{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IAQ4TFTUPI3HTZYOP3U7JRFYUM","short_pith_number":"pith:IAQ4TFTU","schema_version":"1.0","canonical_sha256":"4021c996747a3679e70e7ee9f4c4b8a318fdf4c6791144d734df292c01ad4f0c","source":{"kind":"arxiv","id":"2311.09033","version":3},"attestation_state":"computed","paper":{"title":"MELA: Multilingual Evaluation of Linguistic Acceptability","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hai Hu, Junyu Mao, Rui Wang, Weifang Huang, Yikang Liu, Ziyin Zhang","submitted_at":"2023-11-15T15:25:28Z","abstract_excerpt":"In this work, we present the largest benchmark to date on linguistic acceptability: Multilingual Evaluation of Linguistic Acceptability -- MELA, with 46K samples covering 10 languages from a diverse set of language families. We establish LLM baselines on this benchmark, and investigate cross-lingual transfer in acceptability judgements with XLM-R. In pursuit of multilingual interpretability, we conduct probing experiments with fine-tuned XLM-R to explore the process of syntax capability acquisition. Our results show that GPT-4o exhibits a strong multilingual ability, outperforming fine-tuned X"},"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":"2311.09033","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T15:25:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"96b58264a0a3ac6025c12931f02c05c7416c7fcc72c8ba40446f79c50a88fe77","abstract_canon_sha256":"3004ab0a6a28094c73d02a7f927086141ab2fb57c07eb133f8c82b7dc187e49a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:03.561576Z","signature_b64":"qiHKMGtSD4hdfQeV5gRcqlodn7p6I40MDOCCqfUyDUSMCGLDsyhs+4pqHyITI6xV080Vxss8fhpf2zO9iEQ1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4021c996747a3679e70e7ee9f4c4b8a318fdf4c6791144d734df292c01ad4f0c","last_reissued_at":"2026-07-05T08:28:03.561118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:03.561118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MELA: Multilingual Evaluation of Linguistic Acceptability","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hai Hu, Junyu Mao, Rui Wang, Weifang Huang, Yikang Liu, Ziyin Zhang","submitted_at":"2023-11-15T15:25:28Z","abstract_excerpt":"In this work, we present the largest benchmark to date on linguistic acceptability: Multilingual Evaluation of Linguistic Acceptability -- MELA, with 46K samples covering 10 languages from a diverse set of language families. We establish LLM baselines on this benchmark, and investigate cross-lingual transfer in acceptability judgements with XLM-R. In pursuit of multilingual interpretability, we conduct probing experiments with fine-tuned XLM-R to explore the process of syntax capability acquisition. Our results show that GPT-4o exhibits a strong multilingual ability, outperforming fine-tuned X"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09033","kind":"arxiv","version":3},"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/2311.09033/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":"2311.09033","created_at":"2026-07-05T08:28:03.561177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09033v3","created_at":"2026-07-05T08:28:03.561177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09033","created_at":"2026-07-05T08:28:03.561177+00:00"},{"alias_kind":"pith_short_12","alias_value":"IAQ4TFTUPI3H","created_at":"2026-07-05T08:28:03.561177+00:00"},{"alias_kind":"pith_short_16","alias_value":"IAQ4TFTUPI3HTZYO","created_at":"2026-07-05T08:28:03.561177+00:00"},{"alias_kind":"pith_short_8","alias_value":"IAQ4TFTU","created_at":"2026-07-05T08:28:03.561177+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/IAQ4TFTUPI3HTZYOP3U7JRFYUM","json":"https://pith.science/pith/IAQ4TFTUPI3HTZYOP3U7JRFYUM.json","graph_json":"https://pith.science/api/pith-number/IAQ4TFTUPI3HTZYOP3U7JRFYUM/graph.json","events_json":"https://pith.science/api/pith-number/IAQ4TFTUPI3HTZYOP3U7JRFYUM/events.json","paper":"https://pith.science/paper/IAQ4TFTU"},"agent_actions":{"view_html":"https://pith.science/pith/IAQ4TFTUPI3HTZYOP3U7JRFYUM","download_json":"https://pith.science/pith/IAQ4TFTUPI3HTZYOP3U7JRFYUM.json","view_paper":"https://pith.science/paper/IAQ4TFTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09033&json=true","fetch_graph":"https://pith.science/api/pith-number/IAQ4TFTUPI3HTZYOP3U7JRFYUM/graph.json","fetch_events":"https://pith.science/api/pith-number/IAQ4TFTUPI3HTZYOP3U7JRFYUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IAQ4TFTUPI3HTZYOP3U7JRFYUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IAQ4TFTUPI3HTZYOP3U7JRFYUM/action/storage_attestation","attest_author":"https://pith.science/pith/IAQ4TFTUPI3HTZYOP3U7JRFYUM/action/author_attestation","sign_citation":"https://pith.science/pith/IAQ4TFTUPI3HTZYOP3U7JRFYUM/action/citation_signature","submit_replication":"https://pith.science/pith/IAQ4TFTUPI3HTZYOP3U7JRFYUM/action/replication_record"}},"created_at":"2026-07-05T08:28:03.561177+00:00","updated_at":"2026-07-05T08:28:03.561177+00:00"}