{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OYRS4KUYFX4S3DSZO2Z5HIHFVO","short_pith_number":"pith:OYRS4KUY","schema_version":"1.0","canonical_sha256":"76232e2a982df92d8e5976b3d3a0e5ab9351fecc0efd8b47e3fb9f06c10db68c","source":{"kind":"arxiv","id":"2507.07274","version":1},"attestation_state":"computed","paper":{"title":"LinguaMark: Do Multimodal Models Speak Fairly? A Benchmark-Based Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Ananya Raval, Aravind Narayanan, Shaina Raza, Vahid Reza Khazaie","submitted_at":"2025-07-09T20:45:04Z","abstract_excerpt":"Large Multimodal Models (LMMs) are typically trained on vast corpora of image-text data but are often limited in linguistic coverage, leading to biased and unfair outputs across languages. While prior work has explored multimodal evaluation, less emphasis has been placed on assessing multilingual capabilities. In this work, we introduce LinguaMark, a benchmark designed to evaluate state-of-the-art LMMs on a multilingual Visual Question Answering (VQA) task. Our dataset comprises 6,875 image-text pairs spanning 11 languages and five social attributes. We evaluate models using three key metrics:"},"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":"2507.07274","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T20:45:04Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f6d40c91b3b4b7406ec3abf2929cb8fe17aa879e4643d157f34db445d17f7a3e","abstract_canon_sha256":"a045bf040a81d5757aa1c25523d74f07265bb4717fdde3c61912c9f9ebedc5ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:54.962071Z","signature_b64":"3/eNMikmr/+ZO71g3C4NmQhRHCQ4wj0eQSgQrD7v71qLL9v0VAJH0jbdZKIYA+kfrPpCholltBAILSa89KqnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76232e2a982df92d8e5976b3d3a0e5ab9351fecc0efd8b47e3fb9f06c10db68c","last_reissued_at":"2026-07-05T11:34:54.961621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:54.961621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LinguaMark: Do Multimodal Models Speak Fairly? A Benchmark-Based Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Ananya Raval, Aravind Narayanan, Shaina Raza, Vahid Reza Khazaie","submitted_at":"2025-07-09T20:45:04Z","abstract_excerpt":"Large Multimodal Models (LMMs) are typically trained on vast corpora of image-text data but are often limited in linguistic coverage, leading to biased and unfair outputs across languages. While prior work has explored multimodal evaluation, less emphasis has been placed on assessing multilingual capabilities. In this work, we introduce LinguaMark, a benchmark designed to evaluate state-of-the-art LMMs on a multilingual Visual Question Answering (VQA) task. Our dataset comprises 6,875 image-text pairs spanning 11 languages and five social attributes. We evaluate models using three key metrics:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07274","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/2507.07274/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":"2507.07274","created_at":"2026-07-05T11:34:54.961676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07274v1","created_at":"2026-07-05T11:34:54.961676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07274","created_at":"2026-07-05T11:34:54.961676+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYRS4KUYFX4S","created_at":"2026-07-05T11:34:54.961676+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYRS4KUYFX4S3DSZ","created_at":"2026-07-05T11:34:54.961676+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYRS4KUY","created_at":"2026-07-05T11:34:54.961676+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/OYRS4KUYFX4S3DSZO2Z5HIHFVO","json":"https://pith.science/pith/OYRS4KUYFX4S3DSZO2Z5HIHFVO.json","graph_json":"https://pith.science/api/pith-number/OYRS4KUYFX4S3DSZO2Z5HIHFVO/graph.json","events_json":"https://pith.science/api/pith-number/OYRS4KUYFX4S3DSZO2Z5HIHFVO/events.json","paper":"https://pith.science/paper/OYRS4KUY"},"agent_actions":{"view_html":"https://pith.science/pith/OYRS4KUYFX4S3DSZO2Z5HIHFVO","download_json":"https://pith.science/pith/OYRS4KUYFX4S3DSZO2Z5HIHFVO.json","view_paper":"https://pith.science/paper/OYRS4KUY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07274&json=true","fetch_graph":"https://pith.science/api/pith-number/OYRS4KUYFX4S3DSZO2Z5HIHFVO/graph.json","fetch_events":"https://pith.science/api/pith-number/OYRS4KUYFX4S3DSZO2Z5HIHFVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYRS4KUYFX4S3DSZO2Z5HIHFVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYRS4KUYFX4S3DSZO2Z5HIHFVO/action/storage_attestation","attest_author":"https://pith.science/pith/OYRS4KUYFX4S3DSZO2Z5HIHFVO/action/author_attestation","sign_citation":"https://pith.science/pith/OYRS4KUYFX4S3DSZO2Z5HIHFVO/action/citation_signature","submit_replication":"https://pith.science/pith/OYRS4KUYFX4S3DSZO2Z5HIHFVO/action/replication_record"}},"created_at":"2026-07-05T11:34:54.961676+00:00","updated_at":"2026-07-05T11:34:54.961676+00:00"}