{"total":13,"items":[{"citing_arxiv_id":"2606.25079","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FreeStory: Training-Free Character Consistency for Free-Form Visual Storytelling","primary_cat":"cs.CV","submitted_at":"2026-06-23T18:37:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FreeStory reformulates character consistency as entity-grounded feature reuse for free-form prompts, introduces FreeStoryBench, and reports stronger consistency than baselines among training-free methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.24984","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Diachronic Representations of Ancient Greek Letterforms","primary_cat":"cs.LG","submitted_at":"2026-06-23T14:13:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces Hell-Char, PaLit-Char and Med-Char datasets plus a similarity-weighted supervised contrastive loss and lacuna augmentation to learn diachronic embeddings for ancient Greek letterforms.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22625","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DR-Mamba: Automatic Inference-Time Domain Adaptation for Document Image Binarization via Sample-Conditioned Detail-Background Suppression","primary_cat":"cs.CV","submitted_at":"2026-06-21T18:09:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DR-Mamba performs automatic per-document domain adaptation for binarization by modeling fast detail and slow background routes with subtractive suppression in a single forward pass.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.19148","ref_index":141,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Fast Computation of Free-Support Wasserstein Medians","primary_cat":"stat.CO","submitted_at":"2026-06-17T14:50:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Direct fixed-weight solver for free-support Wasserstein medians relocates atoms using OT barycentric projections and inverse-distance weights, achieving monotone descent on smoothed objectives with fewer subproblems than nested Weiszfeld baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.12150","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Tracking atomic-scale interdiffusion in immiscible bimetallic nanoparticles via four-dimensional electron tomography","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-06-10T14:39:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Immiscible PdIr nanoparticles show atomic-scale interdiffusion via surface atom hopping at 200°C, flattening at 300°C, interfacial Ir diffusion at 400°C, and collective mixing at 900°C, observed with 4D electron tomography.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00233","ref_index":97,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Density Evolution: A Multiscale View of Density Estimation","primary_cat":"math.ST","submitted_at":"2026-05-29T18:08:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A review reframing density estimation as 'density evolution' across scales, linking kernel smoothing to heat flow, mixtures to compression, and topology to level sets, while stating three structural results on modes, Gaussian semigroups, and log-concavity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27132","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Image Thresholding: Understanding Bias of Evaluation Metrics towards Specific Evaluation Functions","primary_cat":"cs.CV","submitted_at":"2026-05-26T15:02:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Otsu's between-class variance correlates more strongly with SSIM and PSNR than Kapur's entropy on BSDS500 images, revealing metric-objective bias in multilevel thresholding evaluation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.26564","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Modified Multi-Level Tracking Scheme for the Detection of Sunspot Umbral Dots","primary_cat":"astro-ph.SR","submitted_at":"2026-05-26T05:24:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Modified MLT on Hinode blue continuum images yields 70-90 km smaller median UD diameters and 12-13% fill fractions versus 17-19% for regular MLT, with nearly identical intensity histograms and spatial clustering.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15860","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"On RGB-TIR Stereo Calibration under Extreme Resolution Asymmetry","primary_cat":"cs.CV","submitted_at":"2026-05-15T11:21:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A stereo calibration framework for RGB-TIR cameras with 625:1 resolution asymmetry uses an active OLED screen, Hessian-based corner detection, and baseline-constrained bundle adjustment to achieve 0.382 px reprojection error.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12116","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MPEX AI Digital Twins Milestone Report","primary_cat":"physics.plasm-ph","submitted_at":"2026-05-12T13:31:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":1.0,"formal_verification":"none","one_line_summary":"The MPEX AI Digital Twins project reports that its two phase-I AI milestones for hot-spot control and damage assessment are on track for June 2026 demonstration.","context_count":1,"top_context_role":"background","top_context_polarity":"support","context_text":"Segmentation is performed usingtriangle thresholding[37]. This method is well suited to the present setting, where crack pixels form a small fraction of the image and appear as a low-population tail extending from a dominant background mode. In such unimodal but skewed histograms, variance-based methods such as Otsu's method can become unreliable, particularly when the foreground is sparse [16, 22]. The triangle method instead determines the threshold geometrically from the histogram shape, providing a robust and fully automatic separation of crack and background regions. Post-processing is applied to refine the resulting binary mask. Small isolated components are removed to eliminate spurious detections arising from residual texture or noise."},{"citing_arxiv_id":"2605.00363","ref_index":261,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Profile Likelihood Inference for Anisotropic Hyperbolic Wrapped Normal Models on Hyperbolic Space","primary_cat":"math.ST","submitted_at":"2026-05-01T02:54:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"The profile maximum likelihood estimator for the location in anisotropic hyperbolic wrapped normal models is strongly consistent, asymptotically normal, and attains the Hájek-Le Cam minimax lower bound under squared geodesic loss.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.09233","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A GPU-enhanced workflow for non-Fourier SENSE reconstruction","primary_cat":"eess.IV","submitted_at":"2026-04-10T11:41:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A public GPU workflow for non-Fourier SENSE MRI reconstruction with sensitivity and off-resonance mapping enables fast, accurate imaging from challenging spiral trajectories.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"When using long readouts, especially in combination with spiral trajectories [2, 11, 23, 22, 19],B 0 arti- facts increasingly impair image fidelity [64, 50, 9, 19, 42]. Although several correction methods operating on already reconstructed images have been suggested [35, 3], full correction of these artifacts can only be achieved during image reconstruction if parallel imaging is used [42]. Spirals, among many other non-Cartesian trajectories [31, 65, 13], offer a high encoding efficiency [23]. However, the reconstruction of non-Cartesian k-space data requires additional effort as the fast Fourier transform (FFT) cannot be applied directly [46, 32, 51]. Additionally, due to the imperfections of the gradient system, the effective k-space trajectory may not traverse k-space on a Cartesian grid, even when"},{"citing_arxiv_id":"2603.02087","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Detection-Gated Pipeline for Robust Glottal Area Waveform Extraction and Clinical Pathology Assessment","primary_cat":"cs.CV","submitted_at":"2026-03-02T17:05:41+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A detection-gated YOLOv8n-U-Net pipeline extracts glottal area waveforms from high-speed endoscopy videos, achieving cross-dataset DSC of 0.745 and using area coefficient of variation to distinguish healthy from pathological cases in a 40-subject study.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}