{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KRYG4KNUIQX65MBLWG2UDV6PYQ","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":"883653714a3ba6fbada660e8732396570f618ee1dcc6b2cd15103c913ca25b87","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-10T02:35:34Z","title_canon_sha256":"ecfb8dea43970515837e140d76abf44e87af521c10e76fb4b462c7c75ece0844"},"schema_version":"1.0","source":{"id":"1909.04242","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.04242","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"arxiv_version","alias_value":"1909.04242v2","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.04242","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"pith_short_12","alias_value":"KRYG4KNUIQX6","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"pith_short_16","alias_value":"KRYG4KNUIQX65MBL","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"pith_short_8","alias_value":"KRYG4KNU","created_at":"2026-07-05T00:10:04Z"}],"graph_snapshots":[{"event_id":"sha256:1d2d62ad85853285cfb23d113787dc37c095596db0274e36a14a655e3820b45e","target":"graph","created_at":"2026-07-05T00:10:04Z","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/1909.04242/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural language inference (NLI) aims at predicting the relationship between a given pair of premise and hypothesis. However, several works have found that there widely exists a bias pattern called annotation artifacts in NLI datasets, making it possible to identify the label only by looking at the hypothesis. This irregularity makes the evaluation results over-estimated and affects models' generalization ability. In this paper, we consider a more trust-worthy setting, i.e., cross-dataset evaluation. We explore the impacts of annotation artifacts in cross-dataset testing. Furthermore, we propo","authors_text":"Bing Bai, Conghui Zhu, Guanhua Zhang, Junqi Zhang, Kun Bai, Tiejun Zhao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-10T02:35:34Z","title":"Mitigating Annotation Artifacts in Natural Language Inference Datasets to Improve Cross-dataset Generalization Ability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.04242","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":"sha256:7c7a35e34d30e616a2f1a1cdd24a8519f3e16f56b877c275254decff266bd95c","target":"record","created_at":"2026-07-05T00:10:04Z","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":"883653714a3ba6fbada660e8732396570f618ee1dcc6b2cd15103c913ca25b87","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-10T02:35:34Z","title_canon_sha256":"ecfb8dea43970515837e140d76abf44e87af521c10e76fb4b462c7c75ece0844"},"schema_version":"1.0","source":{"id":"1909.04242","kind":"arxiv","version":2}},"canonical_sha256":"54706e29b4442feeb02bb1b541d7cfc434dfbc473d7e8bdd980b0a2abbc3c856","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54706e29b4442feeb02bb1b541d7cfc434dfbc473d7e8bdd980b0a2abbc3c856","first_computed_at":"2026-07-05T00:10:04.060279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:10:04.060279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"706zIiYawNxZHIKJ9I3J9yC5g7GQQOnW9TqNoY/YlTmqxm+ltQ+vxSvOT2YVKF9FvNypfaCpM709F6TozgXlDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:10:04.060670Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.04242","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c7a35e34d30e616a2f1a1cdd24a8519f3e16f56b877c275254decff266bd95c","sha256:1d2d62ad85853285cfb23d113787dc37c095596db0274e36a14a655e3820b45e"],"state_sha256":"5518f66d384597bb0919c8394720773226352d2e86e3dd596555bab4ddabe4d7"}