Pre-debate, pre-establishment CIVOBS dry run with two CIV parameters.
Sivasubramanian M
ChatGPT said:
Let’s put on our "Internet cartographer" hat and look at the two parameters:
1. Openness – free flow of information
2. End-to-End Principle – the ability of any two users to connect directly, without gatekeepers shaping or blocking communications.
a) Worldwide snapshot
Openness:
Globally, the Internet is very uneven in this respect.
-
Highly open environments: Much of Europe, North America, parts of Latin America, and a few Asian democracies (e.g. Japan, Taiwan) have strong legal frameworks that protect speech and restrict arbitrary filtering.
-
Partially open: India, Brazil, South Africa and many others have constitutional protections for expression, but governments and corporations sometimes restrict access—blocking platforms, throttling during protests, or mandating data localization.
-
Restrictive: China, Iran, Russia, and a growing club of states operate heavily filtered, surveilled, and “walled” Internets. In these systems, the flow of information is systematically censored, and cross-border connections are closely monitored or throttled.
End-to-End Principle:
This principle was core to the original Internet design, but has been eroded almost everywhere.
-
ISP practices: Many ISPs apply NAT (Network Address Translation), carrier-grade NAT, or firewalls that prevent true peer-to-peer connections. IPv6 adoption (which restores user-level addressing) is happening, but unevenly.
-
Platformization: Much end-to-end communication has been replaced by client-to-platform-to-client (e.g. social media intermediaries), meaning "end-to-end" now often involves corporate-controlled servers as the middleman.
-
Policy restrictions: In authoritarian contexts, entire categories of traffic (VoIP, VPNs, Tor) are restricted or banned, deliberately undermining the end-to-end model.
So worldwide, we see:
-
Openness under significant political pressure.
-
End-to-end weakened both by commercial convenience (middlemen platforms) and deliberate state controls.
b) Canada
Openness:
Canada sits on the “generally open” end of the spectrum. There are no nationwide firewalls or systematic censorship mechanisms. Courts occasionally order ISPs to block piracy sites (e.g. IPTV streaming or torrent sites), but these are targeted rather than wholesale. Laws like the Online Streaming Act (Bill C-11, 2023) raise debates: critics argue it could influence what content is promoted on platforms, but it does not amount to outright blocking. So openness is good, though there are tensions between cultural regulation and pure free flow.
End-to-End Principle:
-
ISPs: Canada’s ISPs use NAT and firewalls like elsewhere, so most users are not globally reachable on IPv4. IPv6 deployment is patchy but improving—some providers (like Bell and Rogers) now enable IPv6 by default, which restores direct addressing in principle.
-
Net neutrality: Canada has strong net neutrality protections via the CRTC (Canadian Radio-television and Telecommunications Commission). ISPs cannot throttle or prioritize traffic based on content type, which bolsters the spirit of end-to-end.
-
Corporate mediation: As elsewhere, many communications (chat, video, social media) are intermediated by large US-based platforms, so the "directness" is often more logical than physical.
So compared to the global scene, Canada’s Internet is:
-
Among the more open, with only modest pressures from cultural/rights-management regulation.
-
Still compromised in end-to-end terms by IPv4 address exhaustion, platform centralization, and the practical dominance of intermediaries—but with a relatively healthy regulatory stance on neutrality.
To telescope out: if the observatory wants to measure these things, they might need a mixed-method approach. Technical measurements (e.g. IPv6 reachability, censorship tests like OONI probes, traceroutes for gatekeeping) combined with policy/legal analysis (e.g. censorship laws, neutrality rulings, corporate transparency) would give a clearer picture.
Do you want me to sketch what such an observatory’s metrics might look like in practice—like a starter “dashboard” of what to measure for openness and end-to-end? That would make this less abstract and more actionable.
You said:
ChatGPT said:
Perfect, let’s get down to brass tacks. If the “Observatory on Core Internet Values” is to be more than just a think-piece, it needs metrics that are empirical, repeatable, and comparable across countries. For the two parameters, here’s how I’d sketch a starter dashboard:
1. Openness – free flow of information
a. Legal/Policy indicators (desk research):
-
Censorship laws: Does the country mandate blocking/filtering of political, social, or cultural content? (Yes/No/Scope)
-
Platform regulation: Are platforms required to remove content or adjust algorithms under government order?
-
Transparency of blocking: Do governments publish blocklists, or is censorship opaque?
-
International rankings: Cross-reference with Freedom House’s Freedom on the Net or Article 19’s expression indices.
b. Technical/Measurement indicators (in the field):
-
Reachability tests: Using probes (like OONI), check if popular news, social, political, and minority sites are accessible without VPN.
-
Platform accessibility: Is traffic to major global platforms (e.g., Twitter/X, WhatsApp, YouTube) uninterrupted?
-
DNS manipulation: Detect if ISPs poison DNS lookups for “sensitive” domains.
-
Throttling detection: Measure if specific services (e.g. video streaming, VoIP) are degraded compared to general web traffic.
2. End-to-End Principle – ability of users to connect directly
a. Infrastructure indicators:
-
IPv6 deployment: % of users with native IPv6 addresses (data from Google IPv6 stats or APNIC).
-
Public addressing: % of users behind Carrier-Grade NAT vs. unique addresses.
-
Port availability: Are key ports (SSH, VoIP, gaming, P2P) open or blocked?
-
VPN/Tor reachability: Can users establish encrypted tunnels freely?
b. Policy/Regulation indicators:
-
Net neutrality: Are there enforceable protections against throttling/blocking?
-
Interconnection openness: Does the country have healthy Internet Exchange Points (IXPs) that support direct local traffic exchange?
c. Corporate practice indicators:
-
ISP transparency: Do ISPs disclose shaping/throttling policies?
-
Platform dependence: What % of user traffic flows through a handful of global platforms (measured at IXPs where possible)?
How it might look as a Dashboard (example values)
Country: Canada
-
Openness:
-
Censorship laws: Minimal, piracy-related only.
-
DNS blocking: Occasional, court-ordered.
-
OONI probes: No systemic censorship detected.
-
-
End-to-End:
-
IPv6 deployment: ~40–45% of users (as of 2025).
-
NAT: Carrier-grade NAT common in IPv4, less so in IPv6.
-
Net neutrality: Protected by law.
-
VPN/Tor: Unrestricted.
-
Country: China (for contrast)
-
Openness:
-
Censorship laws: Comprehensive, multi-level.
-
DNS blocking/poisoning: Widespread.
-
OONI probes: Systematic blocking of foreign platforms.
-
-
End-to-End:
-
IPv6 deployment: Rapidly growing, but tightly monitored.
-
NAT/firewalls: State-level deep packet inspection.
-
Net neutrality: Not enforced.
-
VPN/Tor: Banned/restricted.
-
The observatory could publish these as country profiles, refreshed quarterly, with both a quantitative score and qualitative analysis. Over time, trends would become visible: tightening, loosening, or hybrid models of control.
If you like, I could mock up a prototype scoring framework (say 0–100 for each parameter) to make these profiles easily comparable between countries. Would that be useful?
You said:
ChatGPT said:
Excellent — let’s imagine the Observatory putting out a Core Internet Values Index that turns all these messy signals into a 0–100 score. Think of it like a weather forecast for Internet health in each country:
Prototype Scoring Framework
1. Openness Score (0–100)
Measures how freely information flows in and out of a country.
Indicators (with suggested weights):
-
Legal/policy environment (25%)
-
100 = no censorship laws, transparent oversight.
-
0 = heavy content controls, vague laws, arbitrary takedowns.
-
-
Censorship in practice (25%)
-
OONI tests, DNS manipulation, reachability of major platforms.
-
-
Transparency & accountability (15%)
-
Clear legal processes, published blocklists vs. opaque orders.
-
-
Platform access (20%)
-
Are global tools (WhatsApp, Signal, YouTube, Wikipedia, etc.) reachable?
-
-
Selective throttling (15%)
-
None = 100, systematic throttling = 0.
-
2. End-to-End Score (0–100)
Measures how closely the network still follows the end-to-end principle.
Indicators (with suggested weights):
-
IPv6 deployment & addressability (20%)
-
% of users with unique IPv6 addresses.
-
-
NAT/Port openness (20%)
-
Can users host services or are they stuck behind carrier NAT/firewalls?
-
-
Net neutrality protections (20%)
-
Strong laws & enforcement = 100, absent/ignored = 0.
-
-
Freedom to use encryption/tunnels (20%)
-
VPN/Tor accessibility.
-
-
Local interconnection health (20%)
-
Vibrant IXPs, local peering = higher score; reliance on upstream foreign providers = lower.
-
Example Country Profiles (2025)
Canada
-
Openness:
-
Legal/policy: 90 (no systemic censorship, only targeted copyright orders).
-
Censorship practice: 95 (OONI detects little to no blocking).
-
Transparency: 80 (court-ordered blocks, but not always publicized).
-
Platform access: 95 (all major services reachable).
-
Throttling: 85 (net neutrality law prevents it, but occasional disputes).
-
Openness Score ≈ 89/100.
-
-
End-to-End:
-
IPv6 deployment: 70 (~40–45% of users).
-
NAT/port openness: 60 (IPv4 NAT still common).
-
Net neutrality: 95 (legal protections in place).
-
Encryption freedom: 100 (VPN/Tor unrestricted).
-
Interconnection: 80 (healthy IXPs, though heavily tied to US backbones).
-
End-to-End Score ≈ 81/100.
-
China (for contrast)
-
Openness:
-
Legal/policy: 10 (systemic censorship).
-
Censorship practice: 5 (OONI shows widespread DNS poisoning & blocks).
-
Transparency: 0 (opaque, arbitrary orders).
-
Platform access: 10 (foreign platforms blocked, domestic clones dominate).
-
Throttling: 20 (used to control flows).
-
Openness Score ≈ 9/100.
-
-
End-to-End:
-
IPv6 deployment: 70 (fast rollout, but under tight monitoring).
-
NAT/port openness: 20 (state firewall restricts peer-to-peer).
-
Net neutrality: 10 (no protections).
-
Encryption freedom: 5 (VPN/Tor blocked).
-
Interconnection: 40 (domestic IXPs strong, but international tightly filtered).
-
End-to-End Score ≈ 29/100.
-
This way, the Observatory could:
-
Publish a map showing country-by-country scores.
-
Track yearly changes (is a country opening or closing?).
-
Highlight red-flag events (e.g., sudden drop in openness score during protests).
Would you like me to draft a global baseline ranking (say top 5 and bottom 5 countries on each parameter, with indicative scores), so you’d have a sense of where Canada sits in the pack?
You said:
ChatGPT said:
Lovely. Let’s sketch a first “exploratory leaderboard,” not as gospel but as a working compass for the Observatory. Think of it as a pilot run with indicative scores, combining technical reports (OONI, APNIC, Google IPv6 stats), policy studies (Freedom on the Net, net neutrality laws), and industry practices.
🌍 Exploratory Global Baseline (2025)
Top 5 – Openness
-
Iceland – 95/100
-
Strong protections for expression, minimal blocking, very transparent regulation.
-
-
Estonia – 93/100
-
Digital-first state, robust free-speech protections, open cross-border flows.
-
-
Canada – 89/100
-
Strong net neutrality, no systemic censorship, some copyright blocks.
-
-
Netherlands – 88/100
-
Transparent governance, strong openness ethos, minor site-blocking.
-
-
Costa Rica – 87/100
-
Constitutionally protects free expression, no systemic filtering.
-
Bottom 5 – Openness
-
China – 9/100
-
Great Firewall, comprehensive censorship, foreign platforms blocked.
-
-
Iran – 12/100
-
National Information Network isolates citizens, heavy blocking of global services.
-
-
North Korea – 5/100
-
Internet only for elites, citizens restricted to a closed intranet.
-
-
Russia – 20/100
-
Sovereign Internet law, expanding censorship, platform bans.
-
-
Turkmenistan – 15/100
-
State-controlled single ISP, VPNs illegal, pervasive blocking.
-
Top 5 – End-to-End Principle
-
Germany – 85/100
-
High IPv6 penetration (~65%), strong net neutrality, open IXPs.
-
-
Japan – 83/100
-
Widespread IPv6, liberal P2P environment, freedom for VPNs.
-
-
Canada – 81/100
-
Moderate IPv6 deployment, net neutrality laws, open IXPs, VPNs unrestricted.
-
-
United States – 80/100
-
Advanced IPv6 deployment (~50%), open interconnection, but net neutrality protection fragile.
-
-
Sweden – 80/100
-
High IPv6 adoption, open IXPs, strong neutrality traditions.
-
Bottom 5 – End-to-End Principle
-
China – 29/100
-
IPv6 rollout strong, but Great Firewall blocks VPNs/Tor and restricts ports.
-
-
Iran – 30/100
-
Carrier NAT, VPN restrictions, throttling of services.
-
-
Egypt – 35/100
-
Pervasive filtering, blocked VPNs/Tor, limited IXPs.
-
-
Turkey – 38/100
-
Ongoing throttling/blocking of services, VPN restrictions.
-
-
Russia – 40/100
-
Mandated deep packet inspection at ISPs, selective blocking, VPN restrictions.
-
Takeaway
-
Canada is top-tier in both Openness (3rd place) and End-to-End (3rd place). Its main weaknesses are IPv6 rollout (not yet universal) and creeping regulatory interventions (e.g., cultural mandates).
-
The observatory could position Canada as a reference country for “how to do it right” — a counterbalance to authoritarian models and also a test bed for fine-grained measurements (because it’s not perfect, but it’s mostly healthy).
Alejandro Pisanty
--
You received this message because you are subscribed to the Google Groups "coreinternetvalues" group.
To unsubscribe from this group and stop receiving emails from it, send an email to coreinternetval...@googlegroups.com.
To view this discussion visit https://groups.google.com/d/msgid/coreinternetvalues/CAKsgsGwLCxWOXSFexDH0%2BXKT-rGHyQ7EZjoWkHXoXrZp-hRBhg%40mail.gmail.com.
--
Dr. Alejandro Pisanty
Facultad de Química UNAM
Av. Universidad 3000, 04510 Mexico DF Mexico
+525541444475
Blog: http://pisanty.blogspot.com
LinkedIn: http://www.linkedin.com/in/pisanty
Unete al grupo UNAM en LinkedIn, http://www.linkedin.com/e/gis/22285/4A106C0C8614
Twitter: http://twitter.com/apisanty
---->> Unete a ISOC Mexico, http://www.isoc.org
. . . . . . . . . . . . . . . .
Sivasubramanian Muthusamy
To view this discussion visit https://groups.google.com/d/msgid/coreinternetvalues/CAOxRbV_t%3DLE_vcdQvZAhizJf1G5xcjnk7-asM00m57X2gaXJdQ%40mail.gmail.com.