MétaCan
Menu
← Back to cohort
Record W7104027439 · doi:10.5683/sp3/kiu3r6

Transitioning dairy cows to automatic milking: predictive effects of training on post transition AMS use

2025· dataset· W7104027439 on OpenAlexaff

Bibliographic record

VenueBorealis · 2025
Typedataset
Language
Field
Topic
Canadian institutionsUniversity of British Columbia
Fundersnot available
KeywordsMilkingInterval trainingAutomatic milkingConfidence intervalTraining (meteorology)Attendance

Abstract

fetched live from OpenAlex

Dairy cows transitioning to automatic milking systems (AMS) must learn to visit the unit voluntarily; cows that fail to do so must be fetched repeatedly, increasing the risk of negative human-animal interactions. Delayed visits also carry welfare consequences, including udder engorgement and reduced lying and feeding times. Understanding why some cows adapt poorly, and whether they can be identified early, is important for developing management strategies for the transition period. We tested whether positive reinforcement training (PRT) could ease a herd-wide transition to AMS, and whether individual responses to training predicted subsequent AMS use. We enrolled 181 lactating Holstein cows housed in four pens, each with one AMS unit. Before the transition, cows received either baseline training alone (control; n = 71) or baseline training preceded by PRT (n = 110). Treatment was randomised at the cow level in one pen and assigned at the pen level in the remaining three. During PRT, cows were given one opportunity daily to approach and enter the AMS, with pelleted concentrate as an incentive. After each session, cows were scored on the furthest stage of engagement reached: Step 1 (no interaction), Step 2 (approached but did not enter), or Step 3 (entered or walked through). Cow behaviour was monitored for four weeks following the transition, with the daily maximum interval between AMS visits as the primary outcome variable. We tested the effect of PRT in the randomised pen, then examined whether training progression predicted subsequent AMS use across all PRT-trained cows. PRT had no detectable effect on maximum visit interval in the randomised pen (difference between control and treatment: 8.3 ± 39.2 min; 95% CI: -70.7 to 87.3 min). Among PRT-trained cows, however, those that engaged the least had the longest maximum intervals between visits: Step 1 (n = 6; 877.0 ± 50.4 min), Step 2 (n = 50; 720.0 ± 20.5 min), and Step 3 (n = 54; 593.9 ± 17.7 min). Individual responses to PRT may provide an early indicator of how well a cow will behaviourally adjust to AMS milking, allowing those at greater risk of a difficult transition to be identified before it begins. More broadly, these findings suggest that understanding AMS adaptation in dairy cows may require looking beyond the overall effects of training interventions or broad behavioural traits, and instead focusing on the behaviours cows express towards the technology itself as a more direct indicator of adaptation.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Dataset · Consensus signal: none
Teacher disagreement score0.002
Threshold uncertainty score0.003

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.017
GPT teacher head0.265
Teacher spread0.248 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreDataset

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueBorealis→French-language works237,207→