AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese

AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/amalia-technical-report-a-fully-open-source-large-language-model-for-european-portuguese

stale

Proof freshness: stale
Proof status: unverified
Display score: 7/10
Last proof check: 2026-03-30
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 20
Source count: 10
Coverage: 50%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

Agent Handoff

Canonical ID amalia-technical-report-a-fully-open-source-large-language-model-for-european-portuguese | Route /signal-canvas/amalia-technical-report-a-fully-open-source-large-language-model-for-european-portuguese

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/amalia-technical-report-a-fully-open-source-large-language-model-for-european-portuguese

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "amalia-technical-report-a-fully-open-source-large-language-model-for-european-portuguese",
    "query_text": "Summarize AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese",
  "normalized_query": "2603.26511",
  "route": "/signal-canvas/amalia-technical-report-a-fully-open-source-large-language-model-for-european-portuguese",
  "paper_ref": "amalia-technical-report-a-fully-open-source-large-language-model-for-european-portuguese",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 12

References: 20

Proof: Verification pending

Freshness state: computing

Source paper: AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese

PDF: https://arxiv.org/pdf/2603.26511v1

Source count: 10

Coverage: 50%

Last proof check: 2026-03-30T21:52:19.867Z

Signal Canvas receipt window

Watch and verify: AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese

/buildability/amalia-technical-report-a-fully-open-source-large-language-model-for-european-portuguese

Watchwatch

Subject: AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Preparing verified analysis

GitHub Code Pulse

No public code linked for this paper yet.

Claim map

Strong 12Mixed 0Weak 0

Evidencepartial
A Fully Open Source Large Language Model for European Portuguese
Implicationpartial
This is explicitly stated in the title and abstract.
Verificationpartial
partial
Evidencepartial
AMALIA, a fully open LLM that prioritizes pt-PT by using more high-quality pt-PT data during both the mid- and post-training stages.
Implicationpartial
This is directly stated in the abstract and elaborated in the introduction.
Verificationpartial
partial
Evidencepartial
To evaluate pt-PT more faithfully, we release a suite of pt-PT benchmarks that includes translated standard tasks and four new datasets targeting pt-PT generation, linguistic competence, and pt-PT/pt-BR bias.
Implicationpartial
This is clearly stated in the abstract and introduction.
Verificationpartial
partial
Evidencepartial
Experiments show that AMALIA matches strong baselines on translated benchmarks while substantially improving performance on pt-PT-specific evaluations
Implicationpartial
This is a key finding reported in the abstract and introduction.
Verificationpartial
partial
Evidencepartial
We leveraged Arquivo.pt, the Portuguese Web Archive,2 as a primary source for this data.
Implicationpartial
This is explicitly mentioned in the data collection section.
Verificationpartial
partial
Evidencepartial
The model was then pretrained on this data and post-trained on specific datasets for instruction following, conversational reasoning, and problem solving.
Implicationpartial
This is described as the process of creating AMALIA in the introduction.
Verificationpartial
partial
Evidencepartial
While this strategy led to overall performance improvements, it resulted in declines in mathematical reasoning and instruction following.
Implicationpartial
This describes a specific experimental strategy and its outcome, as detailed in the analysis excerpt.
Verificationpartial
partial
Evidencepartial
A Fully Open Source Large Language Model for European Portuguese
Implicationpartial
The title and abstract explicitly state this.
Verificationpartial
partial
Evidencepartial
AMALIA, a fully open LLM that prioritizes pt-PT by using more high-quality pt-PT data during both the mid- and post-training stages.
Implicationpartial
The abstract directly states this as a key aspect of AMALIA's development.
Verificationpartial
partial
Evidencepartial
To evaluate pt-PT more faithfully, we release a suite of pt-PT benchmarks that includes translated standard tasks and four new datasets targeting pt-PT generation, linguistic competence, and pt-PT/pt-BR bias.
Implicationpartial
The abstract clearly states the release of these benchmarks for evaluation.
Verificationpartial
partial
Evidencepartial
Experiments show that AMALIA matches strong baselines on translated benchmarks
Implicationpartial
The abstract directly states this comparative performance.
Verificationpartial
partial
Evidencepartial
while substantially improving performance on pt-PT-specific evaluations
Implicationpartial
The abstract directly states this improvement.
Verificationpartial
partial

Author intelligence and commercialization panels stay hidden until the proof receipt is verified, cites at least 3 references, includes at least 2 sources, and clears 50% coverage. The paper narrative and citation surfaces remain public while verification is pending.

AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface