{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DXRDPWMD27C2B5MHJ3LSDGBXFP","short_pith_number":"pith:DXRDPWMD","schema_version":"1.0","canonical_sha256":"1de237d983d7c5a0f5874ed72198372be7cc0055166c30b10178f928d024089e","source":{"kind":"arxiv","id":"2409.18199","version":2},"attestation_state":"computed","paper":{"title":"LangSAMP: Language-Script Aware Multilingual Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunlan Ma, Haotian Ye, Hinrich Sch\\\"utze, Mingyang Wang, Yihong Liu","submitted_at":"2024-09-26T18:29:10Z","abstract_excerpt":"Recent multilingual pretrained language models (mPLMs) often avoid using language embeddings -- learnable vectors assigned to individual languages. However, this places a significant burden on token representations to encode all language-specific information, which may hinder language neutrality. To address this limitation, we propose Language-Script Aware Multilingual Pretraining (LangSAMP), a method that incorporates both language and script embeddings to enhance representation learning. Specifically, we integrate these embeddings into the output of the Transformer blocks before passing the "},"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":"2409.18199","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T18:29:10Z","cross_cats_sorted":[],"title_canon_sha256":"b6dd40b010457bf1b1747819b2deafca91c85436efc3d1837456c7417bdda842","abstract_canon_sha256":"8fe38aa96d68e5d0c13ae9b87a4f08751ffedd79ac862d6b2f7fdc106f92beb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:04.771334Z","signature_b64":"hN8cvm4MEzakvVy8el9FlstgfhTp+LcQmwlINkXA1uM0pZXBvFCfV+n7EOs6ehSC7d5nkd5xb04dJM70zLmTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1de237d983d7c5a0f5874ed72198372be7cc0055166c30b10178f928d024089e","last_reissued_at":"2026-07-05T11:07:04.770861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:04.770861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LangSAMP: Language-Script Aware Multilingual Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunlan Ma, Haotian Ye, Hinrich Sch\\\"utze, Mingyang Wang, Yihong Liu","submitted_at":"2024-09-26T18:29:10Z","abstract_excerpt":"Recent multilingual pretrained language models (mPLMs) often avoid using language embeddings -- learnable vectors assigned to individual languages. However, this places a significant burden on token representations to encode all language-specific information, which may hinder language neutrality. To address this limitation, we propose Language-Script Aware Multilingual Pretraining (LangSAMP), a method that incorporates both language and script embeddings to enhance representation learning. Specifically, we integrate these embeddings into the output of the Transformer blocks before passing the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18199","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/2409.18199/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":"2409.18199","created_at":"2026-07-05T11:07:04.770917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18199v2","created_at":"2026-07-05T11:07:04.770917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18199","created_at":"2026-07-05T11:07:04.770917+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXRDPWMD27C2","created_at":"2026-07-05T11:07:04.770917+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXRDPWMD27C2B5MH","created_at":"2026-07-05T11:07:04.770917+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXRDPWMD","created_at":"2026-07-05T11:07:04.770917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09758","citing_title":"Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP","json":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP.json","graph_json":"https://pith.science/api/pith-number/DXRDPWMD27C2B5MHJ3LSDGBXFP/graph.json","events_json":"https://pith.science/api/pith-number/DXRDPWMD27C2B5MHJ3LSDGBXFP/events.json","paper":"https://pith.science/paper/DXRDPWMD"},"agent_actions":{"view_html":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP","download_json":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP.json","view_paper":"https://pith.science/paper/DXRDPWMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18199&json=true","fetch_graph":"https://pith.science/api/pith-number/DXRDPWMD27C2B5MHJ3LSDGBXFP/graph.json","fetch_events":"https://pith.science/api/pith-number/DXRDPWMD27C2B5MHJ3LSDGBXFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP/action/storage_attestation","attest_author":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP/action/author_attestation","sign_citation":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP/action/citation_signature","submit_replication":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP/action/replication_record"}},"created_at":"2026-07-05T11:07:04.770917+00:00","updated_at":"2026-07-05T11:07:04.770917+00:00"}