{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TXDSRRYJOTLBCAQDVKP6Q5UGWJ","short_pith_number":"pith:TXDSRRYJ","schema_version":"1.0","canonical_sha256":"9dc728c70974d6110203aa9fe87686b25cbfb9b4f4d775e5931403f49640f58e","source":{"kind":"arxiv","id":"2510.15551","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Cross-lingual Gaps from a Statistical Viewpoint","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Darshan Singh, Partha Talukdar, Preethi Jyothi, Purvam Jain, Trevor Cohn, Vihari Piratla","submitted_at":"2025-10-17T11:34:04Z","abstract_excerpt":"Any piece of knowledge is usually expressed in one or a handful of natural languages on the web or in any large corpus. Large Language Models (LLMs) act as a bridge by acquiring knowledge from a source language and making it accessible when queried using target languages. A cross-lingual gap is a drop in accuracy incurred when querying knowledge in a target language rather than the source language. Existing research focused on modeling or training failures leading to cross-lingual gaps. In this work, we take an alternative view to characterize the nature of cross-lingual error, and hypothesize"},"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":"2510.15551","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-17T11:34:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"531e2eabd75ac6fcc91a23e60f692ace85e95bdaec096cf0d60e080e119abd9f","abstract_canon_sha256":"421c34571a187e7ff894ec9b23295049e4fdbfb1570e6af89a3345b340d51cdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:14.158809Z","signature_b64":"LhDgko1l7kbeiFvQUgIqU7iBOiEY+3OvdnDBl1vChM1uny7vXeTN5xZ8fOY66/zqa0SUWgJP3kowXMGu/J+BBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dc728c70974d6110203aa9fe87686b25cbfb9b4f4d775e5931403f49640f58e","last_reissued_at":"2026-06-19T16:11:14.158371Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:14.158371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Cross-lingual Gaps from a Statistical Viewpoint","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Darshan Singh, Partha Talukdar, Preethi Jyothi, Purvam Jain, Trevor Cohn, Vihari Piratla","submitted_at":"2025-10-17T11:34:04Z","abstract_excerpt":"Any piece of knowledge is usually expressed in one or a handful of natural languages on the web or in any large corpus. Large Language Models (LLMs) act as a bridge by acquiring knowledge from a source language and making it accessible when queried using target languages. A cross-lingual gap is a drop in accuracy incurred when querying knowledge in a target language rather than the source language. Existing research focused on modeling or training failures leading to cross-lingual gaps. In this work, we take an alternative view to characterize the nature of cross-lingual error, and hypothesize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.15551","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/2510.15551/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":"2510.15551","created_at":"2026-06-19T16:11:14.158429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.15551v2","created_at":"2026-06-19T16:11:14.158429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.15551","created_at":"2026-06-19T16:11:14.158429+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXDSRRYJOTLB","created_at":"2026-06-19T16:11:14.158429+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXDSRRYJOTLBCAQD","created_at":"2026-06-19T16:11:14.158429+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXDSRRYJ","created_at":"2026-06-19T16:11:14.158429+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/TXDSRRYJOTLBCAQDVKP6Q5UGWJ","json":"https://pith.science/pith/TXDSRRYJOTLBCAQDVKP6Q5UGWJ.json","graph_json":"https://pith.science/api/pith-number/TXDSRRYJOTLBCAQDVKP6Q5UGWJ/graph.json","events_json":"https://pith.science/api/pith-number/TXDSRRYJOTLBCAQDVKP6Q5UGWJ/events.json","paper":"https://pith.science/paper/TXDSRRYJ"},"agent_actions":{"view_html":"https://pith.science/pith/TXDSRRYJOTLBCAQDVKP6Q5UGWJ","download_json":"https://pith.science/pith/TXDSRRYJOTLBCAQDVKP6Q5UGWJ.json","view_paper":"https://pith.science/paper/TXDSRRYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.15551&json=true","fetch_graph":"https://pith.science/api/pith-number/TXDSRRYJOTLBCAQDVKP6Q5UGWJ/graph.json","fetch_events":"https://pith.science/api/pith-number/TXDSRRYJOTLBCAQDVKP6Q5UGWJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXDSRRYJOTLBCAQDVKP6Q5UGWJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXDSRRYJOTLBCAQDVKP6Q5UGWJ/action/storage_attestation","attest_author":"https://pith.science/pith/TXDSRRYJOTLBCAQDVKP6Q5UGWJ/action/author_attestation","sign_citation":"https://pith.science/pith/TXDSRRYJOTLBCAQDVKP6Q5UGWJ/action/citation_signature","submit_replication":"https://pith.science/pith/TXDSRRYJOTLBCAQDVKP6Q5UGWJ/action/replication_record"}},"created_at":"2026-06-19T16:11:14.158429+00:00","updated_at":"2026-06-19T16:11:14.158429+00:00"}