{"record": {"aliases": ["Read the Room, Read the Image: Understanding Indirect Speech Acts in Multimodal Visual Contexts"], "artifacts": [{"id": "arxiv:2608.30270", "kind": "paper", "url": "https://arxiv.org/abs/2608.30270"}], "authors": ["Jaehee Kim", "Ji Hoon Chung", "Seoyoon Park", "Unsol Kim", "Kyungwon Park", "Ji Hak Kim", "Yi-Jun Chen", "Hansaem Kim"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.30270", "source_url": "https://arxiv.org/abs/2608.30270"}, "categories": ["General AI", "Multimodal", "Reasoning"], "description": {"en": "Multimodal benchmark for indirect speech act understanding in visual contexts, supporting English and Korean."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.30270", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.30270", "title": "READI"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.30270", "modality": null, "name": "READI", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "false", "origin_record_id": "bm_read-the-room-read-the-image-understanding_4e0b4326", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "75dc39c4722050740f940aa5b91ee776faaa711624628251303d4100850f6898", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-02T05:23:11.715633Z", "source_url": "https://arxiv.org/abs/2608.30270"}, "publisher": null, "released": "2026-08-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.30270", "source_url": "https://arxiv.org/abs/2608.30270"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-30270", "source": "claire_radar", "source_benchmark_id": "2608.30270", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Read the Room, Read the Image: Understanding Indirect Speech Acts in Multimodal Visual Contexts"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "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/2608.30270", "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"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Cross-lingual pragmatic reasoning is a niche but emerging area; lack of public resources limits initial attention.", "score": 36}, "capabilities": ["Reasoning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "980ab42a2a3148e135795a790a69c3d4af1efe8172a4d734fa282d8e293145e5", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce READI, a multimodal benchmark for evaluating ISA understanding through integrated reasoning over visual con- text and dialogue.", "canonicalNameSource": "abstract", "decisionReason": "No public dataset or code link is provided, making the benchmark's availability unclear.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Multimodal benchmark for indirect speech act understanding in visual contexts, supporting English and Korean.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce READI, a multimodal benchmark for evaluating ISA understanding through integrated reasoning over visual con- text and dialogue."}, "familyId": "bmf_e84b64d05475", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_read-the-room-read-the-image-understanding_4e0b4326", "indexedAt": "2026-09-01T06:28:29.895112Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.30270", "pdf": "https://arxiv.org/pdf/2608.30270", "project": null, "report": "https://arxiv.org/abs/2608.30270"}, "metrics": [], "motivation": "Indirect speech acts (ISAs) require pragmatic reasoning over context, as directive intent can- not be inferred from surface form alone.", "name": "READI", "oneLine": "Multimodal benchmark for indirect speech act understanding in visual contexts, supporting English and Korean.", "paperTitle": "Read the Room, Read the Image: Understanding Indirect Speech Acts in Multimodal Visual Contexts", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to Findings of ACL 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.30270", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "Findings of ACL 2026", "verifiedAt": "2026-09-01T06:28:29.895112Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 0.6, "relation": "introduces", "releasedAt": "2026-08-31", "source": {"authors": ["Jaehee Kim", "Ji Hoon Chung", "Seoyoon Park", "Unsol Kim", "Kyungwon Park", "Ji Hak Kim", "Yi-Jun Chen", "Hansaem Kim"], "categories": ["cs.CL"], "id": "2608.30270", "title": "Read the Room, Read the Image: Understanding Indirect Speech Acts in Multimodal Visual Contexts", "type": "arxiv", "url": "https://arxiv.org/abs/2608.30270"}, "sourceUpdatedAt": "2026-08-31T05:28:32Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [{"decisionRaw": "Accepted to Findings of ACL 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-09-01T06:28:29.895112Z", "rawValue": "Accepted to Findings of ACL 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.30270"}], "reviewStatus": "accepted", "venueName": "Findings of ACL 2026"}], "whyItMatters": "Tests pragmatic reasoning under visual grounding, which is underexplored in current benchmarks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
