{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RJ5KQ76BH5F4Z5TMGWWZU4WFF4","short_pith_number":"pith:RJ5KQ76B","schema_version":"1.0","canonical_sha256":"8a7aa87fc13f4bccf66c35ad9a72c52f348a32a91e42520ca834ccb0450e5f2f","source":{"kind":"arxiv","id":"2306.07610","version":1},"attestation_state":"computed","paper":{"title":"Soft Language Clustering for Multilingual Model Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binghuai Lin, Fandong Meng, Jiali Zeng, Jie Zhou, Yi Jing, Yongjing Yin, Yufan Jiang, Yunbo Cao","submitted_at":"2023-06-13T08:08:08Z","abstract_excerpt":"Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typology from source languages or when pre-training data is limited in size. In this paper, we propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods. On the tasks of "},"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":"2306.07610","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T08:08:08Z","cross_cats_sorted":[],"title_canon_sha256":"d13dcf446e9d604a11431b25342aab50c4522dc66e478b2bddbddc9cb3157faa","abstract_canon_sha256":"d4a6b66f09215d23ca39a6a47b3cdb5793c61f28db0779f7bf27b00347cc0fe1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:06.780631Z","signature_b64":"06uVuwN96ayRsT1YVLoo4fOaXnsI2U3K9pg3X4nUWz6Tdt0TugZgdjoDwVmsfZIVJ8eEtqY+IZZvOmTKvusUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a7aa87fc13f4bccf66c35ad9a72c52f348a32a91e42520ca834ccb0450e5f2f","last_reissued_at":"2026-07-05T06:20:06.780253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:06.780253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Soft Language Clustering for Multilingual Model Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binghuai Lin, Fandong Meng, Jiali Zeng, Jie Zhou, Yi Jing, Yongjing Yin, Yufan Jiang, Yunbo Cao","submitted_at":"2023-06-13T08:08:08Z","abstract_excerpt":"Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typology from source languages or when pre-training data is limited in size. In this paper, we propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods. On the tasks of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07610","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/2306.07610/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":"2306.07610","created_at":"2026-07-05T06:20:06.780322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07610v1","created_at":"2026-07-05T06:20:06.780322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07610","created_at":"2026-07-05T06:20:06.780322+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJ5KQ76BH5F4","created_at":"2026-07-05T06:20:06.780322+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJ5KQ76BH5F4Z5TM","created_at":"2026-07-05T06:20:06.780322+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJ5KQ76B","created_at":"2026-07-05T06:20:06.780322+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/RJ5KQ76BH5F4Z5TMGWWZU4WFF4","json":"https://pith.science/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4.json","graph_json":"https://pith.science/api/pith-number/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/graph.json","events_json":"https://pith.science/api/pith-number/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/events.json","paper":"https://pith.science/paper/RJ5KQ76B"},"agent_actions":{"view_html":"https://pith.science/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4","download_json":"https://pith.science/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4.json","view_paper":"https://pith.science/paper/RJ5KQ76B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07610&json=true","fetch_graph":"https://pith.science/api/pith-number/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/graph.json","fetch_events":"https://pith.science/api/pith-number/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/action/storage_attestation","attest_author":"https://pith.science/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/action/author_attestation","sign_citation":"https://pith.science/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/action/citation_signature","submit_replication":"https://pith.science/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/action/replication_record"}},"created_at":"2026-07-05T06:20:06.780322+00:00","updated_at":"2026-07-05T06:20:06.780322+00:00"}