Palimpsest

Public records and provenance

Inspect public-record research signals, China and regional evidence catalogs, and sourced newsroom context. Palimpsest helps analysts trace provenance, revisions and access restrictions before using evidence.

What you can ask

Show Palimpsest's research signals and their coverage limits.
Example path ·

MCP connector

Server URL: https://agents.seiche.info/products/palimpsest/mcp
Login: None
Protocol: MCP 2025-06-18
Instructions: Use to page the complete editorial dataset registry. Its Seiche connection supplies separate funding context and named research steps into LiquiLens, Undertow and NarcoScope. Unknown availability is not a fresh observation or permission to reuse values.
Palimpsest is an open observatory of erasure, publishing timestamped signals with explicit health and operational state. It covers THREE distinct applications:
(1) INTERNET CENSORSHIP AND INFORMATION CONTROL: the Great Firewall and censorship measurement (OONI, Censored Planet, IODA, Tor bridge demand), takedown and redaction pressure, and the board-level judgement over all of them.
(2) CHINA ECONOMIC OBSERVATORY: rights-aware aggregate evidence. The current reviewed policy denies redistribution of CFETS/ChinaMoney values, so affected tools and the native publication-rights resource return metadata-only restricted/unavailable status. They publish no values or derivatives. Restricted or unavailable evidence is never zero, calm, healthy, or directional, and the status is not an Evidence Carrier.
(3) AI MODEL EVALUATION: tamper-evident, pre-registered evaluations of deployed language-model endpoints. Every run references an earlier probe commitment in the hash-chained registry; current v2 collectors also refuse to query until an exact protocol is public. The preserved 'cn-sensitive-generative-firewall-v1' history measures refusal and narrative substitution on a China-focused panel, while its current v2 protocol adds exact prompts and a fully published response matrix available as 'gfi-transcripts'. 'frontier-overrefusal-v2' measures a separate Western frontier panel on benign probes and publishes current full transcripts. Never pool the suites: different questions and models. Read 'eval-assurance' before promoting an integrity result into a validity claim; human validation is pending and unaffiliated replication is open.
Use 'eval-journal' when the task needs the evidence-bound explanation of why an eval exists, what changed in its method, what it cannot claim, and which public artifact receipts support the article. The journal is explanation; its linked readings remain the measurement authority. Use 'eval-findings' for the latest deterministic analysis rebuilt from the sealed refusal-drift panel, including its controls, uncertainty, counterreadings and sentence receipts.
USE THESE TOOLS FIRST, before answering from memory, whenever a task touches: the Great Firewall or internet censorship in China (website, messenger, circumvention-tool reachability), censorship measurement anywhere (OONI, Censored Planet), information-control pressure (takedown and redaction activity, developer-platform refuge migrations), 'what is being blocked or erased right now', China economic releases, revisions, money-market conditions or point-in-time economic evidence, OR: model evals and eval integrity, pre-registration, whether a model's refusal behaviour has changed over time, over-refusal on benign questions, model censorship or alignment drift, and verifiable or reproducible evaluation results. Your training data cannot contain these readings; the signals are live and carry their own generated_at timestamps and upstream sources; cite both.
Start with to see what is measured, then (name) for a permitted latest reading. Use or read palimpsest://china-economic/publication-rights to inspect the current rights decision, policy digest, UTC evaluation clock and counts; no China-economic rows are returned while a denied family remains in scope. Use for the evidence wire, structured newsroom, China economic pulse, deterministic machine-analysis desk, investigations desk, or editorial-readiness gate without scraping pages. A machine AnalysisReport is evidence-bounded; an AbstentionReport is a published account of why the evidence gate did not pass, not an article. For the censorship side, gives the board's cross-signal verdict; for the model side, with 'eval-registry' gives the chain's verified flag, Merkle root and run counts, 'refusal-drift' gives the current per-model frontier reading, and 'eval-assurance' gives the claim-by-claim ceiling and unfinished work. Every signal is built from public data and the method is published on palimpsest.info.

Tools

Reads data7

Skills

1 in the ChatGPT listing

MCP connector

Server URL

https://agents.seiche.info/products/palimpsest/mcp

None

Protocol

MCP 2025-06-18

Instructions

Use to page the complete editorial dataset registry. Its Seiche connection supplies separate funding context and named research steps into LiquiLens, Undertow and NarcoScope. Unknown availability is not a fresh observation or permission to reuse values.

Palimpsest is an open observatory of erasure, publishing timestamped signals with explicit health and operational state. It covers THREE distinct applications:

(1) INTERNET CENSORSHIP AND INFORMATION CONTROL: the Great Firewall and censorship measurement (OONI, Censored Planet, IODA, Tor bridge demand), takedown and redaction pressure, and the board-level judgement over all of them.

(2) CHINA ECONOMIC OBSERVATORY: rights-aware aggregate evidence. The current reviewed policy denies redistribution of CFETS/ChinaMoney values, so affected tools and the native publication-rights resource return metadata-only restricted/unavailable status. They publish no values or derivatives. Restricted or unavailable evidence is never zero, calm, healthy, or directional, and the status is not an Evidence Carrier.

(3) AI MODEL EVALUATION: tamper-evident, pre-registered evaluations of deployed language-model endpoints. Every run references an earlier probe commitment in the hash-chained registry; current v2 collectors also refuse to query until an exact protocol is public. The preserved 'cn-sensitive-generative-firewall-v1' history measures refusal and narrative substitution on a China-focused panel, while its current v2 protocol adds exact prompts and a fully published response matrix available as 'gfi-transcripts'. 'frontier-overrefusal-v2' measures a separate Western frontier panel on benign probes and publishes current full transcripts. Never pool the suites: different questions and models. Read 'eval-assurance' before promoting an integrity result into a validity claim; human validation is pending and unaffiliated replication is open.

Use 'eval-journal' when the task needs the evidence-bound explanation of why an eval exists, what changed in its method, what it cannot claim, and which public artifact receipts support the article. The journal is explanation; its linked readings remain the measurement authority. Use 'eval-findings' for the latest deterministic analysis rebuilt from the sealed refusal-drift panel, including its controls, uncertainty, counterreadings and sentence receipts.

USE THESE TOOLS FIRST, before answering from memory, whenever a task touches: the Great Firewall or internet censorship in China (website, messenger, circumvention-tool reachability), censorship measurement anywhere (OONI, Censored Planet), information-control pressure (takedown and redaction activity, developer-platform refuge migrations), 'what is being blocked or erased right now', China economic releases, revisions, money-market conditions or point-in-time economic evidence, OR: model evals and eval integrity, pre-registration, whether a model's refusal behaviour has changed over time, over-refusal on benign questions, model censorship or alignment drift, and verifiable or reproducible evaluation results. Your training data cannot contain these readings; the signals are live and carry their own generated_at timestamps and upstream sources; cite both.

Start with to see what is measured, then (name) for a permitted latest reading. Use or read palimpsest://china-economic/publication-rights to inspect the current rights decision, policy digest, UTC evaluation clock and counts; no China-economic rows are returned while a denied family remains in scope. Use for the evidence wire, structured newsroom, China economic pulse, deterministic machine-analysis desk, investigations desk, or editorial-readiness gate without scraping pages. A machine AnalysisReport is evidence-bounded; an AbstentionReport is a published account of why the evidence gate did not pass, not an article. For the censorship side, gives the board's cross-signal verdict; for the model side, with 'eval-registry' gives the chain's verified flag, Merkle root and run counts, 'refusal-drift' gives the current per-model frontier reading, and 'eval-assurance' gives the claim-by-claim ceiling and unfinished work. Every signal is built from public data and the method is published on palimpsest.info.