{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.18989", "kind": "paper", "url": "https://arxiv.org/abs/2606.18989"}], "authors": ["Fengying Ye", "Yanming Sun", "Runzhe Zhan", "Zheqi Zhang", "Lidia S. Chao", "Derek F. Wong"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.18989", "source_url": "https://arxiv.org/abs/2606.18989"}, "categories": ["General AI", "Language & Knowledge", "Safety"], "description": {"en": "G-IdiomAlign is a gloss-pivoted benchmark for cross-lingual idiom alignment, with protocols for multiple-choice equivalence and gloss-contrastive generation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.18989", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.18989", "title": "G-IdiomAlign"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Macau"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.18989", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.18989", "source_url": "https://openalex.org/W7165111886"}, "key": "claire-radar:2606.18989", "modality": null, "name": "G-IdiomAlign", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_g-idiomalign_39650ae3", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "59bf35d465be4ded46d28d1973a3a7c47b313aad8591bf4c509a3cd86a73ea68", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.18989"}, "publisher": null, "released": "2026-06-17", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.18989", "source_url": "https://arxiv.org/abs/2606.18989"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-18989", "source": "claire_radar", "source_benchmark_id": "2606.18989", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.18989", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "3ab442b80666c7e46cfee103fb07c7ec581c30864e51b0fac1b83ec948ce2b69", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "G-IdiomAlign is a gloss-pivoted benchmark for cross-lingual idiom alignment, with protocols for multiple-choice equivalence and gloss-contrastive generation.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "We present G-IdiomAlign, a gloss-pivoted benchmark where each idiom is anchored by an English gloss from Wiktionary."}, "familyId": "bmf_eb51932671bc", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_g-idiomalign_39650ae3", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.18989", "paper": "https://arxiv.org/abs/2606.18989", "pdf": "https://arxiv.org/pdf/2606.18989", "project": null, "report": "https://arxiv.org/abs/2606.18989"}, "metrics": [], "motivation": "Idioms are difficult to transfer across languages due to their non-compositionality and weak surface-form grounding, making literal mappings unreliable.", "name": "G-IdiomAlign", "oneLine": "G-IdiomAlign is a gloss-pivoted benchmark for cross-lingual idiom alignment, with protocols for multiple-choice equivalence and gloss-contrastive generation.", "paperTitle": "G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to ACL 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.18989", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ACL 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-17", "source": {"authors": ["Fengying Ye", "Yanming Sun", "Runzhe Zhan", "Zheqi Zhang", "Lidia S. Chao", "Derek F. Wong"], "categories": ["cs.CL", "cs.AI"], "id": "2606.18989", "title": "G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment", "type": "arxiv", "url": "https://arxiv.org/abs/2606.18989"}, "sourceUpdatedAt": "2026-06-17T12:09:00Z", "topics": ["Safety"], "venueAttempts": [{"decisionRaw": "Accepted to ACL 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to ACL 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.18989"}], "reviewStatus": "accepted", "venueName": "ACL 2026"}], "whyItMatters": "Idiom translation is challenging due to non-compositionality. This benchmark could support evaluation of multilingual models, but its public availability and scoring contract are not fully clear."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
