{"total":20,"items":[{"citing_arxiv_id":"2607.08177","ref_index":16,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ASMR: Agentic Schema Generation for Ship Maintenance Report Writing","primary_cat":"cs.AI","submitted_at":"2026-07-09T07:25:28+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ASMR extracts concepts with an LLM, clusters them into candidate fields, then uses RL to select compact non-redundant schemas for each ship-report form type.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.01468","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CADENZA in Action: Breaking the Monolith with Intent-Dependent Plan Spaces for Semantic Queries","primary_cat":"cs.DB","submitted_at":"2026-07-01T21:00:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CADENZA demonstrates an optimizer that breaks semantic query intents into alternative plans, selects implementations per step, and optimizes under user preferences via a web interface.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29532","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SemJoin: Semantic Join Optimization","primary_cat":"cs.DB","submitted_at":"2026-06-28T17:57:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SemJoin dynamically routes semantic joins via an LLM advisor to Cluster Join or Classifier strategies, achieving 20-33 higher F1 than ABJ and lower token cost than FDJ on three datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21831","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RAIDS: Rethinking Data Systems as Responsible Intelligent Infrastructure","primary_cat":"cs.DB","submitted_at":"2026-06-20T01:54:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RAIDS proposes making responsibility an execution-level property in data systems via composable operator contracts and a preservation objective.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28365","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval","primary_cat":"cs.IR","submitted_at":"2026-06-14T16:59:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CAMI frames multi-index construction for semantic retrieval as a budgeted multi-objective portfolio problem and uses agent-guided search plus confidence-aware pruning to find high-recall configurations with reduced evaluation cost.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08090","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase Method","primary_cat":"cs.DB","submitted_at":"2026-06-06T10:32:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"An adaptive two-phase semantic filter using clustering then a hybrid proxy trained on LLM confidence achieves 1.6-2.0x speedup over prior methods at 90% accuracy on 10K document corpora.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07923","ref_index":56,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Larch: Learned Query Optimization for Semantic Predicates","primary_cat":"cs.DB","submitted_at":"2026-06-06T01:16:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Larch uses a GNN-MDP formulation and a selectivity predictor plus dynamic programming to reorder semantic filter evaluation, cutting token usage 3x-19x versus prior systems on real and synthetic workloads.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02282","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems","primary_cat":"cs.AI","submitted_at":"2026-06-01T14:05:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"POIROT protocol repurposes agents in LLM multi-agent systems as an internal diagnostic layer for failure detection, outperforming single-LLM evaluators with gains that increase with complexity, agent count, and fault types.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21765","ref_index":67,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PrismaDV: Automated Task-Aware Data Unit Test Generation","primary_cat":"cs.LG","submitted_at":"2026-04-23T15:18:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PrismaDV generates task-aware data unit tests by jointly analyzing downstream code and dataset profiles, outperforming task-agnostic baselines on new benchmarks spanning 60 tasks, with SIFTA enabling automatic prompt optimization that beats hand-written prompts.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"tion blocks enabled, and report precision, recall, and F1 score for detecting erroneous batches. 7 Related Work Data validation. Existing data validation systems vary in how rules are specified and inferred. Great Expectations offers a flexi- ble assertion grammar but relies on manually defined expectation suites, limiting automation. Deequ [61] and TFDV [67] infer statis- tical constraints via data profiling, while Auto-Test [7] and Auto- Validate [70] learn semantic constraints from large table corpora, with Auto-Validate focusing on string columns. These approaches are largely task-agnostic and depend primarily on observed data. DataPrism [19] incorporates downstream systems, using causal reasoning to identify data-profile violations that trigger failures."},{"citing_arxiv_id":"2604.17815","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Navigating the Conceptual Multiverse","primary_cat":"cs.HC","submitted_at":"2026-04-20T05:12:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"The conceptual multiverse system with a verification framework for decision structures helps users in philosophy, AI alignment, and poetry build clearer working maps of open-ended problems by making implicit LLM choices explicit and changeable.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.15233","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Blue Data Intelligence Layer: Streaming Data and Agents for Multi-source Multi-modal Data-Centric Applications","primary_cat":"cs.AI","submitted_at":"2026-04-16T17:10:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Blue DIL is a new architecture that unifies structured enterprise data, LLM world knowledge, and personal context through declarative query plans and agents for multi-source multi-modal applications.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.09944","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PLOP: Cost-Based Placement of Semantic Operators in Hybrid Query Plans","primary_cat":"cs.DB","submitted_at":"2026-04-10T22:51:41+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PLOP is a cost-based optimizer that finds optimal placements for semantic LLM operators in hybrid query plans via dynamic programming, delivering up to 1.5x speedup and 4.29x cost reduction on 44 benchmark queries while preserving accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.04479","ref_index":56,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"How can LLMs Support Policy Researchers? Evaluating an LLM-Assisted Workflow for Large-Scale Unstructured Data","primary_cat":"cs.HC","submitted_at":"2026-04-06T07:04:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"An LLM-assisted workflow scales thematic analysis of millions of online posts and interviews, yielding themes that align and diverge from authoritative policy reports and serving as rough input for policy researchers.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.02690","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysis","primary_cat":"cs.IR","submitted_at":"2026-04-03T03:34:19+00:00","verdict":"REJECT","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"AnnoRetrieve induces annotation schemas from documents and answers queries via structured retrieval, reporting F1 0.87 with lower LLM cost than graph/LLM baselines but higher cost than QUEST and vector search.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"semantic understanding with structured reasoning 2 Related Work 2.1 Document Analysis for Structured Retrieval Transforming raw documents into a queryable format is a prerequi- site for any retrieval system. A mature ecosystem of document pars- ing and layout analysis tools exists to digitize and initially structure content. Frameworks like DeepDoctection [20] and DocETL [18] provide robust pipelines for complex documents, performing OCR, layout analysis, table extraction, and text block classification to reconstruct logical document structure. General-purpose tools like Unstructured.io [21] offer a unified interface to parse diverse file formats into clean text. These tools are often positioned as the first step in a Retrieval-"},{"citing_arxiv_id":"2604.02655","ref_index":55,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Semantic Data Processing with Holistic Data Understanding","primary_cat":"cs.DB","submitted_at":"2026-04-03T02:37:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HoldUp uses LLM-guided clustering to provide holistic dataset context for semantic operators, yielding up to 33% higher classification accuracy and 30% higher scoring accuracy than row-by-row LLM processing across 15 datasets.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"label? improving data quality and data mining using multiple, noisy labelers. InProceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining. 614-622. [54] Snoflake. 2025. Introducing Cortex AISQL: Reimagining SQL into AI Query Language for Multimodal Data. https://www.snowflake.com/en/blog/ai-sql- query-language/. [55] Xiaofei Sun, Xiaoya Li, Jiwei Li, Fei Wu, Shangwei Guo, Tianwei Zhang, and Guoyin Wang. 2023. Text Classification via Large Language Models. InFindings of the Association for Computational Linguistics: EMNLP 2023, Houda Bouamor, Juan Pino, and Kalika Bali (Eds.). Association for Computational Linguistics, Singapore, 8990-9005. https://doi.org/10.18653/v1/2023."},{"citing_arxiv_id":"2603.15970","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models","primary_cat":"cs.DB","submitted_at":"2026-03-16T22:42:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Lightweight proxy models deliver over 100x cost and latency savings for semantic AI queries in databases with accuracy preserved or improved on benchmarks up to 10M rows.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.16432","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"iPDB -- Optimizing Semantic SQL Queries","primary_cat":"cs.DB","submitted_at":"2026-01-23T04:11:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"iPDB adds a predict operator and semantic query optimizations to SQL so that LLM and ML calls run efficiently inside the database, delivering 2.5x average and up to 30x speedup over prior systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.12610","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ScaleDoc: Scaling LLM-based Predicates over Large Document Collections","primary_cat":"cs.DB","submitted_at":"2025-09-16T03:18:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ScaleDoc achieves over 2x end-to-end speedup and up to 85% fewer LLM invocations for semantic predicates on large document collections via offline LLM representations, contrastive-trained proxy filtering, and adaptive cascades.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.00303","ref_index":59,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Access Paths for Efficient Ordering with Large Language Models","primary_cat":"cs.DB","submitted_at":"2025-08-30T01:44:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces the LLM ORDER BY semantic operator with algorithmic improvements, a semantic-aware external merge sort, and a budget-aware optimizer that selects near-optimal access paths for LLM-based ordering.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2508.05012","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Making Prompts First-Class Citizens for Adaptive LLM Pipelines","primary_cat":"cs.DB","submitted_at":"2025-08-07T03:49:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SPEAR proposes structured prompt views, runtime adaptive refinement, and policy rules to make prompts first-class, versioned, and evolvable components in complex LLM applications.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}