Oct 2026· Zenodo (CERN European Organization for Nuclear Research)
Identity, Memory, and Therapy
Abstract
This paper presents a self-observed case study of autobiographical memory reconstruction following a school reunion held after a long interval since graduation. Contemporary theories increasingly describe memory as a reconstructive process rather than the retrieval of fixed records. The present observations provide an opportunity to examine this process in real time. Over approximately forty-four hours following the reunion, recognition of former classmates triggered the progressive re-emergence of contextual information including seasons, music, school events, interpersonal relationships, and temporally localized autobiographical episodes extending far into the past. Rather than appearing instantaneously, memories emerged through successive stages of reconstruction. Faces triggered contexts; contexts triggered environmental details; environmental details triggered music; music enabled temporal localization. The observations are interpreted within a generative framework inspired by recent developments in diffusion-based artificial intelligence models. The findings suggest that autobiographical memory may function less as retrieval from storage and more as iterative reconstruction from sparse cues. Implications for cognitive science, autobiographical memory research, music-evoked recall, reminiscence therapy, and cognitive medicine are discussed.
GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations...
Xiaotian Zhang, Chun-yan Li, Yi Zong et al.· arXiv.org· 216 citations· ⚡17
An algorithm is proposed which leverages disentangled semantic factors to generate adversarial perturbation by altering controlled semantic attributes to fool the learner towards various "adversarial" targets.
Haonan Qiu, Chaowei Xiao, Lei Yang et al.· arXiv.org· 208 citations· ⚡17
This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.
The results are packaged in the Greenfield Startup Model (GSM), which explains the priority of startups to release the product as quickly as possible, and the need to shorten time-to-market, by speeding up the development through low-precision engineering activities.
Carmine Giardino, Nicolò Paternoster, M. Unterkalmsteiner et al.· IEEE Transactions on Softwar...· 178 citations· ⚡14
Software startup companies develop innovative, software-intensive products within limited timeframes and with few resources, searching for sustainable and scalable business models.
M. Unterkalmsteiner, P. Abrahamsson, Xiaofeng Wang et al.· e-Informatica Software Engin...· 157 citations· ⚡17
This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.