{"total":29,"items":[{"citing_arxiv_id":"2606.31664","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sparsity-Inducing Divergence Losses for Biometric Verification","primary_cat":"cs.CV","submitted_at":"2026-06-30T13:42:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Q-Margin encodes margin penalties into the reference measure of an alpha-divergence loss to produce sparse discriminative embeddings for face and speaker verification.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31291","ref_index":120,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Deep Reinforcement Learning for Spacecraft Attitude Control During Atmospheric Re-Entry","primary_cat":"cs.LG","submitted_at":"2026-06-30T08:06:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Hybrid RL-PID controllers track angle of attack better and show greater robustness than PID alone within a defined operational envelope for re-entry attitude control.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31066","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Secure-CHG: A Comprehensive Framework for Robust and Fair Federated Learning via Hybrid Defense and Contribution-Aware Trust","primary_cat":"cs.CR","submitted_at":"2026-06-30T02:53:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Secure-CHG introduces a cascaded defense with statistical filtering early and CHG-Shapley valuation later to mitigate late-stage failure against backdoor attacks in federated learning, reporting 2.3x and 2.0x lower attack success rates than Krum and Trimmed Mean on CIFAR-10, MedMNIST, and NEU-SDDB.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.25369","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis","primary_cat":"cs.SD","submitted_at":"2026-06-24T03:57:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Sarashina2.2-TTS achieves SOTA kanji reading accuracy via data scaling and Joyo-kanji-targeted synthesis, introduces the Joyo Kanji Yomi Benchmark and Kana-CER metric, and shows stable cross-lingual performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.24985","ref_index":143,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection","primary_cat":"cs.LG","submitted_at":"2026-06-23T14:24:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Retrieval from out-of-domain foundation models enables personalization of a lightweight transformer for stress detection, yielding +3.92% accuracy and +4.76% F1 gains on WESAD without user labels.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.19105","ref_index":15,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Smoothness-Based Derandomization of PAC-Bayes Bounds","primary_cat":"cs.LG","submitted_at":"2026-06-17T14:17:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Derives smoothness-based PAC-Bayes derandomization bounds for deterministic predictors using Rademacher complexity of the Jensen gap class, yielding Jacobian/Hessian flatness terms and a practical regularizer tested on CIFAR-10.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18898","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Anomaly Detection for Sparse and Irregular Multivariate Time Series with Latent SDEs","primary_cat":"cs.LG","submitted_at":"2026-06-17T10:17:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Latent SDE generative model for anomaly detection in sparse irregular multivariate time series outperforms baselines on six benchmarks and stays robust under severe sparsity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.13028","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Comparing Commercial Depth Sensor Accuracy for Medical Applications","primary_cat":"cs.RO","submitted_at":"2026-06-11T08:02:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Zivid 2M+ 60 outperformed Intel RealSense D405, PMD Flexx2, and Stereolabs ZED 2i on all tested specimens and metrics; ZED ranked second on real tissue but last on the phantom.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08615","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Harnessing Streaming Video in the Wild","primary_cat":"cs.CV","submitted_at":"2026-06-07T13:00:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Presents Streaming-Train-248K dataset, Streaming Harness system, and Streaming-Eval benchmark to enable VLMs for proactive, memory-equipped streaming video understanding.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02569","ref_index":93,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AdaCodec: A Predictive Visual Code for Video MLLMs","primary_cat":"cs.CV","submitted_at":"2026-06-01T17:56:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AdaCodec introduces a predictive visual code that cuts visual token use in video MLLMs by sending full frames only on high predictive cost and otherwise encoding inter-frame changes as P-tokens, yielding better benchmark scores at lower budgets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00751","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Head-Pose-Aware Visual Speech Recognition with FiLM Modulation","primary_cat":"cs.CV","submitted_at":"2026-05-30T14:35:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HP-VSR-ResFiLM adds a single residual FiLM modulation block conditioned on head pose to a CNN visual encoder, yielding WER of 25.0% on LRS2 and 33.2% on LRS3 under standard training conditions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30993","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue","primary_cat":"eess.AS","submitted_at":"2026-05-29T08:27:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SwanVoice is a zero-shot TTS system for 1-4 speakers that reports higher richness and hierarchy scores than open-source baselines on monologue and dialogue tasks via mixed training and DiffusionNFT post-training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29260","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Deep Psychovisual Image Representations","primary_cat":"cs.CV","submitted_at":"2026-05-28T02:24:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Proposes a psychovisual-inspired deep learning method that encodes images in learned frequency sub-bands for interpretable semantic structures and reduced depth dependence.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.25348","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Parameter-Efficient CT Reconstruction via Deep Graph Laplacian Regularization","primary_cat":"eess.IV","submitted_at":"2026-05-25T02:04:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Deep GLR combines graph Laplacian regularization with three lightweight CNN modules in a proximal optimization framework to reach 30.70 dB PSNR on LoDoPaB-CT using 5.8x fewer parameters and 30x less data per dB gain than typical deep methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.24920","ref_index":24,"ref_count":3,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Quaternion Self-Attention with Shared Scores","primary_cat":"cs.LG","submitted_at":"2026-05-24T07:52:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Shared-score quaternion self-attention reduces score multiplications by 75% and softmax operations from four to one while proving equivalence to component-wise attention under quaternion linear projections.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19965","ref_index":21,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Normative Networks for Source Separation via Local Plasticity and Dendritic Computation","primary_cat":"cs.LG","submitted_at":"2026-05-19T15:15:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Predictive Entropy Maximization performs competitive blind source separation using only local error-driven and Hebbian updates derived from a surrogate entropy objective with spectral error bounds.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18483","ref_index":111,"ref_count":4,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Modality vs. Morphology: A Framework for Time Series Classification for Biological Signals","primary_cat":"cs.LG","submitted_at":"2026-05-18T14:36:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A review synthesizes evidence from EEG, EMG, ECG, PPG and ocular signals to argue that waveform morphology, rather than modality or model class, primarily determines TSC performance and interpretability.","context_count":2,"top_context_role":"background","top_context_polarity":"background","context_text":"highly dependent on muscle group and electrode placement. In addition to differences in signal content, the data formats, annotations, and auxiliary features vary widely across datasets. Despite the availability of large public corpora, few standard- ized formatting conventions have been widely adopted. One exception is the Brain Imaging Data Structure (BIDS) [143], originally developed for MRI and subsequently extended to EEG [144]; BIDS is now the required standard for datasets distributed via the OpenNeuro platform [145]. Finally, although this review focuses on biological signals, researchers may also benefit from general-purpose time-series benchmarks. The UCR archive [146] includes 128 univariate datasets, while the UEA archive [147] contains 30 multivariate"},{"citing_arxiv_id":"2605.12952","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Debunking Grad-ECLIP: A Comprehensive Study on Its Incorrectness and Fundamental Principles for Model Interpretation","primary_cat":"cs.CV","submitted_at":"2026-05-13T03:35:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Grad-ECLIP is an equivalent but flawed variant of attention-based interpretation, with two principles proposed to ensure model explanations reflect the original model.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12792","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions","primary_cat":"cs.LG","submitted_at":"2026-05-12T22:10:01+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"NTGA is the first clean-label generalization attack under black-box settings but is vulnerable to adversarial training and image transformations, with newer attacks outperforming it.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"augmentation can defeat data poisoning attacks [56, 57]. Huang et al. [40] claimed that the error-minimizing attacks is robust to strong data augmentation techniques, such as CutMix [101], Cutout [21] and mixup [103]. However, Liu et al. [56] showed that the effect of error-minimizing attacks can be mitigated by simple grayscale pre-filtering. Moreover, Borgnia et al. [8] diminished the effect of backdoor attacks [14] using mixup [103] and CutMix [101] data aug- mentation techniques. Hence, data poisoning attacks have unpre- dictable reactions to data augmentation which needs to be explored further. Moreover, certain data augmentation techniques used for image compression such as JPEG compression, SHIELD [19] provide"},{"citing_arxiv_id":"2605.12427","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Minimally Rigid Graphs with High Realization Counts","primary_cat":"cs.LG","submitted_at":"2026-05-12T17:23:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Reinforcement learning with graph neural networks finds minimally rigid graphs that match known planar realization optima and set new records for spherical realization counts.","context_count":1,"top_context_role":"background","top_context_polarity":"support","context_text":"vertices) many times produces construction sequences K2 =G 2 →G 3 → · · · →G n, where each transitionG k →G k+1 is obtained by sampling an extension fromπ θt(· |G k). Extensions are particularly natural choices to define the action spaceA, because a graphGis minimally rigid if andonlyif it can be obtained fromK 2 by a finite sequence of 0- and 1-extensions (see e.g. [SJE18, Theorems 19.2 and 19.11]), whose definition we recall now. LetG= (V, E) be a graph, and letz /∈Vbe a new vertex. Ifu, v∈Vare distinct vertices, then the graph (V∪ {z}, E∪ {uz, vz}) is called a 0-extensionofG. Ifu, v, w∈Vare distinct vertices andvw∈E, then the graph (V∪ {z}, E\\ {vw} ∪ {uz, vz, wz}) is called a 1-extensionofG; for illustration, see Figure 3. Thus, for a transition fromG k"},{"citing_arxiv_id":"2605.07489","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Decomposed Retrieval-Edit-Rerank Framework for Chord Generation","primary_cat":"cs.SD","submitted_at":"2026-05-08T09:29:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The RER framework decomposes chord generation into retrieval, editing, and reranking stages to outperform end-to-end models in balancing stylistic diversity with music-theoretic feasibility.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"have become the dominant approach for chord generation. Bi- LSTM-based models were shown to outperform traditional HMM- based methods by better capturing long-range dependencies in musical sequences [11]. Subsequent works refined this direction by modeling the conditional dependencies between melody and harmony [21], employing masked sequence learning for inpainting tasks [15]. Recently, Transformer-based models have been intro- duced to chord progression generation, modeling global harmonic context [9]. Despite their differences, these two paradigms exhibit comple- mentary strengths and limitations. While symbolic and probabilis- tic models rely on explicit structural representations to ensure harmonic validity, their expressive power and generative diver-"},{"citing_arxiv_id":"2605.07241","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Asymmetric Phase Coding Audio Watermarking","primary_cat":"cs.CR","submitted_at":"2026-05-08T04:54:59+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"at the cost of bandwidth and often synchronization. Classical phase coding [ 23] overwrites phase 2 in the first segment and propagates relative phase; concentrated low-frequency modifications leave detectable footprints [24]. Dynamic phase coding with error-control coding [25], adaptive multi-level phase coding [26], and synchronous multi-bit phase shifting [27] improve robustness. None of these methods provide cryptographic non-repudiation by themselves. Table 1: Qualitative positioning. Rob./Imp./Sig./T-free = robustness, impercep- tibility, public-key signature, training-free. Numeric comparison appears in Table 6. Method Rob. Imp. Sig. T-free LSB ×✓×✓ Echo [21]∼ ∼×✓ Spread Spec. [22]✓∼×✓ Phase [23]∼✓×✓"},{"citing_arxiv_id":"2605.00607","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe","primary_cat":"cs.CL","submitted_at":"2026-05-01T12:19:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"An encoding probe reconstructs transformer representations from acoustic, phonetic, syntactic, lexical and speaker features, showing independent syntactic/lexical contributions and training-dependent speaker effects.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.16113","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Co-Design of CNN Accelerators for TinyML using Approximate Matrix Decomposition","primary_cat":"cs.AR","submitted_at":"2026-04-17T14:49:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A co-design framework using approximate matrix decomposition and genetic algorithms delivers 33% average latency reduction in TinyML CNN FPGA accelerators with 1.3% average accuracy loss versus standard systolic arrays.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"bitwise shifts and sign flips for both inference and training. You et al. introduced ShiftAddNet [23], a model that separates shift and add layers to enhance accuracy.However, these techniques rely on retraining, which is infeasible when training data are proprietary, sensitive, or unavailable. Several Po2-based approaches avoid retraining entirely. M¨uller et al. [26] introduced WMD to approximate matrices using sparse and Po2 components. Lehnert et al. [24] proposed a post-training Po2 quantization technique, used to implement an FPGA accelerator for small models with fully-unfolded datapaths and hardwired shifts and zeros. This was later extended to CNNs by M ¨uller et al. [25]. With ShiftCNN [30], Gudovskiy and Rigazio proposed a Po2 quantization algorithm"},{"citing_arxiv_id":"2604.12456","ref_index":23,"ref_count":4,"confidence":0.9,"is_internal_anchor":false,"paper_title":"X-VC: Zero-shot Streaming Voice Conversion in Codec Space","primary_cat":"eess.AS","submitted_at":"2026-04-14T08:42:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"X-VC achieves zero-shot streaming voice conversion via one-step codec-space conversion with dual-conditioning acoustic converter and role-assignment training on generated paired data.","context_count":2,"top_context_role":"background","top_context_polarity":"background","context_text":"Voice conversion (VC) aims to transform a source utterance so that it sounds as if spoken by a target speaker while preserving the original linguistic content. It has broad applications in multimedia and speech technologies, including dubbing and localization, character voice editing in films, games, and animation, personalized speech generation, and assistive communication [ 23, 33]. Zero-shot or any-to-any VC further requires the model to generalize to unseen speakers without speaker-specific fine-tuning. A practical zero-shot VC system therefore needs to preserve source linguistic content, accurately transfer target speaker characteristics, and support low- latency streaming inference in a unified framework. Prior work often approaches zero-shot VC via an analysis and"},{"citing_arxiv_id":"2604.08838","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Exploring Bounded Component Analysis Using an $\\ell_\\infty$ Norm Criterion","primary_cat":"eess.SP","submitted_at":"2026-04-10T00:31:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Minimizing the sum of ℓ∞ norms enables separation of antisparse bounded sources via PCA followed by Givens rotations optimization, with claimed superior performance over prior methods in simulations.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Verleysen, A minimum-range approach to blind extraction of bounded sources, IEEE Transactions on Neural Networks 18 (3) (2007) 809-822. doi:10.1109/TNN.2006.889941. [31] G. Tatli, A. T. Erdogan, Polytopic matrix factorization: Determinant maximization based criterion and identifiability, IEEE Transactions on Signal Processing 69 (2021) 5431-5447. doi:10.1109/TSP.2021.3112918. [32] G. Tatli, A. T. Erdogan, Generalized polytopic matrix factorization, in: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, pp. 3235-3239. doi:10.1109/ICASSP39728.2021.9413709. 23 [33] R. Brotto, K. Nose Filho, J. M. T. Romano, Alternative criteria for predictive blind deconvolution, Journal of Communication and Information Systems 33 (1) (2018)."},{"citing_arxiv_id":"2602.17711","ref_index":23,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Interpreting Multi-Branch Anti-Spoofing Architectures: Correlating Internal Strategy with Empirical Performance","primary_cat":"cs.SD","submitted_at":"2026-02-14T20:15:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A framework using covariance-based spectral signatures and TreeSHAP attributions on AASIST3 branches identifies four operational archetypes and a flawed specialization mode that explains high error rates on specific spoofing attacks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.14939","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Decoding in the presence of ISI without interleaving -- ORBGRAND-AI","primary_cat":"eess.SP","submitted_at":"2025-10-16T17:51:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ORBGRAND-AI achieves the same or lower block error rate in ISI channels without interleaving compared to CA-SCL decoding with an interleaver at equal energy per information bit.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2305.02304","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"New Equivalences Between Interpolation and SVMs: Kernels and Structured Features","primary_cat":"stat.ML","submitted_at":"2023-05-03T17:52:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"New conditions for support vector proliferation (SVP) in RKHS for bounded orthonormal systems and sub-Gaussian features, yielding generalization bounds for kernel SVMs beyond prior restrictive assumptions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}