In large e-commerce platforms, search systems are typically composed of a series of modules, including recall, pre-ranking, and ranking phases. The pre-ranking phase, serving as a lightweight module, is crucial for filtering out the bulk of products in advance for the downstream ranking module. Industrial efforts on optimizing the pre-ranking model have predominantly focused on enhancing ranking consistency, model structure, and generalization towards long-tail items. Beyond these optimizations, meeting the system performance requirements presents a significant challenge. Contrasting with existing industry works, we propose a novel method: a Generalizable and RAnk-ConsistEnt Pre-Ranking Model (GRACE), which achieves: 1) Ranking consistency by introducing multiple binary classification tasks that predict whether a product is within the top-k results as estimated by the ranking model, which facilitates the addition of learning objectives on common point-wise ranking models; 2) Generalizability through contrastive learning of representation for all products by pre-training on a subset of ranking product embeddings; 3) Ease of implementation in feature construction and online deployment. Our extensive experiments demonstrate significant improvements in both offline metrics and online A/B test: a 0.75% increase in AUC and a 1.28% increase in CVR.
Hybrid halocuprates (I) with organic cations show great potential for optoelectronic applications due to their tunable luminescence and high thermal stability. In this study, the iodocuprate (I) [PPh4][Cu3I4], featuring unique helical chains of face-sharing tetrahedra, was synthesized and characterized. This compound exhibits a bandgap of 3.1 eV and orange luminescence at low temperature, attributed to self-trapped exciton emission. [PPh4][Cu3I4] demonstrates exceptional thermal stability among hybrid halocuprates with decomposition above 380 °C, forming a stable melt at ~255 °C without Cu+ oxidation in ambient atmosphere.
A new hybrid lead bromide, acetamidinium lead bromide (Aca 3 PbBr 5 ), representing a previously unreported member of the A 3 PbBr 5 halide family, has been synthesized and characterized.
We report the crystal structures, thermal stability, and luminescence properties of three trimethylsulfonium halocuprates: (TMS)Cu 2 I 3 , and two new bromide phases: (TMS)Cu 2 Br 3 and (TMS) 2 CuBr 3 .
Organic-inorganic hybrid copper halides have emerged as promising candidates for optoelectronic applications due to their structural tunability and luminescent properties. In this work, four novel copper halides, namely AcaCuI2, AcaCuBr2, ImCuI2, and ImCuBr2 (Aca = acetamidinium, Im = Imidazolium) were synthesized for the first time and characterized structurally, thermally, and optically. Single-crystal X-ray diffraction revealed that AcaCuBr2, AcaCuI2, and ImCuBr2 crystallize with one-dimensional chains consisting of edge-sharing [CuX4] tetrahedra, whereas ImCuI2 forms zigzag chains composed of corner-sharing [Cu3I7]4- clusters. Thermogravimetric analysis indicated high thermal stability, particularly for the bromide derivatives, with decomposition temperatures exceeding 200 °C. Optical studies demonstrated that all compounds exhibit broadband emission profiles modulated by structural connectivity: edge-sharing chains exhibit low-temperature self-trapped exciton (STE) emission (460-580 nm), whereas ImCuI2 enables room-temperature photoluminescence (PL max = 533 nm) due to its flexible corner-sharing structure. This work provides valuable insights into cation-driven structural engineering for advanced luminescent materials guiding future design of efficient and thermally robust halocuprate-based luminescent materials.
19 May 2026 in ACM Transactions on Knowledge Discovery From Data
Product search is crucial for customers to discover and purchase products. With the growing importance of AI explanations, many KG-based methods use independent reasoning paths to provide explanations for retrieved results. However, these methods often fail to relate explanations to the current query and provide only single-facet explanations rather than multi-facet explanations that address users’ diverse search intents, such as different categories or bands. To overcome this issue, we propose an explainable product search model QGCNM, to generate query-aware multi-facet explanations through hierarchical graph convolution. Specifically, we design a query-aware graph convolutional ranker to excavate user’s multi-aspect search intent and develop a multi-path reasoner to explore the intent-based multiple paths for multi-facet explanations. Empirical evaluations on Amazon datasets show that QGCNM outperforms existing models on retrieval effectiveness and has better explanation abilities.