{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:53L4XZZZXX6KOP7FBVVKCXMQHT","short_pith_number":"pith:53L4XZZZ","schema_version":"1.0","canonical_sha256":"eed7cbe739bdfca73fe50d6aa15d903cfa35bbcb5ebce2014a451df4b8a261b9","source":{"kind":"arxiv","id":"2306.08658","version":2},"attestation_state":"computed","paper":{"title":"Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Goran Glava\\v{s}, Gregor Geigle, Radu Timofte","submitted_at":"2023-06-14T17:53:06Z","abstract_excerpt":"Vision-and-language (VL) models with separate encoders for each modality (e.g., CLIP) have become the go-to models for zero-shot image classification and image-text retrieval. They are, however, mostly evaluated in English as multilingual benchmarks are limited in availability. We introduce Babel-ImageNet, a massively multilingual benchmark that offers (partial) translations of ImageNet labels to 100 languages, built without machine translation or manual annotation. We instead automatically obtain reliable translations by linking them -- via shared WordNet synsets -- to BabelNet, a massively m"},"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":"2306.08658","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-14T17:53:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a683662d5fbb84ec7a3d6f3c48ead573c3a31a65420c6ae8a52f2b8dacffb3c2","abstract_canon_sha256":"478e3f24e981259f59e8c5d4527b47b1f91e6a0ca91411794b36c551aee6d21f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:48.035783Z","signature_b64":"E6ykcyzL2SO7eyZ9shFi6qkxmclQhjYmbw/JXZCgWzoUuHVpWkQaHD+SGoI1i94rif/aBZRwwET3Qe8TanYhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eed7cbe739bdfca73fe50d6aa15d903cfa35bbcb5ebce2014a451df4b8a261b9","last_reissued_at":"2026-07-05T08:30:48.035358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:48.035358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Goran Glava\\v{s}, Gregor Geigle, Radu Timofte","submitted_at":"2023-06-14T17:53:06Z","abstract_excerpt":"Vision-and-language (VL) models with separate encoders for each modality (e.g., CLIP) have become the go-to models for zero-shot image classification and image-text retrieval. They are, however, mostly evaluated in English as multilingual benchmarks are limited in availability. We introduce Babel-ImageNet, a massively multilingual benchmark that offers (partial) translations of ImageNet labels to 100 languages, built without machine translation or manual annotation. We instead automatically obtain reliable translations by linking them -- via shared WordNet synsets -- to BabelNet, a massively m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08658","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/2306.08658/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":"2306.08658","created_at":"2026-07-05T08:30:48.035415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.08658v2","created_at":"2026-07-05T08:30:48.035415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08658","created_at":"2026-07-05T08:30:48.035415+00:00"},{"alias_kind":"pith_short_12","alias_value":"53L4XZZZXX6K","created_at":"2026-07-05T08:30:48.035415+00:00"},{"alias_kind":"pith_short_16","alias_value":"53L4XZZZXX6KOP7F","created_at":"2026-07-05T08:30:48.035415+00:00"},{"alias_kind":"pith_short_8","alias_value":"53L4XZZZ","created_at":"2026-07-05T08:30:48.035415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22788","citing_title":"SPI-BoTER: Error Compensation for Industrial Robots via Sparse Attention Masking and Hybrid Loss with Spatial-Physical Information","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53L4XZZZXX6KOP7FBVVKCXMQHT","json":"https://pith.science/pith/53L4XZZZXX6KOP7FBVVKCXMQHT.json","graph_json":"https://pith.science/api/pith-number/53L4XZZZXX6KOP7FBVVKCXMQHT/graph.json","events_json":"https://pith.science/api/pith-number/53L4XZZZXX6KOP7FBVVKCXMQHT/events.json","paper":"https://pith.science/paper/53L4XZZZ"},"agent_actions":{"view_html":"https://pith.science/pith/53L4XZZZXX6KOP7FBVVKCXMQHT","download_json":"https://pith.science/pith/53L4XZZZXX6KOP7FBVVKCXMQHT.json","view_paper":"https://pith.science/paper/53L4XZZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.08658&json=true","fetch_graph":"https://pith.science/api/pith-number/53L4XZZZXX6KOP7FBVVKCXMQHT/graph.json","fetch_events":"https://pith.science/api/pith-number/53L4XZZZXX6KOP7FBVVKCXMQHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53L4XZZZXX6KOP7FBVVKCXMQHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53L4XZZZXX6KOP7FBVVKCXMQHT/action/storage_attestation","attest_author":"https://pith.science/pith/53L4XZZZXX6KOP7FBVVKCXMQHT/action/author_attestation","sign_citation":"https://pith.science/pith/53L4XZZZXX6KOP7FBVVKCXMQHT/action/citation_signature","submit_replication":"https://pith.science/pith/53L4XZZZXX6KOP7FBVVKCXMQHT/action/replication_record"}},"created_at":"2026-07-05T08:30:48.035415+00:00","updated_at":"2026-07-05T08:30:48.035415+00:00"}