# Interactive Query Answering on Hetionet (test)

Source: [Interactive Query Answering on Hetionet (test)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-27T14:28:56.851Z

Evaluation of model performance on the test split of the Hetionet dataset for Interactive Query Answering, measured using various pairwise accuracy, Mean Reciprocal Rank (MRR), and NDCG@10 metrics across different path configurations.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Interactive query answering |
| Dataset (including any stated split) | Hetionet (test) |
| Metric | Avg Pairwise Acc (1p) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Avg Pairwise Acc (1p)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(1p)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (2p)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(2p)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (3p)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(3p)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (2i)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(2i)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (3i)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(3i)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (ip)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(ip)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (pi)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(pi)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (2in)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(2in)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (3in)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(3in)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (inp)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(inp)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (pin)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(pin)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (pni)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(pni)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (2u)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(2u)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (up)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(up)>): Higher is better; unit: PERCENT.

- [Avg Pairwise Acc (avg)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20Pairwise%20Acc%20(avg)>): Higher is better; unit: PERCENT.

- [Avg MRR (1p)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(1p)>): Higher is better; unit: SCALAR.

- [Avg MRR (2p)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(2p)>): Higher is better; unit: SCALAR.

- [Avg MRR (3p)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(3p)>): Higher is better; unit: SCALAR.

- [Avg MRR (2i)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(2i)>): Higher is better; unit: SCALAR.

- [Avg MRR (3i)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(3i)>): Higher is better; unit: SCALAR.

- [Avg MRR (ip)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(ip)>): Higher is better; unit: SCALAR.

- [Avg MRR (pi)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(pi)>): Higher is better; unit: SCALAR.

- [Avg MRR (2in)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(2in)>): Higher is better; unit: SCALAR.

- [Avg MRR (3in)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(3in)>): Higher is better; unit: SCALAR.

- [Avg MRR (inp)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(inp)>): Higher is better; unit: SCALAR.

- [Avg MRR (pin)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(pin)>): Higher is better; unit: SCALAR.

- [Avg MRR (pni)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(pni)>): Higher is better; unit: SCALAR.

- [Avg MRR (2u)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(2u)>): Higher is better; unit: SCALAR.

- [Avg MRR (up)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(up)>): Higher is better; unit: SCALAR.

- [Avg MRR (avg)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20MRR%20(avg)>): Higher is better; unit: SCALAR.

- [Avg NDCG@10 (1p)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(1p)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (2p)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(2p)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (3p)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(3p)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (2i)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(2i)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (3i)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(3i)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (ip)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(ip)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (pi)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(pi)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (2in)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(2in)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (3in)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(3in)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (inp)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(inp)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (pin)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(pin)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (pni)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(pni)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (2u)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(2u)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (up)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(up)>): Higher is better; unit: PERCENT.

- [Avg NDCG@10 (avg)](<https://www.sota2.com/research/sota/interactive-query-answering-on-hetionet-test.md?metric=Avg%20NDCG%4010%20(avg)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Avg Pairwise Acc (1p) | Result date | Report paper |
| --- | --- | --- | --- |
| LightGBM | 79.18 | Not recorded | 68fa7abf1e209131cea84f6e |
| Cosine | 75.27 | Not recorded | 68fa7abf1e209131cea84f6e |
| NQR | 68.17 | Not recorded | 68fa7abf1e209131cea84f6e |
| Unconstrained | 51.75 | Not recorded | 68fa7abf1e209131cea84f6e |

### LightGBM

Avg Pairwise Acc (1p): 79.18. Result ID: 69c6933647f34ce924b0efd0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7abf1e209131cea84f6e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Cosine

Avg Pairwise Acc (1p): 75.27. Result ID: 69c6933647f34ce924b0efd1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7abf1e209131cea84f6e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7abf1e209131cea84f6e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### NQR

Avg Pairwise Acc (1p): 68.17. Result ID: 69c6933647f34ce924b0efd2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7abf1e209131cea84f6e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7abf1e209131cea84f6e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Unconstrained

Avg Pairwise Acc (1p): 51.75. Result ID: 69c6933647f34ce924b0efcf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7abf1e209131cea84f6e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fa61e209131cea46e17.md>)

[Implementation](<https://github.com/bys0318/QTO>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.