SC-PNC: Semantic Communication-Empowered Physical-Layer Network Coding
Bibliographic record
Abstract
This paper puts forth the first framework for semantic communication (SC)-empowered physical-layer network coding (PNC), referred to as SC-PNC. Although conventional bit-oriented PNC can enhance the throughput of wireless relay networks by turning mutual wireless interference into useful network-coded information, it faces two primary problems that limit its application in practice. First, bit-oriented PNC decoding is susceptible to the relative phase offsets among signals received from different nodes; in particular, some “bad” relative phase offsets could lead to significant performance degradation. Second, the scheduling design of bit-oriented PNC transmissions is limited by the bitwise operation. To address these issues, this paper designs SC-PNC, which leverages semantic communication to bypass the need for bit-perfect message recovery at the destination. First, we employ a two-way relay network (TWRN) to demonstrate how SC-PNC effectively mitigates the detrimental effects of “bad” relative phase offsets. Then, we explore a triangular relay network (TriRN) to show how we can take advantage of semantic communication to redesign the scheduling of PNC transmissions. Specifically, an SC-PNC TriRN architecture is designed, wherein each node receives information from the other two nodes in only two time slots. Taking image delivery as an example, experimental results reveal that SC-PNC consistently achieves high and stable image reconstruction quality under different channel conditions and relative phase offsets, outperforming the conventional bit-oriented counterparts. Moreover, the new two-slot SC-PNC TriRN architecture is effective in extracting semantically accurate information from images, showcasing its potential as a low-latency solution for semantic information exchange.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".