{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PTCMPQV2C6YKAKTV2CVYBDHYIS","short_pith_number":"pith:PTCMPQV2","schema_version":"1.0","canonical_sha256":"7cc4c7c2ba17b0a02a75d0ab808cf844914d5310050a24135e9e42fde584fc9d","source":{"kind":"arxiv","id":"2010.06478","version":1},"attestation_state":"computed","paper":{"title":"XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alessandro Raganato, Jose Camacho-Collados, Mohammad Taher Pilehvar, Tommaso Pasini","submitted_at":"2020-10-13T15:32:00Z","abstract_excerpt":"The ability to correctly model distinct meanings of a word is crucial for the effectiveness of semantic representation techniques. However, most existing evaluation benchmarks for assessing this criterion are tied to sense inventories (usually WordNet), restricting their usage to a small subset of knowledge-based representation techniques. The Word-in-Context dataset (WiC) addresses the dependence on sense inventories by reformulating the standard disambiguation task as a binary classification problem; but, it is limited to the English language. We put forward a large multilingual benchmark, 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":"2010.06478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-13T15:32:00Z","cross_cats_sorted":[],"title_canon_sha256":"40972f7b76062a8739fb11493b8b5d732605cb48fb9dfbcd292a9c7172ddaaf6","abstract_canon_sha256":"b99031cbd803764c494a1d0b829255088bc99dfeee582dca563bf452848580fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:49.150745Z","signature_b64":"LUE+7D5RZI9CY8wzF7bjsQ2+v+ACqKsiKJKp4ZsJM4cRLvi2lCywelGyl83l/MqlMdr+Zcy4AR0um+MPPjgpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cc4c7c2ba17b0a02a75d0ab808cf844914d5310050a24135e9e42fde584fc9d","last_reissued_at":"2026-07-05T01:42:49.150375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:49.150375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alessandro Raganato, Jose Camacho-Collados, Mohammad Taher Pilehvar, Tommaso Pasini","submitted_at":"2020-10-13T15:32:00Z","abstract_excerpt":"The ability to correctly model distinct meanings of a word is crucial for the effectiveness of semantic representation techniques. However, most existing evaluation benchmarks for assessing this criterion are tied to sense inventories (usually WordNet), restricting their usage to a small subset of knowledge-based representation techniques. The Word-in-Context dataset (WiC) addresses the dependence on sense inventories by reformulating the standard disambiguation task as a binary classification problem; but, it is limited to the English language. We put forward a large multilingual benchmark, X"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.06478","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/2010.06478/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":"2010.06478","created_at":"2026-07-05T01:42:49.150439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.06478v1","created_at":"2026-07-05T01:42:49.150439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.06478","created_at":"2026-07-05T01:42:49.150439+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTCMPQV2C6YK","created_at":"2026-07-05T01:42:49.150439+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTCMPQV2C6YKAKTV","created_at":"2026-07-05T01:42:49.150439+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTCMPQV2","created_at":"2026-07-05T01:42:49.150439+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11665","citing_title":"Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Tasks","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PTCMPQV2C6YKAKTV2CVYBDHYIS","json":"https://pith.science/pith/PTCMPQV2C6YKAKTV2CVYBDHYIS.json","graph_json":"https://pith.science/api/pith-number/PTCMPQV2C6YKAKTV2CVYBDHYIS/graph.json","events_json":"https://pith.science/api/pith-number/PTCMPQV2C6YKAKTV2CVYBDHYIS/events.json","paper":"https://pith.science/paper/PTCMPQV2"},"agent_actions":{"view_html":"https://pith.science/pith/PTCMPQV2C6YKAKTV2CVYBDHYIS","download_json":"https://pith.science/pith/PTCMPQV2C6YKAKTV2CVYBDHYIS.json","view_paper":"https://pith.science/paper/PTCMPQV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.06478&json=true","fetch_graph":"https://pith.science/api/pith-number/PTCMPQV2C6YKAKTV2CVYBDHYIS/graph.json","fetch_events":"https://pith.science/api/pith-number/PTCMPQV2C6YKAKTV2CVYBDHYIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTCMPQV2C6YKAKTV2CVYBDHYIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTCMPQV2C6YKAKTV2CVYBDHYIS/action/storage_attestation","attest_author":"https://pith.science/pith/PTCMPQV2C6YKAKTV2CVYBDHYIS/action/author_attestation","sign_citation":"https://pith.science/pith/PTCMPQV2C6YKAKTV2CVYBDHYIS/action/citation_signature","submit_replication":"https://pith.science/pith/PTCMPQV2C6YKAKTV2CVYBDHYIS/action/replication_record"}},"created_at":"2026-07-05T01:42:49.150439+00:00","updated_at":"2026-07-05T01:42:49.150439+00:00"}