{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GJD2OMXENECLSOQCJNKUQJUUTN","short_pith_number":"pith:GJD2OMXE","canonical_record":{"source":{"id":"2210.04675","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-10T13:26:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"13e41ebb3cbbf673394e0f1fbd9c1d0f74c20826c03b45dd9ef13678c8ad28c8","abstract_canon_sha256":"0e106faf7d3ea8a24ed58975a8ee890ad6d94d3ce480eb1bda8c5016e4f9be7c"},"schema_version":"1.0"},"canonical_sha256":"3247a732e46904b93a024b554826949b565372f7277e80aee6542bcd87aecebf","source":{"kind":"arxiv","id":"2210.04675","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04675","created_at":"2026-07-05T05:44:38Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04675v2","created_at":"2026-07-05T05:44:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04675","created_at":"2026-07-05T05:44:38Z"},{"alias_kind":"pith_short_12","alias_value":"GJD2OMXENECL","created_at":"2026-07-05T05:44:38Z"},{"alias_kind":"pith_short_16","alias_value":"GJD2OMXENECLSOQC","created_at":"2026-07-05T05:44:38Z"},{"alias_kind":"pith_short_8","alias_value":"GJD2OMXE","created_at":"2026-07-05T05:44:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GJD2OMXENECLSOQCJNKUQJUUTN","target":"record","payload":{"canonical_record":{"source":{"id":"2210.04675","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-10T13:26:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"13e41ebb3cbbf673394e0f1fbd9c1d0f74c20826c03b45dd9ef13678c8ad28c8","abstract_canon_sha256":"0e106faf7d3ea8a24ed58975a8ee890ad6d94d3ce480eb1bda8c5016e4f9be7c"},"schema_version":"1.0"},"canonical_sha256":"3247a732e46904b93a024b554826949b565372f7277e80aee6542bcd87aecebf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:38.976097Z","signature_b64":"R3oxGzfIKfXWHhNDUzzm9bSgMcipT/lTIJSS3sgsAWANfZ/sI3YuDuWULed+P0z8PJTJk+HuxDU2zRnfmBpRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3247a732e46904b93a024b554826949b565372f7277e80aee6542bcd87aecebf","last_reissued_at":"2026-07-05T05:44:38.975665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:38.975665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.04675","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:44:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MTpSISPTTRoRYKesxGnLowdh6+gEeGp7gXR2wtZsUkI0wMcpGPKZV/RFxW52YbN0YPyD1tGmJAJ1DQasPYAPCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T10:04:25.641516Z"},"content_sha256":"90f549856ec78c58e1a775ae88cd73484356c67957519748f1939fe99791161f","schema_version":"1.0","event_id":"sha256:90f549856ec78c58e1a775ae88cd73484356c67957519748f1939fe99791161f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GJD2OMXENECLSOQCJNKUQJUUTN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Fraser, Annemarie Friedrich, Sophie Henning, William Beluch","submitted_at":"2022-10-10T13:26:40Z","abstract_excerpt":"Many natural language processing (NLP) tasks are naturally imbalanced, as some target categories occur much more frequently than others in the real world. In such scenarios, current NLP models still tend to perform poorly on less frequent classes. Addressing class imbalance in NLP is an active research topic, yet, finding a good approach for a particular task and imbalance scenario is difficult.\n  With this survey, the first overview on class imbalance in deep-learning based NLP, we provide guidance for NLP researchers and practitioners dealing with imbalanced data. We first discuss various ty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04675","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/2210.04675/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:44:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qe9Iz5CUGO2BvsiK65AMVORXhHDxIhdRTg3pGjdfmCG7C7EKMgddjtvUK0I1cMsqXZuVmpj1e0rnORIlw0NJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T10:04:25.641876Z"},"content_sha256":"0b46514b5e7cb5f8e00a585738615e67d0365da58b87096b6fe2902c5abb8073","schema_version":"1.0","event_id":"sha256:0b46514b5e7cb5f8e00a585738615e67d0365da58b87096b6fe2902c5abb8073"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GJD2OMXENECLSOQCJNKUQJUUTN/bundle.json","state_url":"https://pith.science/pith/GJD2OMXENECLSOQCJNKUQJUUTN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GJD2OMXENECLSOQCJNKUQJUUTN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-17T10:04:25Z","links":{"resolver":"https://pith.science/pith/GJD2OMXENECLSOQCJNKUQJUUTN","bundle":"https://pith.science/pith/GJD2OMXENECLSOQCJNKUQJUUTN/bundle.json","state":"https://pith.science/pith/GJD2OMXENECLSOQCJNKUQJUUTN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GJD2OMXENECLSOQCJNKUQJUUTN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GJD2OMXENECLSOQCJNKUQJUUTN","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":"0e106faf7d3ea8a24ed58975a8ee890ad6d94d3ce480eb1bda8c5016e4f9be7c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-10T13:26:40Z","title_canon_sha256":"13e41ebb3cbbf673394e0f1fbd9c1d0f74c20826c03b45dd9ef13678c8ad28c8"},"schema_version":"1.0","source":{"id":"2210.04675","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04675","created_at":"2026-07-05T05:44:38Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04675v2","created_at":"2026-07-05T05:44:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04675","created_at":"2026-07-05T05:44:38Z"},{"alias_kind":"pith_short_12","alias_value":"GJD2OMXENECL","created_at":"2026-07-05T05:44:38Z"},{"alias_kind":"pith_short_16","alias_value":"GJD2OMXENECLSOQC","created_at":"2026-07-05T05:44:38Z"},{"alias_kind":"pith_short_8","alias_value":"GJD2OMXE","created_at":"2026-07-05T05:44:38Z"}],"graph_snapshots":[{"event_id":"sha256:0b46514b5e7cb5f8e00a585738615e67d0365da58b87096b6fe2902c5abb8073","target":"graph","created_at":"2026-07-05T05:44:38Z","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/2210.04675/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many natural language processing (NLP) tasks are naturally imbalanced, as some target categories occur much more frequently than others in the real world. In such scenarios, current NLP models still tend to perform poorly on less frequent classes. Addressing class imbalance in NLP is an active research topic, yet, finding a good approach for a particular task and imbalance scenario is difficult.\n  With this survey, the first overview on class imbalance in deep-learning based NLP, we provide guidance for NLP researchers and practitioners dealing with imbalanced data. We first discuss various ty","authors_text":"Alexander Fraser, Annemarie Friedrich, Sophie Henning, William Beluch","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-10T13:26:40Z","title":"A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04675","kind":"arxiv","version":2},"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":"sha256:90f549856ec78c58e1a775ae88cd73484356c67957519748f1939fe99791161f","target":"record","created_at":"2026-07-05T05:44:38Z","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":"0e106faf7d3ea8a24ed58975a8ee890ad6d94d3ce480eb1bda8c5016e4f9be7c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-10T13:26:40Z","title_canon_sha256":"13e41ebb3cbbf673394e0f1fbd9c1d0f74c20826c03b45dd9ef13678c8ad28c8"},"schema_version":"1.0","source":{"id":"2210.04675","kind":"arxiv","version":2}},"canonical_sha256":"3247a732e46904b93a024b554826949b565372f7277e80aee6542bcd87aecebf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3247a732e46904b93a024b554826949b565372f7277e80aee6542bcd87aecebf","first_computed_at":"2026-07-05T05:44:38.975665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:44:38.975665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R3oxGzfIKfXWHhNDUzzm9bSgMcipT/lTIJSS3sgsAWANfZ/sI3YuDuWULed+P0z8PJTJk+HuxDU2zRnfmBpRCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:44:38.976097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04675","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90f549856ec78c58e1a775ae88cd73484356c67957519748f1939fe99791161f","sha256:0b46514b5e7cb5f8e00a585738615e67d0365da58b87096b6fe2902c5abb8073"],"state_sha256":"131462be7c2646650f97d09b47d6d31752e4eb69bd059eb192cbca688d376a2d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"00m+gC+hjgfbpPv+zeDHiTuQ6Y/JcwL2VhhTS8iSNPwLHoMKC7pKMnuQjVWkoF4Kbh4DiYjWR8x6sdt5lWWxDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T10:04:25.643977Z","bundle_sha256":"ddcbc1cdd3add75c38bf8dce107464084f75b974ad895c3b90c3eeab1401d568"}}