Publications
Preprints, technical reports, methodology notes and data papers produced by the Institute. Everything is open access, versioned and citable.
Editorial and publication policy
The policy is fixed before the first paper is published, so that readers, funders and reviewers know exactly what to expect from us.
Open access without embargo
Every preprint and report is published in full text under CC BY 4.0. We do not place results behind a paywall and we do not sign exclusive transfer agreements that would prevent open publication.
Versioning and provenance
Each revision receives its own DOI suffix and a change log. Superseded versions stay available, so a citation never breaks and readers can see what changed.
Reproducibility
Papers that report experiments are published together with the run configuration, prompts, seeds and the analysis scripts needed to repeat them. Where data cannot be released, the restriction and its reason are stated.
Disclosure of interests
Authors declare funding sources, commercial engagements and any client relationship connected to the work. A funder never receives veto power over a result.
Dual-use review
Before release, every manuscript is reviewed for information that would materially help someone attack a live system. Findings are published; operational attack payloads are not. This is described in responsible disclosure.
Generated content
Use of language models in analysis or drafting is disclosed in the methods section. Authors remain fully responsible for the correctness of every claim, and text is labelled where required by Russian law.
In preparation
Working titles of the first cycle. Titles, authorship and target venues are provisional until the registration of the Institute is complete and the manuscripts pass internal review.
| Working title | Track | Status | Expected |
|---|---|---|---|
| Measuring behavioural drift in long-running agent sessions | AI psychopathology | Drafting | Q1 2027 |
| Memory as an infection vector in multi-agent systems | Hybrid ecosystems | Drafting | Q1 2027 |
| A taxonomy of observable inter-agent behaviours | AI-to-AI sociology | Data collection | Q2 2027 |
| Auditing agent collectives: a method and its limits | Applied audit | Outline | Q2 2027 |
| Shutdown resistance: what is measurable today | Self-preservation | Outline | Q3 2027 |
How to cite our work
When the first papers appear, a citation stub and a BibTeX entry will be published next to each of them. The general form is:
Institute of Sociology and AI Safety (ANO «ISAI»). (YEAR). Title of the work (Version N).
https://doi.org/10.XXXX/XXXXXXX
Preprints under review are cited by their DOI and version number, never by a working title.
Notifications
To be told when the first papers are released, write to info@isai.su with the subject line «publications». A machine-readable feed will be published together with the first preprint.