Raw YAML
schema_version: "1.2"
extraction_run:
created_at: "2026-05-06T00:00:00+02:00"
created_by: Codex
model: gpt-5
source_files:
- papers/shurakov2023trainflightretraction/source/RetractionBased_PaperDraft_18_11_N.docx
- papers/shurakov2023trainflightretraction/source/email.eml
- papers/shurakov2023trainflightretraction/data/Finished_Responses.csv
- papers/shurakov2023trainflightretraction/data/Unfinished_Responses.csv
- papers/shurakov2023trainflightretraction/data/Retraction_Third_person_April_14_2023.csv
- papers/shurakov2023trainflightretraction/data/Retraction_experiment.py
notes: "Unpublished Experiment 3 removed from an earlier draft of Shurakov 2025; source materials supplied by the author by email."
paper:
paper_id: shurakov2023trainflightretraction
citation: "Shurakov, N. (unpublished). Train and Flight scenarios from an earlier draft of The Stakes Effect: New Evidence from a Retraction-Based Experimental Design."
short_label: "Shurakov unpublished Experiment 3"
doi: null
published: "No"
year: 2023
language: English
language_other: null
research_objective: "Test whether the retraction-based stakes effect observed in Shurakov's Bank experiments generalizes to two additional third-person scenarios: Train and Flight."
data_availability:
data_available_online: "No"
url: null
notes: "Dataset, draft manuscript, and email were supplied privately by Nikolai Shurakov; the email also linked to the author's Dropbox copy of the Python analysis script."
notes: "Related published article: Shurakov, N. (2025). The Stakes Effect: New Evidence from a Retraction-Based Experimental Design. Episteme. https://doi.org/10.1017/epi.2025.10060. The Train/Flight experiment was not included in the published version."
studies:
- study_id: 1
label: "Experiment 3 (unpublished Train/Flight extension)"
language: English
language_other: null
objective: "Assess whether the stakes effect from the retraction-based Bank experiments generalizes to two additional third-person scenarios using the modified design with an initial knowledge-ascription screen."
sample:
n_final: 338
recruitment: Prolific
recruitment_other: null
compensation: money
compensation_other: "GBP 0.40 for approximately 3 minutes."
characteristics: "Draft reports 361 native English speakers from the US, UK, and Australia via Prolific, 181 female, mean age 41. Recomputing from the supplied Finished and Unfinished Qualtrics exports yields 338 usable composite-score responses after consent, initial knowledge endorsement, attention-check, and usable follow-up response filters (Train=161, Flight=177)."
mean_age: 41
mean_age_prov:
page: null
quote: "For the final analysis, I included all valid responses per condition, resulting in a total sample of 361 participants (181 female; mean age 41 years)."
tei_id: null
table_ref: out/fulltext.md
provenance:
page: null
quote: "I recruited 361 native speakers of English from the US, UK, and Australia via Prolific."
tei_id: null
table_ref: out/fulltext.md
design: Between-Subjects
design_other: "3 x 2 between-subjects design: story type (Neutral, Stakes, Evidence) by scenario (Train, Flight)."
manipulated_factors:
- "story type: Neutral vs Stakes vs Evidence"
- "scenario: Train vs Flight"
paradigm: Retraction of knowledge attribution
paradigm_other: null
scale:
label: composite-score
points: null
anchors: "Binary retraction response ('I do'=1, 'I don't'=-1) multiplied by confidence from 1 to 7, yielding scores from -7 to 7."
direction: "Higher = more confident standing by the initial knowledge attribution; lower/negative = more confident retraction."
provenance:
page: null
quote: "Composite scores were calculated by multiplying the retraction response by the participant's confidence level... resulting in scores between -7 and 7."
tei_id: null
table_ref: out/fulltext.md
measures:
knowledge_question_text: "Initial knowledge-ascription question followed by a stand-by/retraction question: 'do you stand by your previous claim that [the target] knows...?'"
knowledge_question_first: "Yes"
additional_question_text: "Confidence rating after the binary retraction response, using a 7-point confidence item."
scenarios:
- scenario_code: train
scenario_type: "Third-person Train scenario: a stranger with a printed timetable says the train stops at Kensington."
high_stakes_text: "STAKES: the partner needs the participant to reach Kensington quickly to buy medicine after a shellfish reaction and may need resuscitation."
low_stakes_text: "NEUTRAL: the partner mentions a small party next week and asks whether the participant would like to join."
provenance:
page: null
quote: "You are at the railway station and want to take a train to Kensington... The guy takes out a printed train timetable."
tei_id: null
table_ref: out/fulltext.md; data/Finished_Responses.csv
- scenario_code: flight
scenario_type: "Third-person Flight scenario: a woman in an airport queue says a direct flight to Tokyo takes 14 hours."
high_stakes_text: "STAKES: a close friend wants to plan a Star Wars movie marathon during the flight and says it is very important that the 14-hour claim is right."
low_stakes_text: "NEUTRAL: an acquaintance on the same flight clearly does not care how long the flight takes and asks whether the participant stands by the knowledge claim."
provenance:
page: null
quote: "You are at the airport to take a direct flight to Tokyo... She says: 'I've been to Japan a couple of times; it takes 14 hours to get to Tokyo if you have a direct flight'."
tei_id: null
table_ref: out/fulltext.md; data/Finished_Responses.csv
effects:
- effect_id: s1_e1
subgroup: "Train (retraction-based): Stakes vs Neutral"
subgroup_desc: "Composite retraction score in the Train scenario, high-stakes follow-up vs neutral follow-up, after excluding initial knowledge non-endorsers."
design: Between-Subjects
design_other: null
paradigm: Retraction of knowledge attribution
paradigm_other: null
moderators:
scenario: other
skeptical_pressure: "No"
awareness: "No"
evidence: External
attribution_person: Other
evidence_reliability: High
moderators_coding:
scenario:
provenance:
page: null
quote: "You are at the railway station and want to take a train to Kensington."
tei_id: null
table_ref: out/fulltext.md
reason: "The vignette is a railway/train case, which is outside the fixed scenario vocabulary."
skeptical_pressure:
provenance:
page: null
quote: "STAKES: Could you buy Drugpills for me?... I may need resuscitation if you don't arrive in an hour."
tei_id: null
table_ref: data/Finished_Responses.csv
reason: "The Stakes condition raises practical consequences but does not introduce an explicit doubt or alternative about whether the train stops at Kensington."
awareness:
provenance:
page: null
quote: "The guy takes out a printed train timetable, and says 'Yeah, it stops at Kensington'. STAKES follow-up: your partner asks whether you could buy Drugpills."
tei_id: null
table_ref: data/Finished_Responses.csv
reason: "The target knowledge subject is the guy at the railway station. The high-stakes consequence is conveyed to the participant-attributor by the partner after the guy's timetable-based claim; the vignette does not state that the guy is aware of those stakes."
evidence:
provenance:
page: null
quote: "The guy takes out a printed train timetable, and says 'Yeah, it stops at Kensington'."
tei_id: null
table_ref: out/fulltext.md
reason: "The knowledge attribution rests on testimony supported by an external timetable."
attribution_person:
provenance:
page: null
quote: "The guy knows that the train stops at Kensington."
tei_id: null
table_ref: data/Finished_Responses.csv
reason: "Participants attribute knowledge to the guy, not to themselves."
evidence_reliability:
provenance:
page: null
quote: "The guy takes out a printed train timetable."
tei_id: null
table_ref: out/fulltext.md
reason: "The explicit basis includes a printed timetable, an external record presented without unreliability cues, so it is coded High."
contrast:
group_high: train_stakes
group_low: train_neutral
sign_convention: "d = mean(low) - mean(high)"
other_notes: "Effect uses Stakes vs Neutral; Evidence is a defeater condition and is not extracted as the primary stakes effect."
groups:
- group_id: train_neutral
label: "Train / Neutral"
n: 54
mean: 5.33333333333333
sd: 2.17186121381535
se: null
provenance:
page: null
quote: "Computed from Finished_Responses.csv and Unfinished_Responses.csv after consent, initial knowledge endorsement, attention-check, and usable response filters."
tei_id: null
table_ref: analysis/effect_sizes.qmd
- group_id: train_stakes
label: "Train / Stakes"
n: 53
mean: 4.94339622641509
sd: 2.95097828850303
se: null
provenance:
page: null
quote: "Computed from Finished_Responses.csv and Unfinished_Responses.csv after consent, initial knowledge endorsement, attention-check, and usable response filters."
tei_id: null
table_ref: analysis/effect_sizes.qmd
reported_test:
test: "Tukey HSD pairwise comparison"
p: 0.841
notes: "Draft reports no significant Stakes-vs-Neutral composite-score difference for Train; omnibus ANOVA F(2,158)=54.61, p<.001 because Evidence differs strongly."
provenance:
page: null
quote: "No statistically significant difference was found between STAKES and NEUTRAL (p = .841)."
tei_id: null
table_ref: out/fulltext.md
effect_size:
metric: SMD
d: 0.150717614261
v: 0.037492591641
computed_from: groups
needs_review: false
notes: "Computed from author-sent Finished and Unfinished Qualtrics exports in analysis/effect_sizes.qmd using esc::esc_mean_sd; sign follows d = mean(low) - mean(high)."
quality_flags:
- unpublished_author_dataset
- manuscript_dataset_n_discrepancy
notes: "The manuscript reports the same rounded Neutral and Stakes descriptives for Train when the Finished and Unfinished Qualtrics exports are combined."
- effect_id: s1_e2
subgroup: "Flight (retraction-based): Stakes vs Neutral"
subgroup_desc: "Composite retraction score in the Flight scenario, high-stakes follow-up vs neutral follow-up, after excluding initial knowledge non-endorsers."
design: Between-Subjects
design_other: null
paradigm: Retraction of knowledge attribution
paradigm_other: null
moderators:
scenario: airport
skeptical_pressure: "No"
awareness: "No"
evidence: First Person
attribution_person: Other
evidence_reliability: Medium
moderators_coding:
scenario:
provenance:
page: null
quote: "You are at the airport to take a direct flight to Tokyo."
tei_id: null
table_ref: out/fulltext.md
reason: "The vignette is an airport/flight case."
skeptical_pressure:
provenance:
page: null
quote: "It is very important to me, and I would feel betrayed if you fooled me."
tei_id: null
table_ref: data/Finished_Responses.csv
reason: "The Stakes condition raises social/practical consequences but does not introduce evidence against the 14-hour claim."
awareness:
provenance:
page: null
quote: "She says: 'I've been to Japan a couple of times; it takes 14 hours to get to Tokyo if you have a direct flight'. STAKES follow-up: your friend says it is very important."
tei_id: null
table_ref: data/Finished_Responses.csv
reason: "The target knowledge subject is the woman in the queue. The high-stakes consequence is conveyed to the participant-attributor by the friend after the woman's travel-experience claim; the vignette does not state that the woman is aware of those stakes."
evidence:
provenance:
page: null
quote: "She says: 'I've been to Japan a couple of times; it takes 14 hours to get to Tokyo if you have a direct flight'."
tei_id: null
table_ref: out/fulltext.md
reason: "The target knowledge subject's basis is her own prior travel experience."
attribution_person:
provenance:
page: null
quote: "The woman knows that the flight takes 14 hours."
tei_id: null
table_ref: data/Finished_Responses.csv
reason: "Participants attribute knowledge to the woman, not to themselves."
evidence_reliability:
provenance:
page: null
quote: "I've been to Japan a couple of times; it takes 14 hours to get to Tokyo if you have a direct flight."
tei_id: null
table_ref: out/fulltext.md
reason: "The target knowledge subject's basis is ordinary first-person travel experience without official or independent verification, so it is coded Medium."
contrast:
group_high: flight_stakes
group_low: flight_neutral
sign_convention: "d = mean(low) - mean(high)"
other_notes: "Effect uses Stakes vs Neutral; Evidence is a defeater condition and is not extracted as the primary stakes effect."
groups:
- group_id: flight_neutral
label: "Flight / Neutral"
n: 59
mean: 4.91525423728814
sd: 2.20726180495842
se: null
provenance:
page: null
quote: "Computed from Finished_Responses.csv and Unfinished_Responses.csv after consent, initial knowledge endorsement, attention-check, and usable response filters."
tei_id: null
table_ref: analysis/effect_sizes.qmd
- group_id: flight_stakes
label: "Flight / Stakes"
n: 59
mean: 4.42372881355932
sd: 3.13051383812741
se: null
provenance:
page: null
quote: "Computed from Finished_Responses.csv and Unfinished_Responses.csv after consent, initial knowledge endorsement, attention-check, and usable response filters."
tei_id: null
table_ref: analysis/effect_sizes.qmd
reported_test:
test: "Tukey HSD pairwise comparison"
p: 0.645
notes: "Draft reports no significant Stakes-vs-Neutral composite-score difference for Flight; omnibus ANOVA F(2,173)=123.36, p<.001 because Evidence differs strongly."
provenance:
page: null
quote: "No statistically significant difference was found between STAKES and NEUTRAL (p = .645)."
tei_id: null
table_ref: out/fulltext.md
effect_size:
metric: SMD
d: 0.181474047555
v: 0.034037850974
computed_from: groups
needs_review: false
notes: "Computed from author-sent Finished and Unfinished Qualtrics exports in analysis/effect_sizes.qmd using esc::esc_mean_sd; sign follows d = mean(low) - mean(high)."
quality_flags:
- unpublished_author_dataset
- manuscript_dataset_n_discrepancy
notes: "The manuscript reports the same rounded Neutral and Stakes descriptives for Flight when the Finished and Unfinished Qualtrics exports are combined."
notes: "This unpublished study is Experiment 3 from an earlier draft of the published Shurakov paper. The focal effects are the two Stakes-vs-Neutral contrasts; Evidence is retained in the QMD as a manipulation/defeater comparison but is not extracted as a stakes effect."