{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZPGTBRKF5FQGHWMEG2FUQDFMQN","short_pith_number":"pith:ZPGTBRKF","schema_version":"1.0","canonical_sha256":"cbcd30c545e96063d984368b480cac837b75b4e0ccfa684f757c3fc38c1bd56e","source":{"kind":"arxiv","id":"2411.07474","version":2},"attestation_state":"computed","paper":{"title":"Controlled Evaluation of Syntactic Knowledge in Multilingual Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daria Kryvosheieva, Roger Levy","submitted_at":"2024-11-12T01:26:41Z","abstract_excerpt":"Language models (LMs) are capable of acquiring elements of human-like syntactic knowledge. Targeted syntactic evaluation tests have been employed to measure how well they form generalizations about syntactic phenomena in high-resource languages such as English. However, we still lack a thorough understanding of LMs' capacity for syntactic generalizations in low-resource languages, which are responsible for much of the diversity of syntactic patterns worldwide. In this study, we develop targeted syntactic evaluation tests for three low-resource languages (Basque, Hindi, and Swahili) and use the"},"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":"2411.07474","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-12T01:26:41Z","cross_cats_sorted":[],"title_canon_sha256":"3ab5a61a1191cc6f1ea0ad00b83610673bc3d44b58178e4c6ec1552c0a3f01cc","abstract_canon_sha256":"6481a73f719c14faf898696c9ea6ed2930c0fb219fc8db551d99d762bbb52d5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:57.315531Z","signature_b64":"PA1xXCrSGPfft6ykiNpszz10Hqjyca/+zDqWdzPXQKYzdq8VSPshiUMJz8RWUCo5gQkIGqqBYpAUhUV96qe7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbcd30c545e96063d984368b480cac837b75b4e0ccfa684f757c3fc38c1bd56e","last_reissued_at":"2026-07-05T09:47:57.314994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:57.314994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlled Evaluation of Syntactic Knowledge in Multilingual Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daria Kryvosheieva, Roger Levy","submitted_at":"2024-11-12T01:26:41Z","abstract_excerpt":"Language models (LMs) are capable of acquiring elements of human-like syntactic knowledge. Targeted syntactic evaluation tests have been employed to measure how well they form generalizations about syntactic phenomena in high-resource languages such as English. However, we still lack a thorough understanding of LMs' capacity for syntactic generalizations in low-resource languages, which are responsible for much of the diversity of syntactic patterns worldwide. In this study, we develop targeted syntactic evaluation tests for three low-resource languages (Basque, Hindi, and Swahili) and use the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07474","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/2411.07474/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":"2411.07474","created_at":"2026-07-05T09:47:57.315054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07474v2","created_at":"2026-07-05T09:47:57.315054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07474","created_at":"2026-07-05T09:47:57.315054+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPGTBRKF5FQG","created_at":"2026-07-05T09:47:57.315054+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPGTBRKF5FQGHWME","created_at":"2026-07-05T09:47:57.315054+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPGTBRKF","created_at":"2026-07-05T09:47:57.315054+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01006","citing_title":"UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZPGTBRKF5FQGHWMEG2FUQDFMQN","json":"https://pith.science/pith/ZPGTBRKF5FQGHWMEG2FUQDFMQN.json","graph_json":"https://pith.science/api/pith-number/ZPGTBRKF5FQGHWMEG2FUQDFMQN/graph.json","events_json":"https://pith.science/api/pith-number/ZPGTBRKF5FQGHWMEG2FUQDFMQN/events.json","paper":"https://pith.science/paper/ZPGTBRKF"},"agent_actions":{"view_html":"https://pith.science/pith/ZPGTBRKF5FQGHWMEG2FUQDFMQN","download_json":"https://pith.science/pith/ZPGTBRKF5FQGHWMEG2FUQDFMQN.json","view_paper":"https://pith.science/paper/ZPGTBRKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07474&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPGTBRKF5FQGHWMEG2FUQDFMQN/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPGTBRKF5FQGHWMEG2FUQDFMQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPGTBRKF5FQGHWMEG2FUQDFMQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPGTBRKF5FQGHWMEG2FUQDFMQN/action/storage_attestation","attest_author":"https://pith.science/pith/ZPGTBRKF5FQGHWMEG2FUQDFMQN/action/author_attestation","sign_citation":"https://pith.science/pith/ZPGTBRKF5FQGHWMEG2FUQDFMQN/action/citation_signature","submit_replication":"https://pith.science/pith/ZPGTBRKF5FQGHWMEG2FUQDFMQN/action/replication_record"}},"created_at":"2026-07-05T09:47:57.315054+00:00","updated_at":"2026-07-05T09:47:57.315054+00:00"}