arXiv subjects

Tamal Maharaj

Publications and source records attributed to Tamal Maharaj.

5 recordsLinked to original sources

arXiv2026

Viveka-Insight: a cross-lingual concept graph and citation-grounded retrieval resource over the complete works of Swami Vivekananda in English and Bengali

Classical philosophical corpora pose three compounding challenges for language resources: they exist in several languages without parallel alignment, their vocabulary is remote from that of contemporary readers, and generated text over culturally sensitive material must be verifiably grounded. We present Viveka-Insight, a bilingual resource and open-source pipeline for the works of Swami Vivekananda (1863-1902): the nine-volume English Complete Works and the ten-volume Bengali Vani o Rachana, two related but non-parallel corpora of about 15 million characters. Four layers are released: (i) a structure-preserving parse (32,694 paragraphs, 168,842 sentences) with per-paragraph anchors deep-linking into the published editions; (ii) a cross-lingual concept graph of 8,362 language-agnostic concepts with 87,518 relation-typed paragraph-concept and 55,872 concept-concept edges, in which canonical English labels act as a string-equality key linking Bengali and English passages with no parallel data; (iii) a bilingual alias inventory of 60,850 surface forms (30,053 English, 30,797 Bengali); and (iv) a human-annotated set of 200 paragraph-concept edges judged by three annotators, released with all per-annotator judgments. We report known-item cross-lingual retrieval over 194 verified rendered lecture pairs (Recall@10 0.86 in both directions), a 30-question audit of citation integrity and modern-question bridging, and a human study placing concept-extraction precision at 0.60 under strict two-annotator consensus (Cohen's kappa = 0.61). The extractor's confidence weight is calibrated: restricting to weight >= 0.8 raises precision to 0.71 while retaining 98% of concept-bearing paragraphs. Precision is markedly lower in Bengali than English (0.54 vs 0.68), locating the weakness in exactly the half that cross-lingual access depends on. The design transfers to other multilingual classical corpora.

cs.CL↗

arXiv2026

A Table-Free Index for Tapered Memoization Grids: Compact Out-of-Core Evaluation of Functions of Sorted Arguments

Many applications must repeatedly evaluate an expensive function f of a sorted score vector whose influence decays with rank: Plackett-Luce choice probabilities, alpha-entmax attention thresholds, and rank-weighted aggregates. Biswas and Regan (TCS 2015) introduced a tapered grid that memoizes such functions, indexed through precomputed node-count tables. We first make explicit that the tapered grid's key set is exactly the set of multiset combinations, so its index is the classical combinatorial number system: this yields a table-free closed-form O(d) rank that eliminates the O(Bd)-O(Bd^2) preprocessing tables of the original scheme, generalizes it beyond a pinned first coordinate, and supplies the previously missing O(d) unranking, which enables order-free parallel construction and key-free storage. The resulting structure is a values-only flat array: at N=37.4M entries it occupies 5.7x less memory than a hash-map memo and answers queries 1.1-1.8x faster once both structures exceed cache, and it remains operable memory-mapped beyond RAM, where pointer-based alternatives cannot reside. We give design guidance for choosing the taper: the optimal per-level refinement ratio equals the influence-decay ratio, and we derive a finite-epsilon closed form for the size penalty of a mismatched ratio -- accurate to a few percent where the classical asymptotic rate overstates the penalty by 16-43%. End-to-end, memoizing the Plackett-Luce normalization -- whose exact evaluation is an iterative transcendental root-find -- is 25-55x faster than Newton's method at 2.6e-3 mean error, against the approximately 10x reported originally; we also report a negative result, alpha-entmax thresholds, where the exact solver's tiny active support makes it 2.6x faster than any table, and distil the scoping rule this implies.

cs.DS↗

arXiv2026

A Word-Level Digital Reader of the Prasthanatrayi with Sankara's Bhasya: Corpus, Method, and an Open, Offline Reading Aid for the Advaita Vedanta Canon

The Prasthanatrayi -- the ten principal Upanisads, the Brahmasutra, and the Bhagavadgita, with Sankara's commentaries (bhasya) -- is the foundational corpus of Advaita Vedanta. Continuous euphonic combination (sandhi), long compounds (samasa), and dense scholastic prose make it hard to read at the word level: where one word ends, and what each word means grammatically, are both obscured. We present an open, fully offline, word-level digital reader of the entire Prasthanatrayi with Sankara's bhasya. Every word -- of both the root text (mula) and the commentary -- is clickable and resolves to a pop-up giving its split (padaccheda), morphological analysis, and gloss. Because every word carries a lemma, the reader also acts as a concordance: a search on a dictionary headword retrieves all of that word's inflected and sandhi-hidden occurrences, and its occurrences inside compounds, across both layers. The resource covers thirteen commentarial units (2,971 verses, sutras, and prose sections; 36,881 analysed word-occurrences of root text) and a global dictionary of 95,587 distinct commentarial surface forms. We describe the corpus, the hybrid pipeline -- a rule-based sandhi splitter over an inflected-form lexicon and attested-corpus look-ups, with LLM-assisted analysis under an adversarial two-pass verification protocol -- and a durable human-review loop whose corrections survive every regeneration. An intrinsic evaluation against independent Sanskrit resources finds high-confidence analyses agree with an authoritative inflectional lexicon on over 99% of attested forms, and a band-blind adjudication confirms that quality degrades predictably across confidence bands, with errors concentrated in the low-confidence tier the review loop targets. The reader is a single self-contained HTML file needing no server or network, offered as a freely redistributable teaching and reading aid.

cs.CL↗

arXiv2026

The Multipath Blind Spot: $K$-Agnostic Robust Calibration for Sparse-Anchor Metric Depth from Frozen Foundations

Monocular depth foundations predict domain-general relative depth but lack absolute scale; a handful of sparse metric anchors from a range sensor can calibrate them to metric depth, an attractive alternative to metric-supervised training. Existing sparse-anchor calibration methods, however, assume the anchors are clean, whereas real sensors produce outliers that are present with the wrong value -- time-of-flight multipath, mixed pixels -- not merely missing. We show that the established residual-on-CFA calibration recipe collapses under such outliers, and that the strongest publicly deployed method, VI-Depth, has a structural multipath blind spot: robust to missing anchors, it falls behind an unprotected baseline on three of four datasets when anchors are present but wrong. We propose Multipath-Robust Anchor Calibration (MRAC), a parameter-free, inference-time wrapper that gates anchors by foundation consistency -- a Theil--Sen fit and a median-absolute-deviation test against the foundation's own relative-depth ordering -- before a single call to the calibration head. MRAC adds no learned parameters, runs its selection in $\approx 50\,μ$s on CPU, and serves anchor budgets $K \in [5,200]$ from one checkpoint. On a $320$-cell benchmark with a same-backbone, same-architecture control, MRAC strictly wins $84\%$ of same-backbone cells across all four outlier families and, against VI-Depth, wins all twelve corrupted multipath cells and all sixteen KITTI cells, reducing KITTI multipath AbsRel by $3.2\times$ ($0.489$ to $0.151$) at zero retraining.

cs.CV↗

arXiv2020

OPAC: Opportunistic Actor-Critic

Actor-critic methods, a type of model-free reinforcement learning (RL), have achieved state-of-the-art performances in many real-world domains in continuous control. Despite their success, the wide-scale deployment of these models is still a far cry. The main problems in these actor-critic methods are inefficient exploration and sub-optimal policies. Soft Actor-Critic (SAC) and Twin Delayed Deep Deterministic Policy Gradient (TD3), two cutting edge such algorithms, suffer from these issues. SAC effectively addressed the problems of sample complexity and convergence brittleness to hyper-parameters and thus outperformed all state-of-the-art algorithms including TD3 in harder tasks, whereas TD3 produced moderate results in all environments. SAC suffers from inefficient exploration owing to the Gaussian nature of its policy which causes borderline performance in simpler tasks. In this paper, we introduce Opportunistic Actor-Critic (OPAC), a novel model-free deep RL algorithm that employs better exploration policy and lesser variance. OPAC combines some of the most powerful features of TD3 and SAC and aims to optimize a stochastic policy in an off-policy way. For calculating the target Q-values, instead of two critics, OPAC uses three critics and based on the environment complexity, opportunistically chooses how the target Q-value is computed from the critics' evaluation. We have systematically evaluated the algorithm on MuJoCo environments where it achieves state-of-the-art performance and outperforms or at least equals the performance of TD3 and SAC.

cs.LG↗