ChronoRoute

Experiments / E2

Header overhead

What wire cost buys per-hop time checking?

Label: DERIVED statistics and accounting Label: MODELLED network outcomes

Pre-registered hypothesis

T-CRH costs more than CRH-16 and less than SRv6 SRH over the registered segment counts. Relative to CRH-32 it trades a larger fixed part for a smaller per-entry part; enumerate the crossover and padding ties rather than assert a universal saving. Encapsulation adds the outer IPv6 header. This is exact code/byte accounting, not a statistical latency claim.

Frozen preregistration, identified and verified against this result’s manifest.

Verdict

Hypothesis supported: T-CRH adds more bytes than CRH-16 and fewer than SRv6 SRH at every registered entry count (1–40). Against CRH-32 there is a crossover: CRH-32 is smaller at 1–3, 5, 7 entries, equal at 4, 6, 8–11, 13, 15, and larger at 12, 14, 16–40.

  • Encoder checks: 240 of 320 rows checked, 0 violations.
  • Example (source insertion, 7 entries): T-CRH adds 40 bytes, CRH-32 32, CRH-16 24, SRv6 SRH 120.
  • The CRH-16 overhead penalty is a real cost (preregistration section 9).

Every number in this verdict is computed at build time from the verified summary.csv.

C5 orbital inputs are REAL public data; C2 orbits and positions are MODELLED. Topology, probes, faults and network behaviour are MODELLED. Starlink’s operational routing is UNKNOWN; Starlink does not use T-CRH.

Charts and data

Download CSV · Download manifest

Source: results/E02/20261011T214624Z-confirmatory/summary.csv. SHA-256: 1bc1d6162fdb4e3a77ba64347506d1f321ba4f3965632f1d65f2cd3a72fd2b1d.

This first view shows the 160 rows of the initial selection, out of 320. With scripting, the page loads the same summary.csv offered for download and checks its SHA-256 against the manifest before other selections are enabled.

Added on-wire bytes (bytes). Exact checks or accounting: sampling confidence intervals do not apply.
Values and confidence bounds from the verified summary CSV. Exact values are available in the data table. Infinite and undefined values are listed below.8.0000648.001 / tcrh: 16; exact accounting1 / crh16: 8; exact accounting1 / crh32: 8; exact accounting1 / srh: 24; exact accounting2 / tcrh: 24; exact accounting2 / crh16: 8; exact accounting2 / crh32: 16; exact accounting2 / srh: 40; exact accounting3 / tcrh: 24; exact accounting3 / crh16: 16; exact accounting3 / crh32: 16; exact accounting3 / srh: 56; exact accounting4 / tcrh: 24; exact accounting4 / crh16: 16; exact accounting4 / crh32: 24; exact accounting4 / srh: 72; exact accounting5 / tcrh: 32; exact accounting5 / crh16: 16; exact accounting5 / crh32: 24; exact accounting5 / srh: 88; exact accounting6 / tcrh: 32; exact accounting6 / crh16: 16; exact accounting6 / crh32: 32; exact accounting6 / srh: 104; exact accounting7 / tcrh: 40; exact accounting7 / crh16: 24; exact accounting7 / crh32: 32; exact accounting7 / srh: 120; exact accounting8 / tcrh: 40; exact accounting8 / crh16: 24; exact accounting8 / crh32: 40; exact accounting8 / srh: 136; exact accounting9 / tcrh: 40; exact accounting9 / crh16: 24; exact accounting9 / crh32: 40; exact accounting9 / srh: 152; exact accounting10 / tcrh: 48; exact accounting10 / crh16: 24; exact accounting10 / crh32: 48; exact accounting10 / srh: 168; exact accounting11 / tcrh: 48; exact accounting11 / crh16: 32; exact accounting11 / crh32: 48; exact accounting11 / srh: 184; exact accounting12 / tcrh: 48; exact accounting12 / crh16: 32; exact accounting12 / crh32: 56; exact accounting12 / srh: 200; exact accounting13 / tcrh: 56; exact accounting13 / crh16: 32; exact accounting13 / crh32: 56; exact accounting13 / srh: 216; exact accounting14 / tcrh: 56; exact accounting14 / crh16: 32; exact accounting14 / crh32: 64; exact accounting14 / srh: 232; exact accounting15 / tcrh: 64; exact accounting15 / crh16: 40; exact accounting15 / crh32: 64; exact accounting15 / srh: 248; exact accounting16 / tcrh: 64; exact accounting16 / crh16: 40; exact accounting16 / crh32: 72; exact accounting16 / srh: 264; exact accounting17 / tcrh: 64; exact accounting17 / crh16: 40; exact accounting17 / crh32: 72; exact accounting17 / srh: 280; exact accounting18 / tcrh: 72; exact accounting18 / crh16: 40; exact accounting18 / crh32: 80; exact accounting18 / srh: 296; exact accounting19 / tcrh: 72; exact accounting19 / crh16: 48; exact accounting19 / crh32: 80; exact accounting19 / srh: 312; exact accounting20 / tcrh: 72; exact accounting20 / crh16: 48; exact accounting20 / crh32: 88; exact accounting20 / srh: 328; exact accounting21 / tcrh: 80; exact accounting21 / crh16: 48; exact accounting21 / crh32: 88; exact accounting21 / srh: 344; exact accounting22 / tcrh: 80; exact accounting22 / crh16: 48; exact accounting22 / crh32: 96; exact accounting22 / srh: 360; exact accounting23 / tcrh: 88; exact accounting23 / crh16: 56; exact accounting23 / crh32: 96; exact accounting23 / srh: 376; exact accounting24 / tcrh: 88; exact accounting24 / crh16: 56; exact accounting24 / crh32: 104; exact accounting24 / srh: 392; exact accounting25 / tcrh: 88; exact accounting25 / crh16: 56; exact accounting25 / crh32: 104; exact accounting25 / srh: 408; exact accounting26 / tcrh: 96; exact accounting26 / crh16: 56; exact accounting26 / crh32: 112; exact accounting26 / srh: 424; exact accounting27 / tcrh: 96; exact accounting27 / crh16: 64; exact accounting27 / crh32: 112; exact accounting27 / srh: 440; exact accounting28 / tcrh: 96; exact accounting28 / crh16: 64; exact accounting28 / crh32: 120; exact accounting28 / srh: 456; exact accounting29 / tcrh: 104; exact accounting29 / crh16: 64; exact accounting29 / crh32: 120; exact accounting29 / srh: 472; exact accounting30 / tcrh: 104; exact accounting30 / crh16: 64; exact accounting30 / crh32: 128; exact accounting30 / srh: 488; exact accounting31 / tcrh: 112; exact accounting31 / crh16: 72; exact accounting31 / crh32: 128; exact accounting31 / srh: 504; exact accounting32 / tcrh: 112; exact accounting32 / crh16: 72; exact accounting32 / crh32: 136; exact accounting32 / srh: 520; exact accounting33 / tcrh: 112; exact accounting33 / crh16: 72; exact accounting33 / crh32: 136; exact accounting33 / srh: 536; exact accounting34 / tcrh: 120; exact accounting34 / crh16: 72; exact accounting34 / crh32: 144; exact accounting34 / srh: 552; exact accounting35 / tcrh: 120; exact accounting35 / crh16: 80; exact accounting35 / crh32: 144; exact accounting35 / srh: 568; exact accounting36 / tcrh: 120; exact accounting36 / crh16: 80; exact accounting36 / crh32: 152; exact accounting36 / srh: 584; exact accounting37 / tcrh: 128; exact accounting37 / crh16: 80; exact accounting37 / crh32: 152; exact accounting37 / srh: 600; exact accounting38 / tcrh: 128; exact accounting38 / crh16: 80; exact accounting38 / crh32: 160; exact accounting38 / srh: 616; exact accounting39 / tcrh: 136; exact accounting39 / crh16: 88; exact accounting39 / crh32: 160; exact accounting39 / srh: 632; exact accounting40 / tcrh: 136; exact accounting40 / crh16: 88; exact accounting40 / crh32: 168; exact accounting40 / srh: 648; exact accounting16111621263136tcrhcrh16crh32srh

Data table

Showing 1–25 of 160 matching rows. The download contains every original row and column.

Values from summary.csv. Empty fields are shown as undefined; infinite effective latency remains infinite; a p-value stored as 0 is shown as below numerical resolution.
entriesprotocolmodeheader_bytesadded_bytesreference_bytesreference_percentfinal_percentencoder_checkedencoder_violationslabel
1tcrhsource161614001.14285714285714281.1299435028248588True0DERIVED
1crh16source8814000.57142857142857140.5681818181818182True0DERIVED
1crh32source8814000.57142857142857140.5681818181818182True0DERIVED
1srhsource242414001.71428571428571421.6853932584269662False0DERIVED
2tcrhsource242414001.71428571428571421.6853932584269662True0DERIVED
2crh16source8814000.57142857142857140.5681818181818182True0DERIVED
2crh32source161614001.14285714285714281.1299435028248588True0DERIVED
2srhsource404014002.8571428571428572.7777777777777777False0DERIVED
3tcrhsource242414001.71428571428571421.6853932584269662True0DERIVED
3crh16source161614001.14285714285714281.1299435028248588True0DERIVED
3crh32source161614001.14285714285714281.1299435028248588True0DERIVED
3srhsource565614004.03.8461538461538463False0DERIVED
4tcrhsource242414001.71428571428571421.6853932584269662True0DERIVED
4crh16source161614001.14285714285714281.1299435028248588True0DERIVED
4crh32source242414001.71428571428571421.6853932584269662True0DERIVED
4srhsource727214005.1428571428571434.891304347826087False0DERIVED
5tcrhsource323214002.28571428571428562.2346368715083798True0DERIVED
5crh16source161614001.14285714285714281.1299435028248588True0DERIVED
5crh32source242414001.71428571428571421.6853932584269662True0DERIVED
5srhsource888814006.2857142857142865.913978494623656False0DERIVED
6tcrhsource323214002.28571428571428562.2346368715083798True0DERIVED
6crh16source161614001.14285714285714281.1299435028248588True0DERIVED
6crh32source323214002.28571428571428562.2346368715083798True0DERIVED
6srhsource10410414007.4285714285714296.914893617021277False0DERIVED
7tcrhsource404014002.8571428571428572.7777777777777777True0DERIVED

Where ChronoRoute loses

Every listed point disadvantage is retained, including privileged-oracle advantages. Where a registered paired comparison exists for the same cell, its paired Student-t 95% interval and Holm-adjusted p-value are quoted; otherwise marginal intervals alone do not establish a significant loss. Ties in the predicted stuck-loss reduction are listed as unsupported advantages.

The CRH-16 overhead penalty is a real cost at every entry count, and CRH-32 is smaller than T-CRH at small entry counts; both are listed below.

Descriptive comparisons from the same summary; source row numbers count data rows, excluding the header.
CellMetricPolicyChronoRouteComparatorComparator valueInterpretationSource rows
source / entries 1added_bytestcrh16crh168Header cost disadvantage1, 3
source / entries 1added_bytestcrh16crh328Header cost disadvantage1, 5
encap / entries 1added_bytestcrh56crh1648Header cost disadvantage2, 4
encap / entries 1added_bytestcrh56crh3248Header cost disadvantage2, 6
source / entries 2added_bytestcrh24crh168Header cost disadvantage9, 11
source / entries 2added_bytestcrh24crh3216Header cost disadvantage9, 13
encap / entries 2added_bytestcrh64crh1648Header cost disadvantage10, 12
encap / entries 2added_bytestcrh64crh3256Header cost disadvantage10, 14
source / entries 3added_bytestcrh24crh1616Header cost disadvantage17, 19
source / entries 3added_bytestcrh24crh3216Header cost disadvantage17, 21
encap / entries 3added_bytestcrh64crh1656Header cost disadvantage18, 20
encap / entries 3added_bytestcrh64crh3256Header cost disadvantage18, 22
source / entries 4added_bytestcrh24crh1616Header cost disadvantage25, 27
encap / entries 4added_bytestcrh64crh1656Header cost disadvantage26, 28
source / entries 5added_bytestcrh32crh1616Header cost disadvantage33, 35
source / entries 5added_bytestcrh32crh3224Header cost disadvantage33, 37
encap / entries 5added_bytestcrh72crh1656Header cost disadvantage34, 36
encap / entries 5added_bytestcrh72crh3264Header cost disadvantage34, 38
source / entries 6added_bytestcrh32crh1616Header cost disadvantage41, 43
encap / entries 6added_bytestcrh72crh1656Header cost disadvantage42, 44
source / entries 7added_bytestcrh40crh1624Header cost disadvantage49, 51
source / entries 7added_bytestcrh40crh3232Header cost disadvantage49, 53
encap / entries 7added_bytestcrh80crh1664Header cost disadvantage50, 52
encap / entries 7added_bytestcrh80crh3272Header cost disadvantage50, 54
source / entries 8added_bytestcrh40crh1624Header cost disadvantage57, 59
encap / entries 8added_bytestcrh80crh1664Header cost disadvantage58, 60
source / entries 9added_bytestcrh40crh1624Header cost disadvantage65, 67
encap / entries 9added_bytestcrh80crh1664Header cost disadvantage66, 68
source / entries 10added_bytestcrh48crh1624Header cost disadvantage73, 75
encap / entries 10added_bytestcrh88crh1664Header cost disadvantage74, 76
source / entries 11added_bytestcrh48crh1632Header cost disadvantage81, 83
encap / entries 11added_bytestcrh88crh1672Header cost disadvantage82, 84
source / entries 12added_bytestcrh48crh1632Header cost disadvantage89, 91
encap / entries 12added_bytestcrh88crh1672Header cost disadvantage90, 92
source / entries 13added_bytestcrh56crh1632Header cost disadvantage97, 99
encap / entries 13added_bytestcrh96crh1672Header cost disadvantage98, 100
source / entries 14added_bytestcrh56crh1632Header cost disadvantage105, 107
encap / entries 14added_bytestcrh96crh1672Header cost disadvantage106, 108
source / entries 15added_bytestcrh64crh1640Header cost disadvantage113, 115
encap / entries 15added_bytestcrh104crh1680Header cost disadvantage114, 116
source / entries 16added_bytestcrh64crh1640Header cost disadvantage121, 123
encap / entries 16added_bytestcrh104crh1680Header cost disadvantage122, 124
source / entries 17added_bytestcrh64crh1640Header cost disadvantage129, 131
encap / entries 17added_bytestcrh104crh1680Header cost disadvantage130, 132
source / entries 18added_bytestcrh72crh1640Header cost disadvantage137, 139
encap / entries 18added_bytestcrh112crh1680Header cost disadvantage138, 140
source / entries 19added_bytestcrh72crh1648Header cost disadvantage145, 147
encap / entries 19added_bytestcrh112crh1688Header cost disadvantage146, 148
source / entries 20added_bytestcrh72crh1648Header cost disadvantage153, 155
encap / entries 20added_bytestcrh112crh1688Header cost disadvantage154, 156
source / entries 21added_bytestcrh80crh1648Header cost disadvantage161, 163
encap / entries 21added_bytestcrh120crh1688Header cost disadvantage162, 164
source / entries 22added_bytestcrh80crh1648Header cost disadvantage169, 171
encap / entries 22added_bytestcrh120crh1688Header cost disadvantage170, 172
source / entries 23added_bytestcrh88crh1656Header cost disadvantage177, 179
encap / entries 23added_bytestcrh128crh1696Header cost disadvantage178, 180
source / entries 24added_bytestcrh88crh1656Header cost disadvantage185, 187
encap / entries 24added_bytestcrh128crh1696Header cost disadvantage186, 188
source / entries 25added_bytestcrh88crh1656Header cost disadvantage193, 195
encap / entries 25added_bytestcrh128crh1696Header cost disadvantage194, 196
source / entries 26added_bytestcrh96crh1656Header cost disadvantage201, 203
encap / entries 26added_bytestcrh136crh1696Header cost disadvantage202, 204
source / entries 27added_bytestcrh96crh1664Header cost disadvantage209, 211
encap / entries 27added_bytestcrh136crh16104Header cost disadvantage210, 212
source / entries 28added_bytestcrh96crh1664Header cost disadvantage217, 219
encap / entries 28added_bytestcrh136crh16104Header cost disadvantage218, 220
source / entries 29added_bytestcrh104crh1664Header cost disadvantage225, 227
encap / entries 29added_bytestcrh144crh16104Header cost disadvantage226, 228
source / entries 30added_bytestcrh104crh1664Header cost disadvantage233, 235
encap / entries 30added_bytestcrh144crh16104Header cost disadvantage234, 236
source / entries 31added_bytestcrh112crh1672Header cost disadvantage241, 243
encap / entries 31added_bytestcrh152crh16112Header cost disadvantage242, 244
source / entries 32added_bytestcrh112crh1672Header cost disadvantage249, 251
encap / entries 32added_bytestcrh152crh16112Header cost disadvantage250, 252
source / entries 33added_bytestcrh112crh1672Header cost disadvantage257, 259
encap / entries 33added_bytestcrh152crh16112Header cost disadvantage258, 260
source / entries 34added_bytestcrh120crh1672Header cost disadvantage265, 267
encap / entries 34added_bytestcrh160crh16112Header cost disadvantage266, 268
source / entries 35added_bytestcrh120crh1680Header cost disadvantage273, 275
encap / entries 35added_bytestcrh160crh16120Header cost disadvantage274, 276
source / entries 36added_bytestcrh120crh1680Header cost disadvantage281, 283
encap / entries 36added_bytestcrh160crh16120Header cost disadvantage282, 284
source / entries 37added_bytestcrh128crh1680Header cost disadvantage289, 291
encap / entries 37added_bytestcrh168crh16120Header cost disadvantage290, 292
source / entries 38added_bytestcrh128crh1680Header cost disadvantage297, 299
encap / entries 38added_bytestcrh168crh16120Header cost disadvantage298, 300
source / entries 39added_bytestcrh136crh1688Header cost disadvantage305, 307
encap / entries 39added_bytestcrh176crh16128Header cost disadvantage306, 308
source / entries 40added_bytestcrh136crh1688Header cost disadvantage313, 315
encap / entries 40added_bytestcrh176crh16128Header cost disadvantage314, 316

Limitations

  • Exact encoder and padding accounting has no sampling confidence interval.
  • This page reads summary.csv only. The capture comparison (capture_summary.csv and capture_frames.csv.gz in the same result folder) is not read here, so no capture agreement claim is made on this page.
  • Only T-CRH appears in the captures; SRH sizes are exact accounting without a captured SRH encoder.
  • Header savings are not measured latency or throughput savings.

These pages use only summary.csv and manifest.json; each file is checked against the manifest SHA-256. They do not infer missing comparisons from figures, reports, raw traces or other result files.

How this was made

Recorded producer
E02 exact accounting (1.0.0.dev0)
Manifest commit
8004d42f0053673fb6750c12353e4236651ed140; dirty: false
Run
48b4955de5beef53
Time
2026-10-11T21:46:24.387457Z to 2026-10-11T21:46:30.494849Z; 6.107377 seconds of recorded host wall time (REAL)
Snapshot
20261010T1358Z-celestrak; SHA-256: c37e70812155c2d1d9eeb3e96681303c00c9fca91287939b21bf5313ce83aecd
Seeds
No random seed applies
Command
venv/bin/python -B experiments/E02/account.py --out results/E02/20261011T214624Z-confirmatory
Config SHA-256
7bf6f234012c65396aa11b4e27c09ee4aa95089ae16f4e17131285ce010a75e2
Labels
  • pcap_addresses: MODELLED
  • pcap_timestamps: MODELLED
  • routes_and_budgets: DERIVED
  • tcrh_header_bytes: REAL
Manifest

chronoroute.manifest/1; 6 recorded output files (333375 bytes); 4 recorded input hashes. Download the full manifest (4102 bytes, SHA-256 320b36986a21223a1dcc4fd48b3d78e5e0bf9cfd78ac1f2db245d3088c64be70) for the configuration, versions, host and every input and output hash.

  • summary.csv: 24832 bytes, SHA-256 1bc1d6162fdb4e3a77ba64347506d1f321ba4f3965632f1d65f2cd3a72fd2b1d
  • Versions: chronoroute 1.0.0.dev0; matplotlib 3.11.1; networkx 3.6.1; numpy 2.5.3; python 3.14.4; sgp4 2.27
  • Host (REAL): cpu_model: 13th Gen Intel(R) Core(TM) i9-13900H; logical_cores: 20; machine: x86_64; platform: Linux-6.18.33.2-microsoft-standard-WSL2-x86_64-with-glibc2.43; ram_bytes: 8131362816

For collected results, the manifest commit identifies the collector. Input hashes preserve the producer chain in the downloaded manifest; this page does not load those additional files.