{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CUGZPUNUYLE4UXW5RUB6QSO6WF","short_pith_number":"pith:CUGZPUNU","schema_version":"1.0","canonical_sha256":"150d97d1b4c2c9ca5edd8d03e849deb164595c60a4e65cfad7da03733e314739","source":{"kind":"arxiv","id":"2606.01800","version":1},"attestation_state":"computed","paper":{"title":"Multilinguality of Large Language Models From a Structural Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haruki Sakajo, Hidetaka Kamigaito, Taro Watanabe, Yusuke Sakai","submitted_at":"2026-06-01T07:18:09Z","abstract_excerpt":"Large language models (LLMs) have excelled in processing multiple languages through pre- and post-training on multilingual data, even though English dominates the training data. Prior work focusing on token representations has revealed how those LLMs process non-English text. Although these analyses have provided insightful findings, they fail to capture a structural view, which is an inherent property of language. In this study, we explore the multilinguality of LLMs through representational structural analysis. Our findings reveal that low-resource languages are structurally more different f"},"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":"2606.01800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T07:18:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9d79ab8585a13f26a507163d6dee563f451a19f5db0cd83d7cea285095c21213","abstract_canon_sha256":"a6bf11258d557a1c6dfdb95f63c0a625fd2e34dcc7b2860e68010e8eebeeb055"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:57.150797Z","signature_b64":"SroWJu35AWUtvYJSiCRlSnGCd8wBlfEUiyrA+tfHasAlxPucBwvWbX7NtyqALhJX+KTCMoTjvvxYRjX7FS5BAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"150d97d1b4c2c9ca5edd8d03e849deb164595c60a4e65cfad7da03733e314739","last_reissued_at":"2026-06-02T02:04:57.150429Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:57.150429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilinguality of Large Language Models From a Structural Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haruki Sakajo, Hidetaka Kamigaito, Taro Watanabe, Yusuke Sakai","submitted_at":"2026-06-01T07:18:09Z","abstract_excerpt":"Large language models (LLMs) have excelled in processing multiple languages through pre- and post-training on multilingual data, even though English dominates the training data. Prior work focusing on token representations has revealed how those LLMs process non-English text. Although these analyses have provided insightful findings, they fail to capture a structural view, which is an inherent property of language. In this study, we explore the multilinguality of LLMs through representational structural analysis. Our findings reveal that low-resource languages are structurally more different f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01800","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/2606.01800/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":"2606.01800","created_at":"2026-06-02T02:04:57.150491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01800v1","created_at":"2026-06-02T02:04:57.150491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01800","created_at":"2026-06-02T02:04:57.150491+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUGZPUNUYLE4","created_at":"2026-06-02T02:04:57.150491+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUGZPUNUYLE4UXW5","created_at":"2026-06-02T02:04:57.150491+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUGZPUNU","created_at":"2026-06-02T02:04:57.150491+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/CUGZPUNUYLE4UXW5RUB6QSO6WF","json":"https://pith.science/pith/CUGZPUNUYLE4UXW5RUB6QSO6WF.json","graph_json":"https://pith.science/api/pith-number/CUGZPUNUYLE4UXW5RUB6QSO6WF/graph.json","events_json":"https://pith.science/api/pith-number/CUGZPUNUYLE4UXW5RUB6QSO6WF/events.json","paper":"https://pith.science/paper/CUGZPUNU"},"agent_actions":{"view_html":"https://pith.science/pith/CUGZPUNUYLE4UXW5RUB6QSO6WF","download_json":"https://pith.science/pith/CUGZPUNUYLE4UXW5RUB6QSO6WF.json","view_paper":"https://pith.science/paper/CUGZPUNU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01800&json=true","fetch_graph":"https://pith.science/api/pith-number/CUGZPUNUYLE4UXW5RUB6QSO6WF/graph.json","fetch_events":"https://pith.science/api/pith-number/CUGZPUNUYLE4UXW5RUB6QSO6WF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUGZPUNUYLE4UXW5RUB6QSO6WF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUGZPUNUYLE4UXW5RUB6QSO6WF/action/storage_attestation","attest_author":"https://pith.science/pith/CUGZPUNUYLE4UXW5RUB6QSO6WF/action/author_attestation","sign_citation":"https://pith.science/pith/CUGZPUNUYLE4UXW5RUB6QSO6WF/action/citation_signature","submit_replication":"https://pith.science/pith/CUGZPUNUYLE4UXW5RUB6QSO6WF/action/replication_record"}},"created_at":"2026-06-02T02:04:57.150491+00:00","updated_at":"2026-06-02T02:04:57.150491+00:00"}