Your Temporal Link Predictor Is Blind to Who Is Active: A Missing Factor That Transfers Across Models

An interaction has two parts: someone decides to act, and then chooses whom to act on. Temporal link prediction has concentrated on the second, and we show that it is blind to the first by construction: a standard negative keeps the real source and swaps the destination, and we prove that this cancels the source's activity exactly from the optimal score, so no model trained and evaluated this way is ever rewarded for learning it. Under the harder historical and inductive negatives, whose sources differ, the same factor becomes the dominant signal. We model it with **Source Node Activity Modeling (SNAM)**, a self-exciting event intensity fitted by an exact point-process likelihood to decayed interaction counts the history states already contain; it has **fewer than 20 parameters**. On their own, never looking at the destination, **these parameters beat DyGFormer and TPNet** on four of five datasets under historical negatives. Added to the frozen scores of TPNet, TGN, DyGFormer and DSRD, four models of different design, **without retraining anything**, they raise AP on every backbone–dataset pair in both settings, by up to 25 points. Our full model ranks first overall against eleven baselines on 13 datasets and three protocols, and on million-event streams trains an epoch 9–100 times faster than TPNet and DyGFormer. We conclude that source activity is a blind spot of temporal link prediction, and a cheap, transferable one to close.