{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RUSBOHWIBY55JG7PQB3K6M4QG4","short_pith_number":"pith:RUSBOHWI","schema_version":"1.0","canonical_sha256":"8d24171ec80e3bd49bef8076af339037059d68ba70069ccd4dd20b5927d7cc1b","source":{"kind":"arxiv","id":"2010.07676","version":1},"attestation_state":"computed","paper":{"title":"Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Bai, Conghui Zhu, Guanhua Zhang, Jian Liang, Kun Bai, Tiejun Zhao","submitted_at":"2020-10-15T11:50:12Z","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"},"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":"2010.07676","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-15T11:50:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b669364480d73821a3f5383fa24edb5a639184ba185464d595c2ea2b04d1969f","abstract_canon_sha256":"465bd9d0049ed01e64bbcaab2bfed11b07a19eff08fb6e6b0b246eb1cf0970c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:19.521029Z","signature_b64":"/sKLr3PBWyQ7zbRQXL+S4/B4w2HawnmJsxQDtDhIa75NZ6DIGfY1h1ZYnrv/cCAyFO4IRrlOx4uX/SujrHlDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d24171ec80e3bd49bef8076af339037059d68ba70069ccd4dd20b5927d7cc1b","last_reissued_at":"2026-07-05T01:43:19.520560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:19.520560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Bai, Conghui Zhu, Guanhua Zhang, Jian Liang, Kun Bai, Tiejun Zhao","submitted_at":"2020-10-15T11:50:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07676","kind":"arxiv","version":1},"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/2010.07676/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":"2010.07676","created_at":"2026-07-05T01:43:19.520617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.07676v1","created_at":"2026-07-05T01:43:19.520617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07676","created_at":"2026-07-05T01:43:19.520617+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUSBOHWIBY55","created_at":"2026-07-05T01:43:19.520617+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUSBOHWIBY55JG7P","created_at":"2026-07-05T01:43:19.520617+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUSBOHWI","created_at":"2026-07-05T01:43:19.520617+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/RUSBOHWIBY55JG7PQB3K6M4QG4","json":"https://pith.science/pith/RUSBOHWIBY55JG7PQB3K6M4QG4.json","graph_json":"https://pith.science/api/pith-number/RUSBOHWIBY55JG7PQB3K6M4QG4/graph.json","events_json":"https://pith.science/api/pith-number/RUSBOHWIBY55JG7PQB3K6M4QG4/events.json","paper":"https://pith.science/paper/RUSBOHWI"},"agent_actions":{"view_html":"https://pith.science/pith/RUSBOHWIBY55JG7PQB3K6M4QG4","download_json":"https://pith.science/pith/RUSBOHWIBY55JG7PQB3K6M4QG4.json","view_paper":"https://pith.science/paper/RUSBOHWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.07676&json=true","fetch_graph":"https://pith.science/api/pith-number/RUSBOHWIBY55JG7PQB3K6M4QG4/graph.json","fetch_events":"https://pith.science/api/pith-number/RUSBOHWIBY55JG7PQB3K6M4QG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUSBOHWIBY55JG7PQB3K6M4QG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUSBOHWIBY55JG7PQB3K6M4QG4/action/storage_attestation","attest_author":"https://pith.science/pith/RUSBOHWIBY55JG7PQB3K6M4QG4/action/author_attestation","sign_citation":"https://pith.science/pith/RUSBOHWIBY55JG7PQB3K6M4QG4/action/citation_signature","submit_replication":"https://pith.science/pith/RUSBOHWIBY55JG7PQB3K6M4QG4/action/replication_record"}},"created_at":"2026-07-05T01:43:19.520617+00:00","updated_at":"2026-07-05T01:43:19.520617+00:00"}