{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZFROSFA4S5M2SY3Q6JUKCCB6OK","short_pith_number":"pith:ZFROSFA4","schema_version":"1.0","canonical_sha256":"c962e9141c9759a96370f268a1083e728e69755596ef208a22ca885fa9d3fd6c","source":{"kind":"arxiv","id":"2306.15261","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Out-of-Distribution Evaluation of Neural NLP Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ming Liu, Shang Gao, Wray Buntine, Xinzhe Li","submitted_at":"2023-06-27T07:44:25Z","abstract_excerpt":"Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models. However, a comprehensive, integrated discussion of the three research lines is still lacking in the literature. In this survey, we 1) compare the three lines of research under a unifying definition; 2) summarize the data-generating processes and evaluation protocols for each line of research; and 3) emphasize the challenges and opportunities for future work."},"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":"2306.15261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T07:44:25Z","cross_cats_sorted":[],"title_canon_sha256":"0ec29fc13a607d744d2c4733ab349d0aa2f5e2b38b4a15b5324dd161fa68169e","abstract_canon_sha256":"b2177ec6124012e93113211a3c2859c8c44864e0a10d0f0fcbfd0184600b1a4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:23.636187Z","signature_b64":"sL3CwbyxuM1rfmKn4xHvrb8boe2biQIjQ8il5NOGWn8sWthuhVu9UyhX+zGsFGFlpgu6AotIOR5Lmj6OfdzJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c962e9141c9759a96370f268a1083e728e69755596ef208a22ca885fa9d3fd6c","last_reissued_at":"2026-07-05T09:19:23.635700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:23.635700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Out-of-Distribution Evaluation of Neural NLP Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ming Liu, Shang Gao, Wray Buntine, Xinzhe Li","submitted_at":"2023-06-27T07:44:25Z","abstract_excerpt":"Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models. However, a comprehensive, integrated discussion of the three research lines is still lacking in the literature. In this survey, we 1) compare the three lines of research under a unifying definition; 2) summarize the data-generating processes and evaluation protocols for each line of research; and 3) emphasize the challenges and opportunities for future work."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15261","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/2306.15261/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":"2306.15261","created_at":"2026-07-05T09:19:23.635757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.15261v1","created_at":"2026-07-05T09:19:23.635757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15261","created_at":"2026-07-05T09:19:23.635757+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFROSFA4S5M2","created_at":"2026-07-05T09:19:23.635757+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFROSFA4S5M2SY3Q","created_at":"2026-07-05T09:19:23.635757+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFROSFA4","created_at":"2026-07-05T09:19:23.635757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15208","citing_title":"Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFROSFA4S5M2SY3Q6JUKCCB6OK","json":"https://pith.science/pith/ZFROSFA4S5M2SY3Q6JUKCCB6OK.json","graph_json":"https://pith.science/api/pith-number/ZFROSFA4S5M2SY3Q6JUKCCB6OK/graph.json","events_json":"https://pith.science/api/pith-number/ZFROSFA4S5M2SY3Q6JUKCCB6OK/events.json","paper":"https://pith.science/paper/ZFROSFA4"},"agent_actions":{"view_html":"https://pith.science/pith/ZFROSFA4S5M2SY3Q6JUKCCB6OK","download_json":"https://pith.science/pith/ZFROSFA4S5M2SY3Q6JUKCCB6OK.json","view_paper":"https://pith.science/paper/ZFROSFA4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.15261&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFROSFA4S5M2SY3Q6JUKCCB6OK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFROSFA4S5M2SY3Q6JUKCCB6OK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFROSFA4S5M2SY3Q6JUKCCB6OK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFROSFA4S5M2SY3Q6JUKCCB6OK/action/storage_attestation","attest_author":"https://pith.science/pith/ZFROSFA4S5M2SY3Q6JUKCCB6OK/action/author_attestation","sign_citation":"https://pith.science/pith/ZFROSFA4S5M2SY3Q6JUKCCB6OK/action/citation_signature","submit_replication":"https://pith.science/pith/ZFROSFA4S5M2SY3Q6JUKCCB6OK/action/replication_record"}},"created_at":"2026-07-05T09:19:23.635757+00:00","updated_at":"2026-07-05T09:19:23.635757+00:00"}