"... In PAGE 82: ... We conducted this experiment with both the PH algorithm and our 2-level TPCM algorithm. As the results in Table9 show, both placement techniques benefit from hot-cold splitting to about the same degree. The considerable improvement achieved by this simple technique shows that it is definitely worthwhile to combine hot- cold splitting with procedure placement techniques.... ..."

"... In PAGE 9: ....1. Micro-benchmarks Despite the obvious pitfalls of micro-benchmarks [3], they can be used to give a rough idea of the cost of various primitives. Table2 compares the cost of various protection switching schemes under Linux 2.... ..."

"... In PAGE 4: ... All the locations from the pain experiments are shown in two panels in flgure 1, where the color indicates the experiments the locations originate from. Table1 lists all the included 24 hot and 8 cold pain experiments. Note that the pain stimulus is induced under varying contexts and some studies contributed with several experiments, e.... ..."

"... In PAGE 6: ... Now that we have a validation that the OSPF domain ad- versely impacts the BGP domain, we can begin to focus our experiments on the hypothesized cause of the interruptions. In Table6 we investigate the effects of cold versus hot potato routing. In this design we perform a simple full-factorial of RRS optimizations, turning Hot Potato routing on/off, and the MED on/off within the BGP decision algorithm.... ..."

"... In PAGE 98: ....7.2 Supporting Transactions Four di erent workloads are used in the rst set of experiments designed to evaluate slice consistency in a transactions-only environment. Table14 lists the parameters used for the di erent workloads. Figure 25 shows the performance of di erent methods in a high data contention... In PAGE 104: ... In the rst experiment, 50% of the clients have the hot-cold workload and the rest use the shared-hot workload. The parameters for the two workloads are the same as before ( Table14 ). For slice consistency, the clients running the hot-cold workload use the aggressive variation, while the clients with shared-hot workload use the lazy variation.... In PAGE 108: ... Figures 36 and 37 show the throughput when 10% of the transactions are queries with 100 references each in the hot-cold and the uniform workloads, respectively. The remaining parameters are the same as in Table14 . Here again, avoiding contention between queries and transactions results in 25% to 50% higher throughput for slice consistency for both the workloads.... ..."

"... In PAGE 19: ... In other words any query routing technique could be applied in our setting in order to define the top-k candidate objects. Table3 compares HT-p2p with dominant approaches in top-k query processing for distributed networks. HT-p2p and the approach of [11, 17], are the only ones that are adapted to super-peer p2p networks and, as such, take advantage of the heterogeneity of peers and of a topology that reduces bandwidth by eliminating the transferred messages between peers.... ..."

"... In PAGE 6: ... QFmin was set to 1, 3, 5 and 1, where QFmin = 1 means that no key is activated and only the basic single term index is used to process the queries. Table1 shows the achieved precisions at K (P@K). The highest value in each line of the table is highlighted in bold.... In PAGE 6: ... However, we believe this should not be a problem in the context of Web search where users are usually only in- terested in the top 10-20 documents. In addition, for K gt;20, Table1 also shows that, with a higher value for DFmax, our system is becoming similar to ST-BM25 (in fact, if DFmax = jDj, our system is ex- actly equivalent to ST-BM25). In the worst case, when DFmax = 100 (we only keep top-100 documents in the post- ing lists) and QFmin = 1 (the query driven mechanism is not applied), our system retrieves 75% of the relevant doc- uments retrieved by ST-BM25 at top-50 (0.... ..."

"... In PAGE 10: ... There are very few occurrences of \photographic quot; under keyword, while all occurrences are under dataset. Table2 shows the results of our experiment. For each value of k, we report the speedup obtained through our algorithm, measured as the ratio of the time taken to fully execute the query on the database to the time taken by our algorithm.... ..."

"... In PAGE 17: ... After computing these statistics, we computed the estimated number of complaints of each kind for each building and compared them with the observed number of hot and cold complaints from each building. Table5 shows the number of observed hot and cold complaints for each building during each interval. E1 and F1 correspond to Interval 1 in Table 3.... ..."