Published November 12, 2026
| Version v4.0
Software
Open
Reading Why: Born-Measured Attention with Exact Word Evidence on Light and Qubits
Authors/Creators
- 1. School of Integrated Innovative Technology, King Mongkut's Institute of Technology Ladkrabang
- 2. Faculty of Science and Technology, Suan Dusit University
Description
The code, models, data and IBM job records behind the fourth arXiv version of the paper (arXiv:2611.05355v4). The paper's PDF is attached.
What is new since v3.2.1:
- Compute-uncompute on ibm_kingston. Four new jobs (pair 3765 and pair 3763 without "aliens"; 580 circuits, 316 quantum seconds) read each attention Born weight as the probability of 0000.
src/cu_analysis.pygives the answers, calibrations and evidence from the recorded counts;src/hw_cu_compare.pycompares the two methods on the same Born weights. The device gave the model's answers; the evidence followed the exact one on one run (0.971) and not on the other (0.48). - What each device check can show.
src/device_power.py,device_blocks.py,device_rows.py,device_errors.py,device_floor.py,device_rowsd.py,device_block2_nulls.py: uniform and random attention, block by block; the error per circuit against shot noise; nulls for the evidence check. - The shots the evidence needs.
src/shot_bound.pychecks the paper's proposition on 100 pairs (results/shot_bound.jsonholds our run);src/device_shot_floor.pycompares it with the device. - Baselines. An order-free bag of embeddings (
src/bag_baseline.py, 77.79 +- 0.26 %; seed-0 weights inresults/) and its own evidence (src/bag_evidence.py); rankings that need no model and the evidence across seeds (src/esnli_baselines.py,src/esnli_seed_stability.py). - Optics and the coherent circuit.
src/photon_draws.py(shot noise over 20 draws, photons per detector);src/coherent23.py(the 23-qubit circuit as counted, from |0...0>).
What the numbers say is in the README: accuracy does not set the models apart; the top-word deletion gain is the model's, not the evidence method's; exactness buys the complete sum and a better low end of the ranking. Account details are removed from every job record.
Notes
Files
stein-research/reading-why-v4.0.zip
Additional details
Related works
- Is supplement to
- Software: https://github.com/stein-research/reading-why/tree/v4.0 (URL)
Software
- Repository URL
- https://github.com/stein-research/reading-why