{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YOAQPNCWOVDBNA6JQPM53QTRI6","short_pith_number":"pith:YOAQPNCW","schema_version":"1.0","canonical_sha256":"c38107b45675461683c983d9ddc2714782d9ca121fa1269bc3c04c88c3e4baa0","source":{"kind":"arxiv","id":"2005.03692","version":2},"attestation_state":"computed","paper":{"title":"A Systematic Assessment of Syntactic Generalization in Neural Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ethan Wilcox, Jennifer Hu, Jon Gauthier, Peng Qian, Roger P. Levy","submitted_at":"2020-05-07T18:35:25Z","abstract_excerpt":"While state-of-the-art neural network models continue to achieve lower perplexity scores on language modeling benchmarks, it remains unknown whether optimizing for broad-coverage predictive performance leads to human-like syntactic knowledge. Furthermore, existing work has not provided a clear picture about the model properties required to produce proper syntactic generalizations. We present a systematic evaluation of the syntactic knowledge of neural language models, testing 20 combinations of model types and data sizes on a set of 34 English-language syntactic test suites. We find substantia"},"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":"2005.03692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-07T18:35:25Z","cross_cats_sorted":[],"title_canon_sha256":"2efad487226cfd2654d7b8b909a05aafd96a8a86ee88ed7d170d7b207cd71073","abstract_canon_sha256":"4a7459632c6d84f38c0851a5affde825c92c67105f7d4ad9bae24ef503c426f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:12.816056Z","signature_b64":"U4Os6m3kmSN6/E5m0vvu061wLzwhozVIU9StbP+IFH/yHBh57obrZ8ZEB/F4X56HRscrFHFF+rZGqi4AW1duCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c38107b45675461683c983d9ddc2714782d9ca121fa1269bc3c04c88c3e4baa0","last_reissued_at":"2026-07-05T01:05:12.815697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:12.815697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Systematic Assessment of Syntactic Generalization in Neural Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ethan Wilcox, Jennifer Hu, Jon Gauthier, Peng Qian, Roger P. Levy","submitted_at":"2020-05-07T18:35:25Z","abstract_excerpt":"While state-of-the-art neural network models continue to achieve lower perplexity scores on language modeling benchmarks, it remains unknown whether optimizing for broad-coverage predictive performance leads to human-like syntactic knowledge. Furthermore, existing work has not provided a clear picture about the model properties required to produce proper syntactic generalizations. We present a systematic evaluation of the syntactic knowledge of neural language models, testing 20 combinations of model types and data sizes on a set of 34 English-language syntactic test suites. We find substantia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.03692","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/2005.03692/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":"2005.03692","created_at":"2026-07-05T01:05:12.815749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.03692v2","created_at":"2026-07-05T01:05:12.815749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.03692","created_at":"2026-07-05T01:05:12.815749+00:00"},{"alias_kind":"pith_short_12","alias_value":"YOAQPNCWOVDB","created_at":"2026-07-05T01:05:12.815749+00:00"},{"alias_kind":"pith_short_16","alias_value":"YOAQPNCWOVDBNA6J","created_at":"2026-07-05T01:05:12.815749+00:00"},{"alias_kind":"pith_short_8","alias_value":"YOAQPNCW","created_at":"2026-07-05T01:05:12.815749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07389","citing_title":"Talking with Oompa Loompas: A novel framework for evaluating linguistic acquisition of LLM agents","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YOAQPNCWOVDBNA6JQPM53QTRI6","json":"https://pith.science/pith/YOAQPNCWOVDBNA6JQPM53QTRI6.json","graph_json":"https://pith.science/api/pith-number/YOAQPNCWOVDBNA6JQPM53QTRI6/graph.json","events_json":"https://pith.science/api/pith-number/YOAQPNCWOVDBNA6JQPM53QTRI6/events.json","paper":"https://pith.science/paper/YOAQPNCW"},"agent_actions":{"view_html":"https://pith.science/pith/YOAQPNCWOVDBNA6JQPM53QTRI6","download_json":"https://pith.science/pith/YOAQPNCWOVDBNA6JQPM53QTRI6.json","view_paper":"https://pith.science/paper/YOAQPNCW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.03692&json=true","fetch_graph":"https://pith.science/api/pith-number/YOAQPNCWOVDBNA6JQPM53QTRI6/graph.json","fetch_events":"https://pith.science/api/pith-number/YOAQPNCWOVDBNA6JQPM53QTRI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YOAQPNCWOVDBNA6JQPM53QTRI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YOAQPNCWOVDBNA6JQPM53QTRI6/action/storage_attestation","attest_author":"https://pith.science/pith/YOAQPNCWOVDBNA6JQPM53QTRI6/action/author_attestation","sign_citation":"https://pith.science/pith/YOAQPNCWOVDBNA6JQPM53QTRI6/action/citation_signature","submit_replication":"https://pith.science/pith/YOAQPNCWOVDBNA6JQPM53QTRI6/action/replication_record"}},"created_at":"2026-07-05T01:05:12.815749+00:00","updated_at":"2026-07-05T01:05:12.815749+00:00"}