{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UIT7T7N2YP3WWKY2B2HYLONEK5","short_pith_number":"pith:UIT7T7N2","schema_version":"1.0","canonical_sha256":"a227f9fdbac3f76b2b1a0e8f85b9a4575a20f4c588c9e46e875059c15777ea11","source":{"kind":"arxiv","id":"2509.06401","version":1},"attestation_state":"computed","paper":{"title":"Do LLMs exhibit the same commonsense capabilities across languages?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Albert Gatt, Elena Lloret, Ivan Mart\\'inez-Murillo, Paloma Moreda","submitted_at":"2025-09-08T07:47:00Z","abstract_excerpt":"This paper explores the multilingual commonsense generation abilities of Large Language Models (LLMs). To facilitate this investigation, we introduce MULTICOM, a novel benchmark that extends the COCOTEROS dataset to four languages: English, Spanish, Dutch, and Valencian. The task involves generating a commonsensical sentence that includes a given triplet of words. We evaluate a range of open-source LLMs, including LLaMA, Qwen, Gemma, EuroLLM, and Salamandra, on this benchmark. Our evaluation combines automatic metrics, LLM-as-a-judge approaches (using Prometheus and JudgeLM), and human annotat"},"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":"2509.06401","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-08T07:47:00Z","cross_cats_sorted":[],"title_canon_sha256":"f83248d6c9336649762d4bde4f266181ee6a0a8d926201908af567d791bde347","abstract_canon_sha256":"e5c32b3ba2795bdc4227b39c5603c6b75ef8fb862b3315a4f56154c3e1abf7d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:35.140093Z","signature_b64":"B25xyYLQpBqnT0vBZtPc49B4GXGlFjjVG+BIow4Wf6WEwDtyAZDYF7jO+tLNypmoOiBsg0iXThH1j2M+c4lxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a227f9fdbac3f76b2b1a0e8f85b9a4575a20f4c588c9e46e875059c15777ea11","last_reissued_at":"2026-07-05T12:06:35.139618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:35.139618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do LLMs exhibit the same commonsense capabilities across languages?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Albert Gatt, Elena Lloret, Ivan Mart\\'inez-Murillo, Paloma Moreda","submitted_at":"2025-09-08T07:47:00Z","abstract_excerpt":"This paper explores the multilingual commonsense generation abilities of Large Language Models (LLMs). To facilitate this investigation, we introduce MULTICOM, a novel benchmark that extends the COCOTEROS dataset to four languages: English, Spanish, Dutch, and Valencian. The task involves generating a commonsensical sentence that includes a given triplet of words. We evaluate a range of open-source LLMs, including LLaMA, Qwen, Gemma, EuroLLM, and Salamandra, on this benchmark. Our evaluation combines automatic metrics, LLM-as-a-judge approaches (using Prometheus and JudgeLM), and human annotat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06401","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/2509.06401/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":"2509.06401","created_at":"2026-07-05T12:06:35.139673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06401v1","created_at":"2026-07-05T12:06:35.139673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06401","created_at":"2026-07-05T12:06:35.139673+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIT7T7N2YP3W","created_at":"2026-07-05T12:06:35.139673+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIT7T7N2YP3WWKY2","created_at":"2026-07-05T12:06:35.139673+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIT7T7N2","created_at":"2026-07-05T12:06:35.139673+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/UIT7T7N2YP3WWKY2B2HYLONEK5","json":"https://pith.science/pith/UIT7T7N2YP3WWKY2B2HYLONEK5.json","graph_json":"https://pith.science/api/pith-number/UIT7T7N2YP3WWKY2B2HYLONEK5/graph.json","events_json":"https://pith.science/api/pith-number/UIT7T7N2YP3WWKY2B2HYLONEK5/events.json","paper":"https://pith.science/paper/UIT7T7N2"},"agent_actions":{"view_html":"https://pith.science/pith/UIT7T7N2YP3WWKY2B2HYLONEK5","download_json":"https://pith.science/pith/UIT7T7N2YP3WWKY2B2HYLONEK5.json","view_paper":"https://pith.science/paper/UIT7T7N2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06401&json=true","fetch_graph":"https://pith.science/api/pith-number/UIT7T7N2YP3WWKY2B2HYLONEK5/graph.json","fetch_events":"https://pith.science/api/pith-number/UIT7T7N2YP3WWKY2B2HYLONEK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIT7T7N2YP3WWKY2B2HYLONEK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIT7T7N2YP3WWKY2B2HYLONEK5/action/storage_attestation","attest_author":"https://pith.science/pith/UIT7T7N2YP3WWKY2B2HYLONEK5/action/author_attestation","sign_citation":"https://pith.science/pith/UIT7T7N2YP3WWKY2B2HYLONEK5/action/citation_signature","submit_replication":"https://pith.science/pith/UIT7T7N2YP3WWKY2B2HYLONEK5/action/replication_record"}},"created_at":"2026-07-05T12:06:35.139673+00:00","updated_at":"2026-07-05T12:06:35.139673+00:00"}