Ensuring data quality in large tabular datasets is a critical challenge, typically addressed through data wrangling tasks. Traditional statistical methods, though efficient, cannot often understand the semantic context and deep learning approaches are resource-intensive, requiring task and dataset-specific training. We present an automated system that utilizes large language models to generate executable code for tasks like missing value imputation, error detection, and error correction. Our system aims to identify inherent patterns in the data while leveraging external knowledge, effectively addressing both memory-dependent and memory-independent tasks.

Exploratory Data Analysis (EDA) derives meaningful insights from extensive and complex datasets. This process typically involves a series of analytical operations to identify the patterns within the data. However, the effectiveness of EDA is often limited by the user's domain knowledge and proficiency in data exploration methods. To overcome these challenges, we developed QUIS, a fully automated EDA system that uncovers insights by generating data-related questions and exploring subspaces in the dataset without prior training. QUIS allows users to control key system parameters such as beam width, beam depth, and expansion factor for subspace selection, the interestingness score for filtering valuable insights, and parameters for managing the quality and quantity of generated questions.

A core enabler for blockchain or DLT interoperability is the ability to atomically exchange assets held by mutually untrusting owners on different ledgers. This atomic swap problem has been well-studied, with the Hash Time Locked Contract (HTLC) emerging as a canonical solution. HTLC ensures atomicity of exchange, albeit with caveats for node failure and timeliness of claims. But a bigger limitation of HTLC is that it only applies to a model consisting of two adversarial parties having sole ownership of a single asset in each ledger. Realistic extensions of the model in which assets may be jointly owned by multiple parties, all of whose consents are required for exchanges, or where multiple assets must be exchanged for one, are susceptible to collusion attacks and hence cannot be handled by HTLC. In this paper, we generalize the model of asset exchanges across DLT networks and present a taxonomy of use cases, describe the threat model, and propose MPHTLC, an augmented HTLC protocol for atomic multi-owner-and-asset exchanges. We analyze the correctness, safety, and application scope of MPHTLC. As proof-of-concept, we show how MPHTLC primitives can be implemented in networks built on Hyperledger Fabric and Corda, and how MPHTLC can be implemented in the Hyperledger Labs Weaver framework by augmenting its existing HTLC protocol.

Interoperation between permissioned consortium blockchain networks relies on their abilities to discover and validate the identities of each others’ participant organizations. These organizations may possess self-sovereign decentralized identities and verifiable credentials issued by well-known certification authorities. Two mutually untrusting networks of organizations can establish a basis for interoperation if they have one or more certification authorities in common. Yet, for privacy reasons, neither of them may want to expose a priori their entire lists of authorities, necessitating a negotiation process through which common authorities can be identified. In this paper, we analyze this negotiation problem, and propose and analyze two solution approaches, one involving active participation of the trust anchors and the other without involving them.

Invoice factoring is an invoice financing process where business organizations sell their invoices to banks or financial institutions at a discount to gain faster access to the invoice amount. Carrier organizations, in global trade, exercise invoice factoring to gain quick access to the money they get paid for the shipment of consignments by shippers. Carriers initiate invoice factoring once the invoices are available after the goods delivery. We propose accelerating invoice factoring by predicting the invoice amount at different milestone events as the freight transport progresses from supplier to shipper using smart contracts on a blockchain network operated by the global trade logistics participants. Accurate prediction of the invoice value for ongoing shipment enables the carrier organization to initiate invoice factoring on the trade finance network before the completion of goods delivery to the shipper. Further, based on the past accuracy of prediction models, the financial institutions may choose to release the invoice amount in installments at different freight transportation milestone events.