Exam prompt
How do mass number and proton number change in alpha decay?
How certain was your answer?
CorrectUnsureWrong
Quanta Verified · one source per AI card
Trace AI flashcards
back to their source
In Source-First mode, cards carry source evidence and pass quote matching. If no suitable source is found, no flashcards are created; citations do not prove external factual accuracy.
Start learning now
Free Starter account · no payment details
Physics · Radioactivity
Flashcard
Evidence linked directly to the card
1 / 4 · Switch subject
„Ich hab schon einige Karteikarten-Apps ausprobiert und Quanta hat mir bis jetzt am besten gefallen. […] Auch die Multiple Choice - Funktion und Prüfungssimulation helfen mir echt weiter."- TU Dresden
- Humboldt-Universität zu Berlin
- HTW Dresden
- Fachhochschule Dresden
- Universität Leipzig
- HTWK Leipzig
- Freie Universität Berlin
- IU Internationale Hochschule
- FernUniversität in Hagen
What is a flashcard app with sources?
It is a flashcard app that attaches a verifiable source to each card. Quanta does this per AI card (Quanta Verified) and quote-matches every card against your source, dropping any it cannot ground. As of June 2026, the other apps that cite sources, Memo and NotebookLM, do so only over a closed corpus you upload, not over open-topic generation.
Why per-card citation, and what the others got right
“Anki made spaced repetition accessible to millions, and that was a real achievement. Quizlet's shared library is enormous, RemNote folds notes and review into one place, and Knowt's free generation is genuinely good. I do not want to talk any of that down. The thing none of them does is tell you where an AI card came from. When I generated cards from a textbook, I had no way to know if a fact was in the book or invented. So I built the opposite default: each card records its source, and a quote-match step drops anything it cannot find in your document. Memo and NotebookLM cite sources, but only over a corpus you upload, never open-topic generation. Per-card citation on open-topic generation is an architecture decision, and it shapes how the generator is allowed to run.”
about 80%
of the vocabulary pairs recalled after one week with repeated retrieval
versus 36% and 33% without further retrieval (Karpicke & Roediger 2008, Science 319:966–968)
0.3460
log-loss of FSRS-6, lower is better
srs-benchmark (formerly fsrs-benchmark), open-spaced-repetition, retrieved 5 September 2026. That table carries no row for SM-2.
1
Source cited per AI card
Quanta Verified, on every generated card
€0
Starter plan, free forever
Per-card citation included
What to look for in a flashcard app with sources
These criteria separate a cited, verified flashcard app from a generator that simply guesses. Each includes an honest mini-verdict.
Every AI card cites its source
When Quanta generates a card from your PDF, photo or topic, it records the source it used and shows it on the card (Quanta Verified): source title, type and a confidence score. Anki has no built-in generator, and Quizlet, RemNote, Knowt and Brainscape generate cards without attaching a verifiable per-card source (as of June 2026).
Verdict: if you need to trace where a fact came from, Quanta is the direct choice. If you write every card by hand, the citation layer matters less.
Hallucinated cards are dropped, not guessed
On document upload the AI may only use content found in that document, and each candidate card is quote-matched against the source text. Cards that cannot be matched are dropped before you see them. This does not make AI infallible, but it turns silent hallucination into a visible, removable event.
Verdict: for high-stakes material where a wrong card is costly, the grounding step is the point. For casual review it is a safety net you may rarely notice.
FSRS-6 is active from the first card
FSRS-6 schedules each card from three parameters: stability, difficulty and retrievability. SM-2, the default in many older systems, dates to 1987 and uses a single ease factor. In the open comparison run by the open-spaced-repetition community, FSRS-6 reaches a log-loss of 0.3460 on 349,923,850 reviews from 9,999 collections (retrieved on 5 September 2026); log-loss measures prediction error, lower is better, and that table carries no row for SM-2. The peer-reviewed paper behind it, Ye et al. 2022, reports 220 million behaviour logs and a 12.6% improvement over the state of the art. Both are results of those datasets, not a blanket product effect. FSRS has been integrated in Anki since v23.10, but it is opt-in; Quanta enables FSRS-6 by default from the first card.
Verdict: if you want a modern scheduler with no setup, Quanta gives it to you natively. If you already run Anki with FSRS enabled, you share the same algorithmic core.
Built for STEM, not retrofitted
LaTeX renders natively with a live preview on web, iOS and Android, and chemistry SMILES strings render as 2D structures. The AI generator reads textbook PDFs and understands technical terminology across mathematics, physics, chemistry, biology and computer science. There is no plugin to install for math rendering.
Verdict: for technical subjects with formulas and structures, Quanta is purpose-built. For plain vocabulary or language learning, a lighter app may be enough.
Readiness Score for a real exam date
Most apps show which cards are due. Quanta adds a Readiness Score that estimates how prepared you are for a set exam date from your FSRS retention data, plus an exam simulation that asks follow-up questions instead of a flat self-grade. It is an estimate, not a guarantee of passing.
Verdict: if you study toward a fixed exam date, the Readiness Score gives orientation that pure due-card counters do not.
Quanta vs Anki, Quizlet, RemNote, Knowt and Brainscape
A factual table, feature by feature. The “others” column summarizes the named apps as of June 2026.
| Criterion | Quanta | Anki / Quizlet / RemNote / Knowt / Brainscape |
|---|---|---|
| Per-card source citation (Quanta Verified) | Yes | No |
| Anti-hallucination grounding (quote-match) | Yes | No |
| Built-in AI card generation | Yes | Quizlet, RemNote, Knowt: Yes; Anki, Brainscape: No |
| Default algorithm | FSRS-6 (2022) | SM-2 (1987) or proprietary |
| FSRS native from the first card | Yes | Anki: opt-in (v23.10); others: No |
| Log-loss in the open comparison | 0.3460 | SM-2: no row in that table |
| LaTeX with live preview | Native | Anki: MathJax; varies |
| Chemistry SMILES structures | Yes | No |
| Exam simulation | Yes | No |
| Readiness Score | Yes | No |
| Anki .apkg import | Yes | Anki, RemNote: Yes; varies |
| Starter plan price | €0 forever | Free tiers vary |
Log-loss data: srs-benchmark (formerly fsrs-benchmark), open-spaced-repetition, retrieved 5 September 2026 · Ye et al. 2022, ACM SIGKDD, doi:10.1145/3534678.3539081. Feature and price status June 2026. See the pricing comparison
Strengths and weaknesses, honestly
No app is the best choice for everything. Here are the strengths and weaknesses of both sides, including Quanta’s own.
Quanta
Strengths
- Per-card source citation on every AI card (Quanta Verified): source title, type and confidence
- Quote-match grounding drops cards it cannot match to your source
- FSRS-6 native from the first card, no plugin or configuration
- LaTeX and SMILES native, plus exam simulation and a Readiness Score
- Starter plan free forever, including per-card citation
Weaknesses
- No plugin ecosystem, so the feature set is limited to what is built in
- Full offline mode is only partial (PWA cache); Anki is more mature offline
- Not open source, unlike Anki
- Younger than Anki and Quizlet, so a smaller library of shared community decks
Anki, Quizlet, RemNote, Knowt, Brainscape
Strengths
- Anki: open source, fully offline, a very large plugin ecosystem
- Quizlet: huge shared library and a familiar, fast study mode
- RemNote: note-taking and spaced repetition combined in one workspace
- Knowt: free AI generation with a clean, modern interface
- Brainscape: confidence-based repetition with curated certified decks
Weaknesses
- None attaches a verifiable per-card source citation to AI cards (as of June 2026)
- None publishes a documented anti-hallucination grounding step for generation
- Anki has no built-in AI generator; FSRS is integrated since v23.10 but opt-in
- Memo and NotebookLM cite sources but only over a closed corpus you upload
The science: active recall and FSRS-6
Karpicke and Roediger (2008) report about 80% of the vocabulary pairs recalled after one week in the two conditions with repeated retrieval practice, and 36% and 33% in the two conditions where pairs were dropped from further testing once recalled; those figures describe that experiment and are not a general promise for every learning situation or for Quanta. In the open comparison run by the open-spaced-repetition community, FSRS-6 reaches a log-loss of 0.3460 on 349,923,850 reviews from 9,999 collections (retrieved on 5 September 2026); log-loss measures prediction error, lower is better, and that table carries no row for SM-2. The peer-reviewed paper behind it, Ye et al. 2022, reports 220 million behaviour logs and a 12.6% improvement over the state of the art. Both are results of those datasets, not a blanket product effect. These studies test the method and the algorithm, not Quanta itself.
Sources: srs-benchmark (formerly fsrs-benchmark), open-spaced-repetition, retrieved 5 September 2026 · Ye et al. 2022, ACM SIGKDD, doi:10.1145/3534678.3539081 · Karpicke & Roediger 2008, Science, doi:10.1126/science.1152408
Frequently asked questions
What is a flashcard app with sources?
A flashcard app with sources attaches a verifiable origin to each card so you can trace where a fact came from. Quanta does this per card: when AI generates a card from your PDF, photo or topic, it records the source it used (title, type, confidence) and shows it on the card. This is called Quanta Verified, and it is designed to catch AI hallucinations before a card reaches your deck. As of June 2026, the other apps that attach sources are Memo and NotebookLM, and both work over a closed corpus you upload rather than open-topic generation.
How does Quanta stop flashcard hallucinations?
Quanta uses a quote-match grounding step. When you generate cards from an uploaded document, the AI may only use content found in that document, and each candidate card is checked against the source text. Cards that cannot be matched to the source are dropped before you see them rather than shown with a guess. Every surviving card carries its source (Quanta Verified). This does not make AI infallible, but it converts silent hallucination into a visible, removable event. The constraint is strongest on document upload and lighter on open-topic generation, which Quanta labels accordingly.
Do Anki, Quizlet, RemNote, Knowt or Brainscape cite sources per card?
As of June 2026, no. Anki has no built-in AI generator and therefore no source layer. Quizlet, RemNote, Knowt and Brainscape offer AI card generation, but none attaches a verifiable per-card source citation to the generated cards, and none publishes a documented anti-hallucination grounding step. Memo and NotebookLM cite sources, but only from a closed corpus you upload, not from open-topic generation. As of June 2026, Quanta is the one in this set that attaches a per-card source to open-topic generation.
What are cited flashcards good for?
Cited flashcards let you verify a fact instead of trusting it. For exam preparation in medicine, law or any STEM field, a single wrong card studied for weeks is expensive, because spaced repetition will reinforce the error. With a source on each card you can open the citation, confirm the claim against the original document, and correct or delete the card. Citations also help when you revisit a topic months later and need to remember why a card says what it says.
Is the science behind active recall real?
Yes. Karpicke and Roediger (2008) report about 80% of the vocabulary pairs recalled after one week in the two conditions with repeated retrieval practice, and 36% and 33% in the two conditions where pairs were dropped from further testing once recalled; those figures describe that experiment and are not a general promise for every learning situation or for Quanta. Quanta is built around active recall plus FSRS-6 scheduling. In the open comparison run by the open-spaced-repetition community, FSRS-6 reaches a log-loss of 0.3460 on 349,923,850 reviews from 9,999 collections (retrieved on 5 September 2026); log-loss measures prediction error, lower is better, and that table carries no row for SM-2. The peer-reviewed paper behind it, Ye et al. 2022, reports 220 million behaviour logs and a 12.6% improvement over the state of the art. Both are results of those datasets, not a blanket product effect. These studies test the method and the algorithm, not Quanta itself.
Is Quanta free, and what does the paid plan cost?
Quanta Starter: Free forever: 1 topic, no more than 100 cards in total, FSRS, and exactly one AI generation run over the account lifetime. The regular generator offers 40–100 cards from text, a link, or up to 10 files; the guided onboarding entry offers 10–50 from text or files. The onboarding run counts as that one lifetime run; Starter has no monthly AI quota. Further AI flashcard generations require Essential, which starts at €9.75 per month on the annual plan (300 AI cards per month, unlimited cards). Source-backed cards expose their available source details. No credit card is required to start. Prices as of August 2026; see the pricing comparison for the current breakdown.
Does Quanta support LaTeX and STEM subjects?
Yes. Quanta renders LaTeX natively with a live preview on web, iOS and Android, so inline $E=mc^2$ and block math display visually as you type. It is built for STEM: mathematics, physics, chemistry, biology and computer science. Chemistry SMILES strings render as 2D structures, and the AI generator understands technical terminology when reading textbook PDFs. There is no plugin to install for math rendering.
Can I import my existing Anki or Quizlet decks?
Yes. Export your Anki deck as an .apkg file and upload it to Quanta, and all cards are imported. CSV exports from Quizlet are imported as well, and you can add source documents for AI extraction. FSRS-6 starts with default parameters and recalibrates to your rhythm over the first study sessions. Your previous Anki FSRS history is not carried over, but the card content is preserved in full.
Final verdict
As of June 2026, choose Anki if you need open source, full offline mode and a large plugin ecosystem, which remain its strengths. Choose Quizlet, Knowt or RemNote for a big shared library or combined note-taking. Choose Quanta if you want a flashcard app where every AI card cites its source, a quote-match step that drops hallucinated cards, FSRS-6 with no setup, native LaTeX and a Readiness Score for a real exam date, especially in STEM. The per-card citation slot for open generation is the gap Quanta fills.
Keep exploring
The numbers and the mechanics
What retrieval practice was measured to do
Karpicke and Roediger (2008) report about 80% of the vocabulary pairs recalled after one week in the two conditions with repeated retrieval practice, and 36% and 33% in the two conditions where pairs were dropped from further testing once recalled; those figures describe that experiment and are not a general promise for every learning situation or for Quanta. Karpicke, J.D. and Roediger, H.L. (2008). Science, 319(5865), 966 to 968. doi:10.1126/science.1152408
What the open scheduler comparison covers
In the open comparison run by the open-spaced-repetition community, FSRS-6 reaches a log-loss of 0.3460 on 349,923,850 reviews from 9,999 collections (retrieved on 5 September 2026); log-loss measures prediction error, lower is better, and that table carries no row for SM-2. The peer-reviewed paper behind it, Ye et al. 2022, reports 220 million behaviour logs and a 12.6% improvement over the state of the art. Both are results of those datasets, not a blanket product effect. It compares schedulers, not the Quanta app with current Anki. srs-benchmark (formerly fsrs-benchmark), open-spaced-repetition, retrieved 5 September 2026, https://github.com/open-spaced-repetition/srs-benchmark · Ye, J. et al. (2022). ACM SIGKDD. doi:10.1145/3534678.3539081
What a cited card stores, and what comes in
A matched card keeps its source title, type and confidence score and shows them on the card detail. Uploads read textbook PDFs up to 10 MB; imports accept Anki .apkg and CSV files.
Where your data sits
Accounts, learning content and results are stored in Frankfurt, region europe-west3. AI text functions run through the EU endpoint of Mistral AI SAS in Paris; reading files and voice input runs through the provider standard endpoint, for which no processing location is promised. A data processing agreement with standard contractual clauses applies.
Feature and pricing claims reflect the named apps as of June 2026 and may change. The per-card citation and quote-match grounding described here are Quanta features; the cited studies test the underlying method and algorithm, not Quanta.