{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FCUFKSPVOT4QPQJHKFLORLPSJG","short_pith_number":"pith:FCUFKSPV","schema_version":"1.0","canonical_sha256":"28a85549f574f907c1275156e8adf249b43e9835d430f2ca046780700561cd1f","source":{"kind":"arxiv","id":"2502.06600","version":2},"attestation_state":"computed","paper":{"title":"Evaluation of Multilingual Image Captioning: How far can we get with CLIP models?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bruno Martins, Chrysoula Zerva, Gon\\c{c}alo Gomes","submitted_at":"2025-02-10T16:00:00Z","abstract_excerpt":"The evaluation of image captions, looking at both linguistic fluency and semantic correspondence to visual contents, has witnessed a significant effort. Still, despite advancements such as the CLIPScore metric, multilingual captioning evaluation has remained relatively unexplored. This work presents several strategies, and extensive experiments, related to evaluating CLIPScore variants in multilingual settings. To address the lack of multilingual test data, we consider two different strategies: (1) using quality aware machine-translated datasets with human judgements, and (2) re-purposing mult"},"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":"2502.06600","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T16:00:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1297a7e2f7c10bd06cc24b1ce30bc80a2ead461a27017f78eaa9e1223365af85","abstract_canon_sha256":"089ed61e0d81c519ee8e67b97193f06a31fff3be65ddbd95e0b73447386c56d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:26.051945Z","signature_b64":"Wr6mU4HnGX8CCCOdJl/w7HEvioKXrkWlW3lzUdrVpxUYuwByGrlEJvLL0n0Hv8eDzM+RtSLwF1vFxbzVOtxpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28a85549f574f907c1275156e8adf249b43e9835d430f2ca046780700561cd1f","last_reissued_at":"2026-07-05T10:15:26.051404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:26.051404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of Multilingual Image Captioning: How far can we get with CLIP models?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bruno Martins, Chrysoula Zerva, Gon\\c{c}alo Gomes","submitted_at":"2025-02-10T16:00:00Z","abstract_excerpt":"The evaluation of image captions, looking at both linguistic fluency and semantic correspondence to visual contents, has witnessed a significant effort. Still, despite advancements such as the CLIPScore metric, multilingual captioning evaluation has remained relatively unexplored. This work presents several strategies, and extensive experiments, related to evaluating CLIPScore variants in multilingual settings. To address the lack of multilingual test data, we consider two different strategies: (1) using quality aware machine-translated datasets with human judgements, and (2) re-purposing mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06600","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/2502.06600/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":"2502.06600","created_at":"2026-07-05T10:15:26.051465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06600v2","created_at":"2026-07-05T10:15:26.051465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06600","created_at":"2026-07-05T10:15:26.051465+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCUFKSPVOT4Q","created_at":"2026-07-05T10:15:26.051465+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCUFKSPVOT4QPQJH","created_at":"2026-07-05T10:15:26.051465+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCUFKSPV","created_at":"2026-07-05T10:15:26.051465+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/FCUFKSPVOT4QPQJHKFLORLPSJG","json":"https://pith.science/pith/FCUFKSPVOT4QPQJHKFLORLPSJG.json","graph_json":"https://pith.science/api/pith-number/FCUFKSPVOT4QPQJHKFLORLPSJG/graph.json","events_json":"https://pith.science/api/pith-number/FCUFKSPVOT4QPQJHKFLORLPSJG/events.json","paper":"https://pith.science/paper/FCUFKSPV"},"agent_actions":{"view_html":"https://pith.science/pith/FCUFKSPVOT4QPQJHKFLORLPSJG","download_json":"https://pith.science/pith/FCUFKSPVOT4QPQJHKFLORLPSJG.json","view_paper":"https://pith.science/paper/FCUFKSPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06600&json=true","fetch_graph":"https://pith.science/api/pith-number/FCUFKSPVOT4QPQJHKFLORLPSJG/graph.json","fetch_events":"https://pith.science/api/pith-number/FCUFKSPVOT4QPQJHKFLORLPSJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCUFKSPVOT4QPQJHKFLORLPSJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCUFKSPVOT4QPQJHKFLORLPSJG/action/storage_attestation","attest_author":"https://pith.science/pith/FCUFKSPVOT4QPQJHKFLORLPSJG/action/author_attestation","sign_citation":"https://pith.science/pith/FCUFKSPVOT4QPQJHKFLORLPSJG/action/citation_signature","submit_replication":"https://pith.science/pith/FCUFKSPVOT4QPQJHKFLORLPSJG/action/replication_record"}},"created_at":"2026-07-05T10:15:26.051465+00:00","updated_at":"2026-07-05T10:15:26.051465+00:00"}