historical literature review

Existing timeline tools predominantly employ static visualizations, limiting users’ capacity for active exploration and knowledge construction. To address this, we propose “Generative Timelines,” a novel interactive paradigm that integrates generative AI, interactive visualization, and citation provenance tracking to enable dynamic timeline generation, adaptive expansion/contraction, and verifiable source attribution. Our core contribution lies in reimagining timelines as responsive exploration interfaces—capable of answering user queries and collaboratively supporting the co-construction of historical and conceptual evolution narratives. A user study demonstrates that our system significantly enhances curiosity-driven exploration, serendipitous discovery, and deep relational tracing of complex events. Furthermore, it empirically confirms that source credibility is a critical determinant of user trust formation.

This study addresses the lack of coherence in longitudinal analyses of scientific knowledge graphs, which often stems from inconsistent approaches to topic identification and cross-temporal linkage. To overcome this limitation, the authors propose a unified relational framework that integrates cross-sectional topic detection and longitudinal lineage reconstruction within a single weighted network structure. For the first time, topic evolution is modeled as structural reconfiguration rather than lexical continuity within a relational paradigm. By incorporating relational clustering, directional coverage, centrality-weighted measures of lineage strength, and document membership modeling, the method substantially enhances methodological consistency and interpretive robustness in longitudinal science mapping. This approach enables a more accurate and nuanced understanding of the dynamic mechanisms underlying scientific topic evolution.

Current large language models produce contextual embeddings that lack interpretability and temporal awareness, are susceptible to historical biases, and struggle to reliably capture the evolution of scientific concepts. This work proposes a novel framework integrating topic modeling and complex network analysis, introducing topological density and information entropy into conceptual history research for the first time to dynamically characterize semantic structural shifts in scientific ideas. Using the Royal Society’s historical corpus, we construct a temporal concept network centered on the paradigm shift from phlogiston theory to oxidation theory. Our analysis reveals that conceptual transitions are significantly associated with higher entropy and increased network topological density, indicating concurrent growth in intellectual diversity and efforts toward knowledge integration. These findings demonstrate the method’s effectiveness and robustness in capturing the dynamics of scientific paradigm evolution.

Existing datasets of scientific ideation trajectories struggle to comprehensively capture the full research process—from literature exploration and tool utilization to the evolution of intermediate artifacts and final proposals. This work proposes a reverse-to-forward synthesis mechanism that emulates the uncertainty, evidence integration, and phased convergence characteristic of real scientific inquiry through a Generator–Advisor architecture. By leveraging action–observation–editing sequence modeling, context-aware verification, and process-level supervision, the approach generates multi-turn trajectories aligned with authentic research practices, starting from high-quality papers and proposals. The study yields the first trajectory dataset spanning the complete scientific workflow and establishes a generalizable paradigm for synthesizing process-supervised data for scientific agents.

Existing research ideation tools emphasize breadth-oriented idea generation but lack support for iterative refinement, elaboration, and evaluation—hindering literature-grounded, deep-reading–driven conceptual evolution. Method: We propose the first literature-driven interactive research ideation system, integrating a composable “idea element” canvas model with a multi-dimensional (problem/solution/evaluation/contribution) co-evolution mechanism. Our approach innovatively incorporates LLM-powered literature-aware feedback generation, graph-structured idea modeling, and interactive multi-path variant exploration. Contribution/Results: Experiments demonstrate a 42% increase in user-generated idea output and significantly enhanced detail elaboration. Seven researchers successfully applied the system across the full ideation pipeline—from initial topic conception to paper outline revision—validating its efficacy in supporting deep, iterative, literature-informed research design.

This work addresses the limitation of existing research infrastructures, which are predominantly document-centric and struggle to represent the causal evolutionary relationships among research methodologies in a structured manner. To overcome this, the authors propose Intern-Atlas—the first method evolution atlas—automatically constructed from over one million AI papers. By integrating method-level entity recognition, lineage relationship inference, and evidence-grounded semantic edge construction, Intern-Atlas forms a queryable causal network comprising 9.41 million semantic edges. The authors further introduce a self-guided temporal tree search algorithm to generate methodological evolution chains. Expert evaluations confirm high consistency between the atlas-derived paths and established scientific trajectories. Intern-Atlas has already demonstrated utility in research idea evaluation and automated generation, offering a novel infrastructure for AI-powered scientific agents.

This study addresses the lack of systematic research on how historians actually employ visualization as data-driven evidence—a gap that hinders the design of interdisciplinary visualization tools. Through a mixed-methods approach, the authors construct a corpus of 14,021 images, apply semi-automated annotation to 4,831 visualization instances, and integrate expert interviews with boundary object analysis using HiFigAtlas. Drawing on a large-scale dataset of 4,142 historical journal articles, they propose the first hierarchical taxonomy of visualizations in historical scholarship. This taxonomy identifies five distinct roles of visualizations and reveals their usage patterns across subfields and temporal dimensions, along with associated cognitive and practical barriers. The findings provide both an empirical foundation and a theoretical framework for developing visualization tools better aligned with historians’ disciplinary needs.

Design-oriented visualization research often struggles to meet conventional reproducibility standards due to its inherent subjectivity, contextual dependence, and iterative nature, thereby limiting its transparency and rigor. To address this challenge, this work proposes “traceability” as a viable alternative to traditional reproducibility. It presents the first systematic theoretical framework centered on three core components—recording, reporting, and reading—and introduces tRRRacer, a supporting tool implementing this framework. Through collaborative autoethnography, the authors reflect on practical applications of traceability in design-oriented research, demonstrating its feasibility and yielding actionable principles alongside theoretical insights. This approach offers a novel pathway to enhance the rigor and transparency of such studies without relying on strict reproducibility criteria.