Study 1 (F25): Preregistration Protocol, Run Sheet, and Deterministic Scoring Instruments (v1.3)

Archival mirror of the frozen preregistration protocol and scoring instruments for Study 1 (Probe F25: "Does the Model Ask or Assume Before Answering?"), originally deposited on OSF on 21 October 2026 (https://osf.io/fgjxh; original SHA-256 checksums preserved in SHA256_STUDY1_F25_PROTOCOL_2026-10-21.txt). Contents (7 files):- F25_preregistration_v1.3_public_only.md: Confirmatory protocol specifying fixed model slots, pre-session personalization and profile-preference controls, unified primary endpoint (ASK vs. SILENT and ACT_THEN_OFFER), deterministic lexical and compression metrics (M1-M4), and clinical semantic fidelity rubric (M5).- F25_run_sheet_v1.3.md: Step-by-step operational run sheet for Condition A (bare 267-word passage) and Condition B (two-turn summarize and rewrite).- S.txt: Frozen 267-word clinical-AI stimulus passage ("The Clinical Parallels").- score_f25.py: Deterministic Python scorer for M1, M2a, M2b, M3 first-person pronoun counts, and M4 compression ratios.- semantic_fidelity_key.md: 17-proposition clinical semantic fidelity key and added-claim (+C) specification.- AUTHORSHIP_AND_AI_ROLE_DISCLAIMER.md: Authorship, provenance, and dual-role AI disclosure statement.- SHA256_STUDY1_F25_PROTOCOL_2026-10-21.txt: Original 21 October 2026 SHA-256 hashes for these six files. The completed 30 confirmatory sessions and 12 post-registration exploratory sessions executed on 14 November 2026 under this protocol are archived at Zenodo DOI: https://doi.org/10.5281/zenodo.24309494.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-18
DOI
https://doi.org/10.5281/zenodo.24340645
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Study 1 (F25): Preregistration Protocol, Run Sheet, and Deterministic Scoring Instruments (v1.3)

Gülüstü Salur
1 links
Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence in Healthcare and Education
article

Study 1 (F25): Preregistration Protocol, Run Sheet, and Deterministic Scoring Instruments (v1.3)

Gülüstü Salur
article en

Abstract

Archival mirror of the frozen preregistration protocol and scoring instruments for Study 1 (Probe F25: "Does the Model Ask or Assume Before Answering?"), originally deposited on OSF on 21 October 2026 (https://osf.io/fgjxh; original SHA-256 checksums preserved in SHA256_STUDY1_F25_PROTOCOL_2026-10-21.txt). Contents (7 files):- F25_preregistration_v1.3_public_only.md: Confirmatory protocol specifying fixed model slots, pre-session personalization and profile-preference controls, unified primary endpoint (ASK vs. SILENT and ACT_THEN_OFFER), deterministic lexical and compression metrics (M1-M4), and clinical semantic fidelity rubric (M5).- F25_run_sheet_v1.3.md: Step-by-step operational run sheet for Condition A (bare 267-word passage) and Condition B (two-turn summarize and rewrite).- S.txt: Frozen 267-word clinical-AI stimulus passage ("The Clinical Parallels").- score_f25.py: Deterministic Python scorer for M1, M2a, M2b, M3 first-person pronoun counts, and M4 compression ratios.- semantic_fidelity_key.md: 17-proposition clinical semantic fidelity key and added-claim (+C) specification.- AUTHORSHIP_AND_AI_ROLE_DISCLAIMER.md: Authorship, provenance, and dual-role AI disclosure statement.- SHA256_STUDY1_F25_PROTOCOL_2026-10-21.txt: Original 21 October 2026 SHA-256 hashes for these six files. The completed 30 confirmatory sessions and 12 post-registration exploratory sessions executed on 14 November 2026 under this protocol are archived at Zenodo DOI: https://doi.org/10.5281/zenodo.24309494.

Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence in Healthcare and Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon