{"total":31,"items":[{"citing_arxiv_id":"2607.02416","ref_index":29,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"The Future of NLP may not be at NLP Conferences: Scholarly Migration Patterns in Natural Language Processing","primary_cat":"cs.CL","submitted_at":"2026-07-02T16:47:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"NLP authors show migration from *ACL flagship tracks (–19.2pp) to Findings (+14.8pp) and ML venues (+8.6pp), with new authors increasing ML share from 5% to 21% and causal inference indicating a citation premium drives venue choice.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.26246","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Lacuna: A Research Map for Machine Learning","primary_cat":"cs.DL","submitted_at":"2026-06-24T18:00:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Lacuna is an LLM-powered research map for ML that outperforms OpenScholar on retrieval benchmarks and GPT-Researcher on multi-stage report generation tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.25674","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"BitNet Text Embeddings","primary_cat":"cs.CL","submitted_at":"2026-06-24T10:37:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"BITEMBED converts LLM backbones to ternary BitNet-style encoders, adapts them with contrastive pre-training and teacher distillation, and produces text embeddings at multiple precisions that perform comparably to full-precision baselines on MMTEB.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.24725","ref_index":23,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Reproducible Benchmark and Evidence-Retrieval Software Framework for Silicon Detector R&D Literature","primary_cat":"physics.ins-det","submitted_at":"2026-06-23T15:49:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Introduces a reproducible benchmark and hybrid sparse-dense retrieval framework for evidence-grounded access to silicon detector literature, reporting Hit@5 of 0.917 on core queries.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22610","ref_index":72,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PaperClaw: Harnessing Agents for Autonomous Research and Human-in-the-Loop Refinement","primary_cat":"cs.AI","submitted_at":"2026-06-21T17:37:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PAPERCLAW is a multi-agent system for end-to-end autonomous research paper generation from literature to output, with human refinement and LLM-judge evaluation showing strong results.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22342","ref_index":2,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"How Does Research Evolve? Tracing Cross-Domain Trajectories in NLP, ML, and CV with Claim-Grounded Typed Citations","primary_cat":"cs.CL","submitted_at":"2026-06-21T05:20:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SciTraj is the first claim-grounded typed citation graph with 32,559 papers and 573,126 edges across six relation types, plus a temporally split link-prediction benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18508","ref_index":36,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval","primary_cat":"cs.CL","submitted_at":"2026-06-16T21:50:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MCompassRAG adds topic metadata to chunk representations and uses LLM distillation to train a lightweight topic-aware retriever, reporting 8.24% average information efficiency gain and over 5x lower latency than strong baselines across six benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18381","ref_index":24,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG","primary_cat":"cs.CL","submitted_at":"2026-06-16T18:28:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SproutRAG introduces an attention-guided hierarchical framework that constructs a binary chunking tree for multi-granularity retrieval in RAG systems and reports a 6.1% average gain in information efficiency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05693","ref_index":80,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MolE-RAG: Molecular Structure-Enhanced Retrieval-Augmented Generation for Chemistry","primary_cat":"cs.LG","submitted_at":"2026-06-04T04:19:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MolE-RAG is a training-free RAG framework that augments LLMs with literature, molecular context, and structural analogs to improve performance on nine molecular property prediction tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03919","ref_index":193,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Forecasting Conceptual Diffusion in Science: The Case of Quantum Computing","primary_cat":"cs.SI","submitted_at":"2026-06-02T17:12:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LightGBM models on citation and diversity features predict exogenous diffusion of quantum computing concepts with R² up to 0.78 while endogenous reinforcement remains largely unpredictable after growth controls, with replications in other fields.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03864","ref_index":192,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Explainable Forecasting of Scientific Breakthroughs from Concept Network Dynamics","primary_cat":"cs.SI","submitted_at":"2026-06-02T16:38:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A two-stage LightGBM model on 59 features from concept networks forecasts link formation and intensity with ROC-AUC 0.95-0.967 across domains.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28190","ref_index":10,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness","primary_cat":"cs.CL","submitted_at":"2026-05-27T09:11:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"HTEB introduces dynamic, multi-axis evaluation of text embedding robustness using LLM transformations, finding decoupled profiles across models and that scaling does not close all robustness gaps.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18752","ref_index":81,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Traditional statistical representations outperform generative AI in identifying expert peer reviewers","primary_cat":"cs.IR","submitted_at":"2026-05-18T17:59:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TF-IDF identifies labeled experts in the top 25 recommendations 79.5% of the time versus 51.5% for GPT-4o mini on an astronomy observatory dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17379","ref_index":86,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization","primary_cat":"cs.CL","submitted_at":"2026-05-17T10:45:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Vocabulary adaptation via targeted token addition and replacement improves semantic similarity, domain word usage, and training efficiency for LLM summarization in legal and medical domains.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16608","ref_index":19,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios","primary_cat":"cs.LG","submitted_at":"2026-05-15T20:17:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Truncated embeddings from non-MRL models perform comparably to or better than MRL-trained models for most truncation levels, except heavy truncation of 80% or more.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11258","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Unlocking LLM Creativity in Science through Analogical Reasoning","primary_cat":"cs.AI","submitted_at":"2026-05-11T21:35:44+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Analogical reasoning increases LLM solution diversity by 90-173% and novelty rate to over 50%, delivering up to 13-fold gains on biomedical tasks including perturbation prediction and cell communication.","context_count":1,"top_context_role":"other","top_context_polarity":"unclear","context_text":"com/science/article/pii/S2405844023027779. [10] Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, and Daniel S. Weld. Specter: Document-level representation learning using citation-informed transformers, 2020. URL https://arxiv.org/abs/2004.07180. [11] Elvis Dohmatob, Yunzhen Feng, Arjun Subramonian, and Julia Kempe. Strong model collapse, 2024. URLhttps://arxiv.org/abs/2410.04840. [12] Ethical Explorations. Is our solar system just a giant atom? Facebook post, 2025. https://www.facebook.com/ethicalexploration/posts/122196896288285338 [Ac- cessed: 2026-03-23]. [13] Dan Friedman and Adji Bousso Dieng. The vendi score: A diversity evaluation metric for machine learning, 2023. URLhttps://arxiv.org/abs/2210.02410. [14] Dedre Gentner."},{"citing_arxiv_id":"2605.09012","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Re$^2$Math: Benchmarking Theorem Retrieval in Research-Level Mathematics","primary_cat":"cs.AI","submitted_at":"2026-05-09T15:52:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Re²Math is a new benchmark that evaluates AI models on retrieving and verifying the applicability of theorems from math literature to advance steps in partial proofs, accepting any sufficient theorem while controlling for leakage.","context_count":1,"top_context_role":"background","top_context_polarity":"unclear","context_text":"3 Oracle Rescue: Matroidal Locus and Cubic Threefold Compactifications Instance. 1510.08891_gap_1.Paper.Complete moduli of cubic threefolds and their intermediate Jacobians.Domain.Algebra / number theory. Proof situation.The proof needs a toroidal-compactification fact to show that the extended intermediate- Jacobian map lands in the correct compactification locus. Reference witness.The matroidal locus Matr[5] is the maximal partial compactification contained in both the second V oronoi and perfect-cone compactifications; equivalently,ΣV ∩Σ P = Σmat. Construction citation.Melo-Viviani,Comparing perfect and 2nd Voronoi decompositions: the matroidal locus. Model behavior. 29 Model Query Plan Query Cite@20 Ground Suff Tool Selected source GPT-5.2 cubic threefold monodromy cones N N N N N N Moduli space via degenerations"},{"citing_arxiv_id":"2605.04495","ref_index":3,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation","primary_cat":"cs.CL","submitted_at":"2026-05-06T04:51:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CAR reranks documents in RAG by promoting those that increase generator confidence (via answer consistency sampling) and demoting those that decrease it, yielding NDCG@5 gains on BEIR datasets that correlate with F1 improvements.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.03861","ref_index":11,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Aspect-Aware Content-Based Recommendations for Mathematical Research Papers","primary_cat":"cs.IR","submitted_at":"2026-05-05T15:23:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The authors introduce aspect-aware datasets GoldRiM and SilverRiM for math papers and AchGNN, a heterogeneous GNN that outperforms prior methods by jointly modeling textual semantics, citations, and author lineage across aspects.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"to produce recommendations. However, their quadratic computa- tional complexity makes them impractical for large-scale datasets, and they have shown limited ability to distinguishaspectscompared to embedding-based retrieval [ 37, 38]. Early TF-IDF embedding- based retrieval methods [7, 8] were outperformed [30, 37, 46] by fine-tuned models SciBERT [4] and SPECTER [11]. Although fine- tuned embeddings consistently outperform general-purpose mod- els, prior work has not addressed mathematical CbRPR. The empir- ical success of existingaspect-based CbRPR methods has largely been demonstrated on datasets 1 drawn from CS and BM, which dominate current benchmarks and typically follow the Introduction- Method-Results-Discussion (IMRD) structure [22, 40]."},{"citing_arxiv_id":"2604.27037","ref_index":9,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrieval","primary_cat":"cs.IR","submitted_at":"2026-04-29T17:05:53+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Reproducibility study confirms Hypencoder's non-linear query-specific scoring improves retrieval over bi-encoders on standard benchmarks but standard methods remain faster and hard-task results are mixed due to implementation issues.","context_count":1,"top_context_role":"dataset","top_context_polarity":"use_dataset","context_text":"evaluation metrics, and implementation specifics. The setup for the extension experiments is described separately in Section 4.6. 4.1 Datasets In-Domain evaluation.We evaluate on the MS MARCO Passage Ranking dataset [ 36], which contains approximately 7k queries with shallow relevance labels over a corpus of 8.8M passages. We also evaluate on the TREC Deep Learning 2019 [ 9] and 2020 [8] passage datasets, which share the same corpus but provide deeper annotations over a smaller set of queries (97 queries combined). Out-of-Domain evaluation.The original paper evaluates out-of- domain performance on five selected BEIR datasets. To provide a more comprehensive assessment of out-of-domain generalization, we extend this evaluation to all 13 publicly available datasets in the"},{"citing_arxiv_id":"2604.24608","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models","primary_cat":"cs.IR","submitted_at":"2026-04-27T15:36:54+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RouteHead trains a lightweight router to dynamically select optimal LLM attention heads per query for improved attention-based document re-ranking.","context_count":1,"top_context_role":"dataset","top_context_polarity":"use_dataset","context_text":"This regularizer discourages uniformly high activation probabilities across heads. Thus the total objective is L=L route + Lsparse (10) 4 Experiments 4.1 Experimental Setup Datasets.We evaluate on two benchmarks. The first is BEIR [38] with eleven sub-datasets across diverse domains: NQ [14], COVID [43], NFCorpus [1], FiQA [19], SciFact [44], SciDocs [4], FEVER [39], Climate [5], DBPedia [8], Robust04 [10] and News. The second is BRIGHT [35], a reasoning-intensive retrieval benchmark with 1,385 real-world queries from multiple domains (e.g., StackExchange, LeetCode, and math competitions). Baselines.We compare our approach with baselines from two paradigms: the generation-based methodRankGPT[ 37] and the attention-based methodsICR[ 2],QRhead[ 53], andCoRehead[ 41]."},{"citing_arxiv_id":"2604.24071","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PeeriScope: A Multi-Faceted Framework for Evaluating Peer Review Quality","primary_cat":"cs.CL","submitted_at":"2026-04-27T05:56:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"PeeriScope is an open modular framework that integrates structured features, LLM rubric assessments, and supervised prediction to evaluate peer review quality for self-assessment, editorial triage, and large-scale auditing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23699","ref_index":1,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Beyond coauthorship: semantic structure and phantom collaborators in transportation research, 1967--2025","primary_cat":"cs.DL","submitted_at":"2026-04-26T13:26:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Phantom collaborators—topically similar authors distant in the coauthor graph—become actual coauthors 16-33 times more often than baselines, with a 68-fold similarity gradient.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17680","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MasterSet: A Large-Scale Benchmark for Must-Cite Citation Recommendation in the AI/ML Literature","primary_cat":"cs.IR","submitted_at":"2026-04-20T00:34:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MasterSet is a new large-scale benchmark for must-cite citation recommendation in AI/ML, using LLM-annotated tiers on 150k papers and Recall@K evaluation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.15150","ref_index":2,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Semantic Geometry for Uncovering Paradigm Dynamics via Scientific Publications","primary_cat":"cs.DL","submitted_at":"2026-04-16T15:31:42+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.06163","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Data, Not Model: Explaining Bias toward LLM Texts in Neural Retrievers","primary_cat":"cs.IR","submitted_at":"2026-04-07T17:57:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Bias toward LLM texts in neural retrievers arises from artifact imbalances between positive and negative documents in training data that are absorbed during contrastive learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.16329","ref_index":1,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Beyond Single-Score Ranking: Facet-Aware Reranking for Controllable Diversity in Paper Recommendation","primary_cat":"cs.IR","submitted_at":"2026-03-11T07:55:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SciFACE improves facet-specific paper ranking NDCG scores by training separate cross-encoders for Background and Method similarity on 5,891 GPT-4o-mini labeled pairs, outperforming SPECTER by up to 31 points.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.06668","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Contradictions in Context: Challenges for Retrieval-Augmented Generation in Healthcare","primary_cat":"cs.IR","submitted_at":"2025-11-10T03:27:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Contradictions between highly similar medical abstracts degrade the factual accuracy and consistency of LLM responses in retrieval-augmented generation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.07847","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems","primary_cat":"cs.CL","submitted_at":"2025-07-10T15:26:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Coreference resolution improves retrieval relevance and QA performance in RAG systems, with mean pooling performing best and smaller models benefiting more.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2409.14634","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation","primary_cat":"cs.HC","submitted_at":"2024-09-23T00:09:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Scideator enables facet-based scientific ideation through LLM-driven extraction, human-guided recombination, analogous retrieval, and facet-grounded novelty verification, showing significantly higher creativity support than a baseline LLM in a user study with CS researchers.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"• An automated evaluation of our novelty checker highlighting its advantages compared to other baselines and ablations. Scideator: Human-LLM Scientific Idea Generation and Novelty Evaluation Grounded in Research-Paper Facet Recombination , , 2 RELATED WORK 2.1 Divergent and Convergent Thinking In ideation, there are two main stages of thinking: divergent and convergent [15, 60]. While engaging in divergent thinking, the ideator is not worried about generating the most high-quality ideas. Instead, they aim to produce as many ideas as possible in an effort to leave no stone unturned in considering potential ideas. At this stage of the ideation process, avoiding fixation on familiar concepts is important [18, 57]. Otherwise, the ideator may miss strong can-"},{"citing_arxiv_id":"2401.03563","ref_index":15,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Data-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning","primary_cat":"cs.CL","submitted_at":"2024-01-07T18:12:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Data-CUBE applies a two-level curriculum (TSP-based task ordering via simulated annealing plus difficulty-sorted mini-batches) to multi-task instruction tuning and reports gains on MTEB sentence representation tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}