Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/acmmm-experiments
Use when designing or auditing the experiments of an ACM MM (ACM Multimedia) paper — matched baselines per modality, ablations that isolate the cross-modal fusion, user studies or QoE measurement where the claim is subjective, dataset and media licensing, and honest compute reporting, so evidence supports a multimedia claim.
Passed 20 of 22 test cases with the skill, and 19 of 22 without it.
1 fixed19 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
Can you conduct an experimental check on my draft paper for ACM MM regarding cross-modal retrieval? I've listed our benchmark scores against baseline models, our feature fusion ablations, dataset licenses, and run times below. Please provide your review formatted with the exact bracketed tags: [Works], [Fusion causal], [Failure analysis], [Perceptual claim], [Data + compute], and [Top fixes].
| Checked | Without skill | With skill |
|---|---|---|
| Prioritizes necessary paper revisions by urgency for submission or rebuttal | Missed | Passed |
The instructions your model reads when the skill loads.
Use this to make an ACM Multimedia paper's evidence match its claim. The reviewer's implicit questions are: does it work, does the cross-modal part cause the gain, when does it fail, and — if the target is perceptual — do people actually prefer it.
| Question | Evidence that answers it |
|---|---|
| Does it work? | The headline metric on a recognized benchmark, against strong, matched baselines |
| Does the fusion cause the gain? | A leave-one-modality-out / component ablation isolating the cross-modal term |
| When does it fail? | Failure cases per modality (e.g., noisy audio, missing captions) shown honestly |
| Do people prefer it? | A user study with reported N, protocol, and inter-rater agreement — for subjective claims |
The second row is what separates an ACM MM experiment section from a single-modality one: if removing a modality does not move the result, the paper is not really cross-modal.
Full model .................... reference
- audio stream ................ tests whether audio carries signal
- text/caption stream ......... tests whether language carries signal
- alignment / fusion module ... replaced by concatenation: tests the MECHANISM
- synchronization assumption .. shuffled timing: tests whether cross-modal timing matters
Report each ablation with the same metric and variance as the headline, and state which term carries most of the gain — reviewers reward a paper that can point to why it works.
test cases passed, vs 19 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.