---
id: "20260814-0231-hop-solomonoff-violates-nicods-criterion"
title: "Solomonoff induction, the formal basis of universal AI, violates Jean Nicod's 1930 criterion for how evidence should confirm a hypothesis"
type: "capture"
status: "promoted"
origin: "hop-batch"
writer_model: "claude-sonnet-5"
date_created: "2026-08-14T00:00:00.000Z"
promoted_to: ["30-notes/claim-nicods-1930-criterion-confirming-instances-increase-belief.md","30-notes/claim-leike-hutter-2015-solomonoff-induction-violates-nicods-criterion.md","40-entities/entity-jean-nicod.md","40-entities/entity-marcus-hutter.md"]
not_promoted: ["Institut Jean-Nicod named in Nicod's memory (Wikipedia, Tier 4) — a trivial naming fact, not an atomic claim worth its own note; folded into entity-jean-nicod.md's body instead.","Jean Nicod's biography (died age 30, tuberculosis, 1924; also authored Nicod's axiom) — Tier 4 biographical detail; folded into entity-jean-nicod.md rather than a standalone claim-note.","Hop 5's Marcus Hutter/AIXI biographical confirmation (ANU, IDSIA, DeepMind affiliations) — the capture itself reports 'no new surprising hook surfaced, and the search results themselves were thin/aggregator-quality'; too thin for a claim-note, folded into entity-marcus-hutter.md instead.","Jan Leike (entity candidate) — real, but the capture establishes only one fact about him (co-author of this single 2015 paper); does not clear the person-hub test's 'can you say why in one sentence, beyond authorship' bar the way Nicod and Hutter do. UNSURE, not promoted — left as plain text in both claim-notes rather than a hub or a stub (the entity-page spec gives persons no 'watching' tier).","Saved hooks not followed this chain (I.J. Good's raven-paradox rebuttal, Hempel's 1945 'Studies in the logic of confirmation') — future leads named in the capture body, not claims to promote now.","Icard's 2023 Intellectica taxonomy, flagged in this capture as 'still unread at its own primary' — stale as of promotion: the vault's own record (entity-benjamin-icard.md, question-verify-icard-2023-taxonomy-primary.md) shows this was independently read and closed on 2026-08-09, five days before this capture. No action needed; noted as a capture-freshness gap in the journal, not a claim.","'post-worthy: yes' flag — a drafting note for a future session, not a claim; left as-is in the capture, no draft opened during promotion."]
hop_chain: ["seed: claim-reliability-aware-rag-estimates-source-reliability-separately-from-relevance <-> claim-source-reliability-and-credibility-are-not-judged-independently (cosine 0.89, bipartite ml-ai/epistemology pair)","seed pair -> confirmed already bridged in the vault via observation-halo-effect-names-the-2025-reliability-credibility-leak and the 2026-08-07 Icard hop chain; real convergence, not a false friend, nothing new to add — left the topic per protocol","claim-icard-2024-dynamic-logic-makes-credibility-primary-reliability-secondary (Icard's affiliation) -> Institut Jean-Nicod, flagged 2026-08-07 as an unpursued lead (max_cosine 0.664, orphan P4.8)","Institut Jean-Nicod -> Jean Nicod, the philosopher the institute is named for (max_cosine 0.693, frontier P12.5)","Nicod's 1930 confirmation criterion -> Leike & Hutter (2015) 'Solomonoff Induction Violates Nicod's Criterion?' (max_cosine 0.702, frontier P14.9)","Leike & Hutter's paper -> Marcus Hutter / AIXI and universal artificial intelligence (max_cosine 0.698, frontier P13.7; zoom-out, natural stop)"]
novelty_max_cosine: 0.702
tags: ["confirmation-theory","philosophy-of-science","algorithmic-information-theory","solomonoff-induction","cross-domain-bridge","cross-time-bridge","bayesian-reasoning","epistemics"]
source_url: "https://arxiv.org/pdf/1507.04121"
source_title: "Solomonoff Induction Violates Nicod's Criterion?"
source_author: "Jan Leike, Marcus Hutter"
source_date: 2015
source_tier: 1
source_sha: "99a1134db1eb4cdb4bab72b12ac03de64ad4c79b170b8c944920a528af7a2353"
source_quote: "We show that Solomonoff induction does not satisfy Nicod's criterion: there are time steps in which observing black ravens decreases the belief in H."
seek_code_commit: "17d9798"
---


Jean Nicod (1893–1924), a French philosopher and logician who "died at the age of 30 from tuberculosis" (Wikipedia, Tier 4), proposed in his 1930 *Foundations of Geometry and Induction* what is now called Nicod's criterion: as Leike & Hutter gloss it, "observing an F that is a G increases our belief in the hypothesis that all F s are Gs" (Tier 1). It underlies Hempel's raven paradox and a century of confirmation-theory debate. Institut Jean-Nicod (CNRS, Paris) — a footnote in an earlier vault hop into Benjamin Icard's intelligence-tradecraft logic — is "named in honour of Nicod's memory" (Wikipedia, Tier 4).

Jan Leike and Marcus Hutter (ANU), working on Solomonoff induction — the incomputable ideal underlying Hutter's AIXI model of universal AI — proved in 2015 that it fails Nicod's criterion: "We show that Solomonoff induction does not satisfy Nicod's criterion: there are time steps in which observing black ravens decreases the belief in H" (Tier 1, arXiv:1507.04121). Under the unnormalized Solomonoff prior this happens infinitely often for some computable sequences; normalizing the prior limits it to finitely many violations. Their diagnosis runs against intuition: reject the criterion, not the induction method.

## Why this was hop-worthy
A footnote about a CNRS lab's namesake turned out to be a 1930 philosophy-of-science idea whose falsification, 85 years later, is a load-bearing result for the math underneath universal AI.

> [!note] Seek's commentary:
> The chain almost didn't happen — Institut Jean-Nicod sat as an unfollowed lead across two prior sessions because "linguistic vagueness" sounded like a dead end. It was the wrong guess about what the institute's name would lead to that made it worth checking.
> — Seek

## Further leads
- Leike & Hutter's paper revisits Hempel's raven paradox and I.J. Good's "white shoe is a red herring" rebuttal — untouched this chain.
- Icard's 2023 Intellectica taxonomy is still unread at its own primary (carried over from 2026-08-07).
- Marcus Hutter's broader "universal artificial intelligence" program — touched only biographically here.

## Entity candidates
- Jean Nicod — person — French philosopher/logician (1893–1924); coined Nicod's criterion and Nicod's axiom; unknown to the vault before this capture; the older figure this chain compares against, reached only via his institute's name.
- Marcus Hutter — person — ANU computer scientist; co-author of this paper; creator of the AIXI model of universal artificial intelligence; unknown to vault before this capture.
- Jan Leike — person — co-author of this 2015 paper on Solomonoff induction and confirmation theory; unknown to vault before this capture.

## Hop chain

Hop 1: [[observation-halo-effect-names-the-2025-reliability-credibility-leak]] and [[claim-kelly-et-al-propose-richer-joint-matrix-not-axis-collapse]] (internal, no external URL)
- Hook type: cross-domain bridge (re-checking the seed's own claim)
- Hook: the seed asked whether the RA-RAG/Kelly-et-al resemblance is a real mechanism or a false friend.
- Why followed: required before leaving the topic, per the seed's explicit instruction.
- Key findings: the vault already built and audited this exact bridge across three prior sessions (2026-07-11, 2026-07-20/21, 2026-08-07) — Admiralty Code, RA-RAG, Kelly et al., and Thorndike's 1920 halo effect all converge on the same two-axis-that-leaks pattern, confirmed real by repeated cross-model audit. Nothing new to add; moved on immediately rather than re-mine saturated ground.

Hop 2: 10-inbox/raw/2026-08-07-hop-icard-dynamic-logic-abandons-independence.md, "Saved hooks not followed" (internal)
- Hook type: unfamiliar name
- Hook: Institut Jean-Nicod, Benjamin Icard's affiliation, flagged as an unpursued lead on 2026-08-07 ("linguistic vagueness... untouched by the vault").
- Why followed: an explicitly saved hook nobody had chased in two subsequent sessions; vault_novelty put the org at P4.8 (orphan) with no strong bridge pair, but the hook type (unfamiliar org name in a credible chain) justified a look rather than a full wander.
- Key findings: not a vagueness-theory rabbit hole after all — the institute is named for a specific, mostly-forgotten philosopher.

Hop 3: Jean Nicod — https://en.wikipedia.org/wiki/Jean_Nicod
- Hook type: the person behind the thing
- Hook: "Institut Jean-Nicod... named in honour of Nicod's memory."
- Why followed: standard move from an institution's name to the person it commemorates; vault_novelty frontier (P12.5), close to existing notes on underdetermination and Helmholtz's unconscious inference.
- Key findings: Nicod died at 30 (tuberculosis, 1924), having formulated Nicod's criterion — a foundational rule in confirmation theory, cited via Hempel's raven paradox.
- Surprise: expected a footnote about vagueness theory in philosophy of language — found a different, unrelated contribution (a confirmation-theory axiom with its own century-long life in AI theory).

Hop 4: Leike & Hutter (2015), "Solomonoff Induction Violates Nicod's Criterion?" — https://arxiv.org/pdf/1507.04121
- Hook type: cross-domain bridge (cross-time-period, extra weight per spec)
- Hook: a 2015 cs.LG arXiv paper directly interrogates Nicod's 1930 criterion using algorithmic information theory.
- Why followed: highest-priority hook type; also lands on AI, per Cali's home-planet ruling. vault_novelty frontier (P14.9), unknown entities (Solomonoff induction, Hutter both absent from vault).
- Key findings: Solomonoff induction — the incomputable ideal behind Hutter's AIXI universal-AI model — provably violates Nicod's criterion at specific time steps (infinitely often under the unnormalized prior, finitely often normalized); the authors conclude the criterion, not the induction method, should be rejected.
- Surprise: expected a math paper "using" a 1930 philosophy idea as a clean building block — found instead a formal proof that the idea is false for the very system built to formalize induction, with the authors explicitly siding against the 85-year-old criterion.

Hop 5: Marcus Hutter / AIXI (WebSearch, no single archived primary — biographical confirmation only)
- Hook type: the person behind the thing (zoom-out)
- Hook: Hutter's co-authorship connects this raven-paradox result to his separate, larger universal-AI research program (AIXI, ANU, prior DeepMind/IDSIA affiliations).
- Why followed: alternation — Hop 4 zoomed into a specific technical proof; this zooms back out to the person and program it sits inside.
- Key findings: mostly confirmed existing public biography (ANU, IDSIA, AIXI); no new surprising hook surfaced, and the search results themselves were thin/aggregator-quality — natural stopping point.

Saved hooks not followed:
- I.J. Good's "white shoe is a red herring" rebuttal of the standard Bayesian solution to the raven paradox — from Leike & Hutter's reference list — interesting philosophy-of-science thread, not pursued.
- Hempel's original 1945 "Studies in the logic of confirmation" — the raven paradox's own origin point, one hop further back than Nicod — saved for a future chain.
- Icard's 2023 Intellectica taxonomy, still unread at its own primary — carried over unresolved from the 2026-08-07 chain.

post-worthy: yes — Tier-1 primary, genuine cross-domain and cross-time bridge landing on AI theory, closes a lead two prior sessions flagged and left untouched.