{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RUSBOHWIBY55JG7PQB3K6M4QG4","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":"465bd9d0049ed01e64bbcaab2bfed11b07a19eff08fb6e6b0b246eb1cf0970c2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-15T11:50:12Z","title_canon_sha256":"b669364480d73821a3f5383fa24edb5a639184ba185464d595c2ea2b04d1969f"},"schema_version":"1.0","source":{"id":"2010.07676","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.07676","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"arxiv_version","alias_value":"2010.07676v1","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07676","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"pith_short_12","alias_value":"RUSBOHWIBY55","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"pith_short_16","alias_value":"RUSBOHWIBY55JG7P","created_at":"2026-07-05T01:43:19Z"},{"alias_kind":"pith_short_8","alias_value":"RUSBOHWI","created_at":"2026-07-05T01:43:19Z"}],"graph_snapshots":[{"event_id":"sha256:320356da2a17865cb700f5c16015a761fd0403b1d38cf2decb2d16d5aa36b0d0","target":"graph","created_at":"2026-07-05T01:43:19Z","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/2010.07676/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies show that crowd-sourced Natural Language Inference (NLI) datasets may suffer from significant biases like annotation artifacts. Models utilizing these superficial clues gain mirage advantages on the in-domain testing set, which makes the evaluation results over-estimated. The lack of trustworthy evaluation settings and benchmarks stalls the progress of NLI research. In this paper, we propose to assess a model's trustworthy generalization performance with cross-datasets evaluation. We present a new unified cross-datasets benchmark with 14 NLI datasets, and re-evaluate 9 widely-us","authors_text":"Bing Bai, Conghui Zhu, Guanhua Zhang, Jian Liang, Kun Bai, Tiejun Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-15T11:50:12Z","title":"Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07676","kind":"arxiv","version":1},"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:c50c4bad2717ad67961164162518f53bae2062dc4e064d439721749703263cb0","target":"record","created_at":"2026-07-05T01:43:19Z","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":"465bd9d0049ed01e64bbcaab2bfed11b07a19eff08fb6e6b0b246eb1cf0970c2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-15T11:50:12Z","title_canon_sha256":"b669364480d73821a3f5383fa24edb5a639184ba185464d595c2ea2b04d1969f"},"schema_version":"1.0","source":{"id":"2010.07676","kind":"arxiv","version":1}},"canonical_sha256":"8d24171ec80e3bd49bef8076af339037059d68ba70069ccd4dd20b5927d7cc1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d24171ec80e3bd49bef8076af339037059d68ba70069ccd4dd20b5927d7cc1b","first_computed_at":"2026-07-05T01:43:19.520560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:19.520560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/sKLr3PBWyQ7zbRQXL+S4/B4w2HawnmJsxQDtDhIa75NZ6DIGfY1h1ZYnrv/cCAyFO4IRrlOx4uX/SujrHlDDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:19.521029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.07676","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c50c4bad2717ad67961164162518f53bae2062dc4e064d439721749703263cb0","sha256:320356da2a17865cb700f5c16015a761fd0403b1d38cf2decb2d16d5aa36b0d0"],"state_sha256":"6366e0f0cf532e5e4f6f78cf70e36acbb611a47f739e687a8f64acaa22aa3595"}