e87bc7adf577c79c681e394ada4bea8","abstract_canon_sha256":"86d36bafb4d28da3ed194a3f49730c8eb86e47bba9807b1d6364ac2f803d2205"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:24.601172Z","signature_b64":"/qPN/ut8jZUgXIteZNhoLN7qcITG1o/FhgJE+nZ1kgcbZ2uZSFoSy0OyXXMdBAgFLfkVdJ2m6Sa6cIyKc0SSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"228ffda66f6769c856d3d5b5b5e8ca0ef704a7b24c962097b48bfe8e7757301c","last_reissued_at":"2026-07-05T10:12:24.600726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:24.600726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Let the Fuzzy Rule Speak: Enhancing In-context Learning Debiasing with Interpretability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ruixi Lin, Yang You","submitted_at":"2024-12-26T01:56:42Z","abstract_excerpt":"Large language models (LLMs) often struggle with balanced class accuracy in text classification tasks using in-context learning (ICL), hindering some practical uses due to user dissatisfaction or safety risks caused by misclassifications. Retraining LLMs to address root causes in data or model priors is neither easy nor cost-effective. This paper delves deeper into the class accuracy imbalance issue, identifying that it arises because certain classes consistently receive disproportionately high ICL probabilities, causing under-prediction and lower accuracy for others. More importantly, probabi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19018","kind":"arxiv","version":4},"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/2412.19018/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":"2412.19018","created_at":"2026-07-05T10:12:24.600787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19018v4","created_at":"2026-07-05T10:12:24.600787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19018","created_at":"2026-07-05T10:12:24.600787+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKH73JTPM5U4","created_at":"2026-07-05T10:12:24.600787+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKH73JTPM5U4QVWT","created_at":"2026-07-05T10:12:24.600787+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKH73JTP","created_at":"2026-07-05T10:12:24.600787+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/EKH73JTPM5U4QVWT2W23L2GKB3","json":"https://pith.science/pith/EKH73JTPM5U4QVWT2W23L2GKB3.json","graph_json":"https://pith.science/api/pith-number/EKH73JTPM5U4QVWT2W23L2GKB3/graph.json","events_json":"https://pith.science/api/pith-number/EKH73JTPM5U4QVWT2W23L2GKB3/events.json","paper":"https://pith.science/paper/EKH73JTP"},"agent_actions":{"view_html":"https://pith.science/pith/EKH73JTPM5U4QVWT2W23L2GKB3","download_json":"https://pith.science/pith/EKH73JTPM5U4QVWT2W23L2GKB3.json","view_paper":"https://pith.science/paper/EKH73JTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19018&json=true","fetch_graph":"https://pith.science/api/pith-number/EKH73JTPM5U4QVWT2W23L2GKB3/graph.json","fetch_events":"https://pith.science/api/pith-number/EKH73JTPM5U4QVWT2W23L2GKB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKH73JTPM5U4QVWT2W23L2GKB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKH73JTPM5U4QVWT2W23L2GKB3/action/storage_attestation","attest_author":"https://pith.science/pith/EKH73JTPM5U4QVWT2W23L2GKB3/action/author_attestation","sign_citation":"https://pith.science/pith/EKH73JTPM5U4QVWT2W23L2GKB3/action/citation_signature","submit_replication":"https://pith.science/pith/EKH73JTPM5U4QVWT2W23L2GKB3/action/replication_record"}},"created_at":"2026-07-05T10:12:24.600787+00:00","updated_at":"2026-07-05T10:12:24.600787+00:00"}