iFishIENCi (2022) — Rainbow trout feed-system panel
https://zenodo.org/records/10842711 →benchmark:ifish-rainbow-trout-2022
Shape mix:
3
left-skewed
1
unimodal
Δ 0.36
4.00
()
→ 3.64
()
within-fixture gradient
Acceptance rubric
An SSR re-run acceptably reproduces this benchmark when it clears every check below on the same 4 paired questions the source publishes. The chip badges name the checks the round-38 → round-46 shape-mismatch finding argued are necessary but not sufficient in isolation.
CI overlap
4/4
Shape match
4/4
SSR mean inside CI · shape badge reproduces the source label.
What this benchmark discloses
Recruitment screener (verbatim)
Trained consumer panel recruited by ttz Bremerhaven (DE) for the iFishIENCi project D3.6 sensory assessment. Specific inclusion criteria not in the public spreadsheet; see project deliverable PDF at https://ifishienci.eu/wp-content/uploads/2024/01/iFishIENCi_D3.6.pdf.
Sample weighting & demographics
Unweighted hedonic. 9-point discrete scale per ASTM/ISO 11036. Single rating per product per panellist per attribute (appearance, odour, taste, mouthfeel, general impression). Only general impression is paired here.
Fieldwork dates, country, language
Bremerhaven, Germany (ttz). Fieldwork month: 2022-08 (from filename _08.2022). EU project iFishIENCi D3.6 sensory analysis of alternative-protein-fed fish.
Original question text & translations
On the 9-point hedonic scale, what is your general impression of this rainbow trout sample? (Peryam–Pilgrim 1957; ASTM E2454 / ISO 11036) — single rating per panellist per product.
Likert / scale labelling
9-point hedonic per ASTM/ISO 11036 standard (Peryam–Pilgrim 1957). 1 = "dislike extremely". 5 = "neither like nor dislike". 9 = "like extremely". Intermediate anchors are conventional (dislike very much / moderately / slightly; like slightly / moderately / very much). Labels not in the source spreadsheet; standard sensory-science instrument cited.
FGI moderator guide & coding rules
Hedonic survey by trained consumer panel, not FGI. No moderator guide. Carryover order and serving were balanced by ttz Bremerhaven per the iFishIENCi protocol.
Data source & license
CC-BY 4.0. Attribution: Rost, A. et al., ttz Bremerhaven (2022), iFishIENCi D3.6 sensory analysis. https://zenodo.org/records/10842711
Anything not disclosed here was not available in the source dataset and is recorded as such.
SSR run — reproducibility keys
- template_version
- 3.0.0
- llm_seed
- 4206
- bootstrap_seed
- 8412
- llm_model
- deepseek-v4-flash
- embedding_model
- nvidia/nv-embed-v1
SSR score vs ground truth, by question
Each row holds one question. The teal mark and range are SSR. The sky mark and range are the source FGI/survey.
§
Overall, how much do you like this rainbow trout? (Control — standard commercial feed)
SSR
—
Source
4.00 (3.62–4.38)
Source distribution
SD 0.87
skew -1.13
9 cells
left-skewed
1.02.03.04.05.0
§
Overall, how much do you like this rainbow trout? (Candida — partial protein replaced with Candida utilis yeast)
SSR
—
Source
3.76 (3.39–4.13)
Source distribution
SD 0.84
skew -0.74
9 cells
left-skewed
1.02.03.04.05.0
§
Overall, how much do you like this rainbow trout? (Nanno high — high inclusion of Nannochloropsis microalgae)
SSR
—
Source
3.74 (3.40–4.08)
Source distribution
SD 0.78
skew -0.59
9 cells
left-skewed
1.02.03.04.05.0
§
Overall, how much do you like this rainbow trout? (Nanno Low — low inclusion of Nannochloropsis microalgae)
SSR
—
Source
3.64 (3.37–3.92)
Source distribution
SD 0.62
skew 0.35
9 cells
unimodal
1.02.03.04.05.0
More on this shelf
Aquaculture sensory panels
9-pt hedonic on aquaculture species across feed systems (Control / Insects / Algae / Bioactive), iFishIENCi D3.6. The gradient is which feed system the panel actually prefers.