{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FNMAPLAPNSHBXBSDNHBEZ4IAWO","short_pith_number":"pith:FNMAPLAP","schema_version":"1.0","canonical_sha256":"2b5807ac0f6c8e1b864369c24cf100b3bb2b30daa42dc2d022c8a2d5313036da","source":{"kind":"arxiv","id":"2004.04312","version":2},"attestation_state":"computed","paper":{"title":"Learning to Scale Multilingual Representations for Vision-Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Andrea Burns, Bryan A. Plummer, Derry Wijaya, Donghyun Kim, Kate Saenko","submitted_at":"2020-04-09T01:03:44Z","abstract_excerpt":"Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual Aligned Language Representation (SMALR) that supports many languages with few model parameters without sacrificing downstream task performance. SMALR learns a fixed size language-agnostic representation for most words in a multilingual vocabulary, keeping language-specific features for just a few. We use a masked cross-language modeling loss to align features wi"},"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":"2004.04312","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-09T01:03:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dfc98bcdd4dcbcf58a74f8486a5453c9b33efad5be686b77fa5cfa93aa110026","abstract_canon_sha256":"6ee9637f7c6a7814e231d68c59fb85ac240db69424ba47235f14972ffd9b63fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:31:10.406982Z","signature_b64":"Ch2JsaRRI2FgP6Qp7vGgqsXT7mH766eHL+cCSAeXKOY72zG2fqZ65oOgflqzB9kuagdDzIAYlBOn8k/6k16LCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b5807ac0f6c8e1b864369c24cf100b3bb2b30daa42dc2d022c8a2d5313036da","last_reissued_at":"2026-07-05T01:31:10.406537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:31:10.406537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Scale Multilingual Representations for Vision-Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Andrea Burns, Bryan A. Plummer, Derry Wijaya, Donghyun Kim, Kate Saenko","submitted_at":"2020-04-09T01:03:44Z","abstract_excerpt":"Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual Aligned Language Representation (SMALR) that supports many languages with few model parameters without sacrificing downstream task performance. SMALR learns a fixed size language-agnostic representation for most words in a multilingual vocabulary, keeping language-specific features for just a few. We use a masked cross-language modeling loss to align features wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.04312","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/2004.04312/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":"2004.04312","created_at":"2026-07-05T01:31:10.406603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.04312v2","created_at":"2026-07-05T01:31:10.406603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.04312","created_at":"2026-07-05T01:31:10.406603+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNMAPLAPNSHB","created_at":"2026-07-05T01:31:10.406603+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNMAPLAPNSHBXBSD","created_at":"2026-07-05T01:31:10.406603+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNMAPLAP","created_at":"2026-07-05T01:31:10.406603+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/FNMAPLAPNSHBXBSDNHBEZ4IAWO","json":"https://pith.science/pith/FNMAPLAPNSHBXBSDNHBEZ4IAWO.json","graph_json":"https://pith.science/api/pith-number/FNMAPLAPNSHBXBSDNHBEZ4IAWO/graph.json","events_json":"https://pith.science/api/pith-number/FNMAPLAPNSHBXBSDNHBEZ4IAWO/events.json","paper":"https://pith.science/paper/FNMAPLAP"},"agent_actions":{"view_html":"https://pith.science/pith/FNMAPLAPNSHBXBSDNHBEZ4IAWO","download_json":"https://pith.science/pith/FNMAPLAPNSHBXBSDNHBEZ4IAWO.json","view_paper":"https://pith.science/paper/FNMAPLAP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.04312&json=true","fetch_graph":"https://pith.science/api/pith-number/FNMAPLAPNSHBXBSDNHBEZ4IAWO/graph.json","fetch_events":"https://pith.science/api/pith-number/FNMAPLAPNSHBXBSDNHBEZ4IAWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNMAPLAPNSHBXBSDNHBEZ4IAWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNMAPLAPNSHBXBSDNHBEZ4IAWO/action/storage_attestation","attest_author":"https://pith.science/pith/FNMAPLAPNSHBXBSDNHBEZ4IAWO/action/author_attestation","sign_citation":"https://pith.science/pith/FNMAPLAPNSHBXBSDNHBEZ4IAWO/action/citation_signature","submit_replication":"https://pith.science/pith/FNMAPLAPNSHBXBSDNHBEZ4IAWO/action/replication_record"}},"created_at":"2026-07-05T01:31:10.406603+00:00","updated_at":"2026-07-05T01:31:10.406603+00:00"}