{"record": {"aliases": ["Auditory Illusion Benchmark for Large Audio Language Models"], "artifacts": [{"id": "arxiv:2609.02277", "kind": "paper", "url": "https://arxiv.org/abs/2609.02277"}, {"id": "gh:gillosae/aib", "kind": "repo", "url": "https://github.com/gillosae/aib"}], "authors": ["Hayoon Kim", "Eunice Hong", "Kyogu Lee"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.02277", "source_url": "https://arxiv.org/abs/2609.02277"}, "categories": ["Factuality", "General AI", "Speech & Audio", "cs.SD"], "description": {"en": "Evaluates large audio language models on 14,829 forced-choice trials across ten auditory illusions, scoring human-likeness and reality alignment."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.02277", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.02277", "title": "AIB"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.02277", "modality": null, "name": "AIB", "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": "true", "origin_record_id": "bm_auditory-illusion-benchmark-for-large-audi_9ce2461b", "origin_source": "arxiv", "recognition_confidence": "0.7", "record_sha256": "f5b75ae49908263e71f373ebf2ca59e8ba89a72368af4242541940d6c4c04c6a", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-04T00:46:59.007339Z", "source_url": "https://arxiv.org/abs/2609.02277"}, "publisher": null, "released": "2026-09-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.02277", "source_url": "https://arxiv.org/abs/2609.02277"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-02277", "source": "claire_radar", "source_benchmark_id": "2609.02277", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Auditory Illusion Benchmark for Large Audio Language Models"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Speech & Audio", "attention": {"asOf": "2026-09-03", "attemptedAt": "2026-09-03T06:34:20.331209Z", "githubRepo": "https://github.com/gillosae/aib", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.02277", "observedAt": "2026-09-03T06:34:20.331209Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-03T06:34:20.331209Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-03T06:34:20.331209Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Unique auditory illusion benchmark with accessible code and multiple evaluated models likely to interest audio and multimodal model researchers.", "score": 55}, "capabilities": ["Factuality"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-04T00:46:59.007339Z", "inputHash": "b213c988153078f3bdcbd5afa3cb34fca3edb03bb019f6eb73e3953f14967870", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "To this end, we present AIB, the first auditory illusion benchmark for LALMs, covering ten representative illusions across music, sound, and speech, each annotated for the presence of knowledge-based priors.", "canonicalNameSource": "abstract", "decisionReason": "Provides a clear scoring protocol (HLA, RA, ISI), code repository with detailed instructions, and a stable evaluation contract for model comparison.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-04T00:46:59.007339Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates large audio language models on 14,829 forced-choice trials across ten auditory illusions, scoring human-likeness and reality alignment.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To this end, we present AIB, the first auditory illusion benchmark for LALMs, covering ten representative illusions across music, sound, and speech, each annotated for the presence of knowledge-based priors."}, "familyId": "bmf_25b5b13e4b9a", "firstSeenAt": "2026-09-03", "heat": null, "id": "bm_auditory-illusion-benchmark-for-large-audi_9ce2461b", "indexedAt": "2026-09-03T00:55:28.123857Z", "industrySectors": [], "links": {"code": "https://github.com/gillosae/aib", "data": null, "paper": "https://arxiv.org/abs/2609.02277", "pdf": "https://arxiv.org/pdf/2609.02277", "project": null, "report": "https://arxiv.org/abs/2609.02277"}, "metrics": [], "motivation": "Perceptual illusions have long served as crucial probes into human cognition, revealing biases and limitations of perception.", "name": "AIB", "oneLine": "Evaluates large audio language models on 14,829 forced-choice trials across ten auditory illusions, scoring human-likeness and reality alignment.", "paperTitle": "Auditory Illusion Benchmark for Large Audio Language Models", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to the 2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026)", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2609.02277", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026)", "verifiedAt": "2026-09-03T00:55:28.123857Z"}, "publications": [], "publishers": [{"name": "Music and Audio Research Group, Seoul National University", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/gillosae/aib"}], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "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": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 123, "score": 23}, "method": "attention-ranking-v13", "rank": 123, "score": 23}, "90d": {"confidence": "Low", "coverage": 0.55, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 314, "score": 23}, "method": "attention-ranking-v13", "rank": 314, "score": 23}, "today": {"confidence": "Low", "coverage": 0.25, "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": 1, "historyDate": "2026-09-02", "rank": null, "score": null, "windowDays": 1}, "level": {"components": {"githubStars": {"normalization": "percentile", "normalized": 0.25, "percentile": 0.25, "value": 0}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.78, "role": "bonus", "value": 78}}, "confidence": "Low", "coverage": 0.25, "rank": 4, "score": 51}, "method": "attention-ranking-v13", "rank": 4, "score": 51}}, "readiness": "Runnable", "recognitionConfidence": 0.7, "relation": "introduces", "releasedAt": "2026-09-02", "source": {"authors": ["Hayoon Kim", "Eunice Hong", "Kyogu Lee"], "categories": ["cs.SD", "cs.AI"], "id": "2609.02277", "title": "Auditory Illusion Benchmark for Large Audio Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2609.02277"}, "sourceUpdatedAt": "2026-09-02T08:23:36Z", "topics": ["cs.SD"], "venueAttempts": [{"decisionRaw": "Accepted to the 2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026)", "evidence": [{"level": "author-claim", "observedAt": "2026-09-03T00:55:28.123857Z", "rawValue": "Accepted to the 2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026)", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2609.02277"}], "reviewStatus": "accepted", "venueName": "2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026)"}], "whyItMatters": "Bridges gap in auditory perception evaluation by testing whether models share human misperceptions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
