{"record": {"aliases": ["Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessment"], "artifacts": [{"id": "arxiv:2609.02573", "kind": "paper", "url": "https://arxiv.org/abs/2609.02573"}, {"id": "hf:pino10010/tic-bench", "kind": "dataset", "url": "https://huggingface.co/datasets/pino10010/TIC-Bench"}], "authors": ["Zihao Wang", "Xi Xiang", "Yuwen Sun", "Yingyu Li", "Yabo Zhang", "Yihan Zeng", "Fan Li", "Wangmeng Zuo"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.02573", "source_url": "https://arxiv.org/abs/2609.02573"}, "categories": ["General AI", "Multimodal"], "description": {"en": "Evaluates multimodal LLM capability to integrate text-image clues and recover facts within deeply interleaved contexts."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.02573", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.02573", "title": "TIC-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Harbin Institute of Technology", "Huawei Technologies (China)", "Nankai University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.02573", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.02573", "source_url": "https://openalex.org/W7207865608"}, "key": "claire-radar:2609.02573", "modality": null, "name": "TIC-Bench", "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_deeply-interleaved-text-image-contexts-for_43c50b59", "origin_source": "arxiv", "recognition_confidence": "0.7", "record_sha256": "7b3a86d67999882fcf54dbcc494649e12779f526227e7c533987593f40c4be00", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-04T00:46:59.007339Z", "source_url": "https://arxiv.org/abs/2609.02573"}, "publisher": null, "released": "2026-09-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.02573", "source_url": "https://arxiv.org/abs/2609.02573"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-02573", "source": "claire_radar", "source_benchmark_id": "2609.02573", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessment"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-09-03", "attemptedAt": "2026-09-03T06:34:20.331209Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": "pino10010/TIC-Bench", "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.02573", "observedAt": "2026-09-02T06:30:32.214812Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"checkedAt": "2026-09-03T06:34:20.331209Z", "state": "unavailable"}, "hfDatasetLikes": {"checkedAt": "2026-09-03T06:34:20.331209Z", "state": "unavailable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-03T06:34:20.331209Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Accessible dataset may draw initial interest but no verified scoring details are provided.", "score": 40}, "capabilities": [], "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": "c2d3d0eca6fc2dd697f87d627d6b84e58cc92dcb0db839f12d7df4f38b1b8383", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "we introduce a novel benchmark, TIC-Bench (deeply interleaved Text-Image Contexts), designed to evaluate the capability of models to integrate text-image clues", "canonicalNameSource": "abstract", "decisionReason": "Data is available on Hugging Face but the link status is unverified, making the full evaluation and scoring contract unclear. No independent paper or official site is supplied.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-04T00:46:59.007339Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates multimodal LLM capability to integrate text-image clues and recover facts within deeply interleaved contexts.", "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", "public artifact URL"], "snippet": "To bridge this gap, we introduce a novel benchmark, TIC-Bench (deeply interleaved Text-Image Contexts), designed to evaluate the capability of models to integrate text-image clues and recover the ground truth facts within deeply interleaved contexts."}, "familyId": "bmf_a7af878761cb", "firstSeenAt": "2026-09-03", "heat": null, "id": "bm_deeply-interleaved-text-image-contexts-for_43c50b59", "indexedAt": "2026-09-03T06:05:38.931192Z", "industrySectors": [], "links": {"code": null, "data": "https://huggingface.co/datasets/pino10010/TIC-Bench", "paper": "https://arxiv.org/abs/2609.02573", "pdf": "https://arxiv.org/pdf/2609.02573", "project": null, "report": "https://arxiv.org/abs/2609.02573"}, "metrics": [], "motivation": "Current evaluations and training of multimodal models predominantly focus on multi-image tasks, largely overlooking interleaved text-image scenarios.", "name": "TIC-Bench", "oneLine": "Evaluates multimodal LLM capability to integrate text-image clues and recover facts within deeply interleaved contexts.", "paperTitle": "Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessment", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.02573", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-03T06:05:38.931192Z"}, "publications": [], "ranking": {"30d": {"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": 30}, "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}, "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}, "today": {"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": 1, "historyDate": "2026-09-02", "rank": null, "score": null, "windowDays": 1}, "level": {"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}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.78, "role": "bonus", "value": 78}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": 20}, "method": "attention-ranking-v13", "rank": null, "score": 20}}, "readiness": "Inspectable", "recognitionConfidence": 0.7, "relation": "introduces", "releasedAt": "2026-09-02", "source": {"authors": ["Zihao Wang", "Xi Xiang", "Yuwen Sun", "Yingyu Li", "Yabo Zhang", "Yihan Zeng", "Fan Li", "Wangmeng Zuo"], "categories": ["cs.CV"], "id": "2609.02573", "title": "Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessment", "type": "arxiv", "url": "https://arxiv.org/abs/2609.02573"}, "sourceUpdatedAt": "2026-09-02T13:19:51Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Addresses lack of benchmarks for deeply interleaved text-image contexts."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
