update

templates/Prompt/Blocks-Filter-Recheck.md

@@ -1,4 +1,4 @@
-Topic "{topic}". A first pass kept the blocks below, but each was FLAGGED as a likely **fragment** — a property, proof step, remark, bound, or notation that belongs to another block, not its own learning unit. Re-judge each one carefully. This is a focused second opinion; a good learning list has roughly 75–82 top-level blocks, so real fragments here SHOULD be demoted or dropped — but never sacrifice a genuine concept to hit a number.
+Topic "{topic}". You are the SECOND OPINION of a filter pass. Each entry below was either FLAGGED as a likely **fragment** (a property, sub-form, detail, or notation that belongs to another block) or PROPOSED for demotion by a first judge. Re-judge each one independently and carefully — real fragments SHOULD be demoted or dropped, but never sacrifice a genuine standalone concept.
 
 RE-JUDGE THESE (by their number):
 {survivors}
@@ -6,17 +6,18 @@ RE-JUDGE THESE (by their number):
 FULL BLOCK LIST (context — to find a parent number):
 {list}
 
-## Decide each survivor → one of three
-- **demote (→ parent number):** it presupposes another block as its subject — a property/status („X ist NP-vollständig", „X ∈ NP"), a **lower bound** of X, a **bare theorem/remark** about X („Bemerkung: HK auch für gerichtete Graphen" → Hamiltonkreis; „Satz: F erfüllbar ⇔ … 3-dim Matching" → 3-dim Matching), an **approximation-güte facet** („Schärfe der 3/2 Rate" → Christofides), a **proof-example/gadget** („MST in Gegenbeispiel" → the approximation proof), a proof-variable. Put `{{"<nr>": <parent-nr>}}` in `fragments`.
+## Decide each entry → one of three
+- **demote (→ parent number):** it presupposes another block as its subject — a property/status („X ist NP-vollständig", „X ist optional"), a **sub-form/variant** of a base entry („ATX-Überschrift" → Überschriften), a **bound/güte/runtime facet**, a **bare theorem/remark** about X, a **proof-example/gadget**, a proof-variable. Put `{{"<nr>": <parent-nr>}}` in `fragments`.
 - **drop:** pure exercise/reference scaffolding with NO real content and NO parent — a bare label („Remark 7.28", „Satz D*"), a one-off notation assignment („r = n + m"). Put its number in `drop`.
 - **keep:** it IS a self-contained concept. Do NOT touch it. (Just omit it.)
 
 ## KEEP-guards — these are real blocks, never demote/drop them
-- A **named theorem WITH its own statement or an author**: „Satz 6.24 Cook/Levin — SAT ist NP-vollständig", „Satz von Immerman–Szelepcsényi". KEEP.
-- A **complexity-class (in)equality / open question**: „P = NP?", „NL = coNL". KEEP.
-- Anything headed „**Definition**", a **problem**, an **algorithm**, a **reduction** („3-SAT ≤ Clique"). KEEP.
+- **Similarity is NOT containment:** an element with its own syntax/definition and its own purpose is a SIBLING of its neighbours, not their part — even with similar syntax, the same category, or shared context (a blockquote is not part of a code block; a footnote is not part of a task list). KEEP.
+- A **named theorem WITH its own statement or an author**: „Satz 6.24 Cook/Levin — SAT ist NP-vollständig". KEEP.
+- A **fundamental (in)equality / open question** of the field: „P = NP?", „NL = coNL". KEEP.
+- Anything headed „**Definition**", a **problem**, an **algorithm/method**, a **relation between two named things** („3-SAT ≤ Clique"). KEEP.
 
-Judge by the CONTENT (after „—"), not the label. When unsure whether something is a fragment or a concept: if it has an obvious parent in the list → demote; otherwise → keep (never drop on doubt).
+Judge by the CONTENT (after „—"), not the label. When unsure whether something is a fragment or a concept: demote only if the entry clearly makes a statement ABOUT its parent or is a form OF it; otherwise → keep (never drop on doubt).
 
 Write ONLY the JSON file to: {out_path}
 

templates/Prompt/Blocks-Filter.md

@@ -8,28 +8,26 @@ JUDGE the numbers **{from_n} to {to_n}** — go through them **ONE BY ONE**, one
 ## Procedure per entry (mandatory for EACH one)
 For each entry {from_n}–{to_n}:
 1. What is the **subject**? (What is being talked about?)
-2. Is this subject itself another entry in the list — and does the entry only state a PROPERTY, a PROOF PART, a NOTATION, or a RUNTIME DETAIL about it?
+2. Is this subject itself another entry in the list — and does the entry only state a PROPERTY, a PART, a SUB-FORM, or a DETAIL of it?
    - **Yes → fragment**, parent = the number of that subject.
    - No, it stands on its own → block (keep).
-Lines marked with **⚠** are suspected cases (property/runtime/notation) — check them especially carefully. Decide by the content, not by the marking.
+Lines marked with **⚠** are suspected cases (property/detail/notation) — check them especially carefully. Decide by the content, not by the marking.
 
 ## What is a BLOCK (standalone learning unit — keep)?
-A block is self-contained: you can explain it WITHOUT presupposing another block as its subject.
-- A **problem**: „3-SAT", „Clique", „Knapsack", „Dominating Set".
-- A **method/algorithm**: „LPT Scheduling", „Christofides", „FPTAS".
-- A **definition/concept**: „NP", „Reduktion", „Verifizierer", „KNF".
-- A **named theorem WITH its own statement**: „Cook-Levin: SAT ist NP-vollständig".
+A block is self-contained: you can explain it WITHOUT presupposing another block as its subject. A distinct element, concept, method, problem, or named theorem with its own statement stands on its own.
+- **CRITICAL — similarity is NOT containment.** Two entries with similar syntax, related purpose, or the same category are SIBLINGS, not parent and part. A blockquote is not part of a code block just because both mark lines with a prefix; a footnote is not part of a task list just because both are extensions of the same standard. Demote ONLY when the entry makes a statement ABOUT the parent or is a form OF the parent — never because the two are alike or usually taught together.
+- An element with its own syntax/definition and its own purpose is its own block, even if a bigger neighbour exists.
+- Examples across domains: a **problem** („3-SAT", „Knapsack"), a **method/algorithm** („Christofides", „Quicksort"), a **definition/concept** („NP", „Reduktion", „Blockquote", „Directive"), a **named theorem WITH its own statement** („Cook-Levin: SAT ist NP-vollständig").
 
 ## What is a FRAGMENT (belongs to another block → demote)?
 Self-containment test: does the entry presuppose ANOTHER concept in the list as its subject? Then it is that concept's property/part, not its own block.
-- **Property/status** of a problem X (that is itself in the list): „X ist NP-vollständig", „X ∈ NP", „NP-Schwere von X", „Approximationsgüte von X". → parent = X.
-- **Lower bound / ETH bound** of a problem X: „Lower Bound bzgl. Knoten für VERTEX COVER", „ETH untere Schranke HITTING SET (|U|)", „2^Ω(√|E|) …". → parent = X (the problem the bound is about).
-- **Bare theorem / proof reference**: „Satz 6.12: P ⊆ NP", „Beweis Satz 6.16 (⇒)", „Beweis ⊃ von Satz 6.21", „Satz 7.20 (Sahni)", „Pm||Cmax NP-vollständig (Satz 7.23)" — a restated inclusion/membership or a bare „Satz N"/„Beweis …" is a proof detail. → parent = the problem/algorithm/class it is about (P/NP, Sahni's algorithm, Pm||Cmax …).
-- **Proof/reduction gadget or variable**: „αEnde", „A-Komponente", „Dummy Items", „αu-Variablen", „Variablenungleichungen im ILP", „Austausch-Argument". → parent = the theorem/reduction in whose proof it appears.
-- **Approximation-guarantee facet**: „Güte 2", „Güte 2 − 1/m", „Approximative Güte 2", „List Scheduling Güte (2 − 1/m)". → parent = the algorithm it bounds (List Scheduling, LPT, …).
-- **Runtime/size detail**: „O(|V|⁴) Verifizierer-Laufzeit", „|V'| = |V| bei Reduktion", „Reduktion in O(|E|)". → parent = the algorithm/reduction.
-- **Parent named in the entry's OWN title:** if the title itself contains another block's name („Lower Bound … für **VERTEX COVER**", „**List Scheduling** Güte …", „**Pm||Cmax** NP-vollständig"), that named block IS the parent — demote to it. Do not keep such an entry just because you would scan the whole list; the parent is right there in the title.
-- **Over-specific variant** of a base problem that is itself in the list: „Even-Knapsack", „Subset Sum Cardinality", „Partition (3·Summe)", „SAT3" are exercise-tweaked variants of „Rucksackproblem"/„Subset Sum"/„Partition"/„SAT". → parent = the base problem. (A genuinely different problem with its own theory stays its own block.)
+- **Property/status of X** (X itself in the list): „X ist NP-vollständig", „X ∈ NP", „X ist optional", „Standard-Verhalten von X". → parent = X.
+- **Parent named in the entry's OWN title:** if the title itself contains another block's name as its subject („Lower Bound für **VERTEX COVER**", „**List Scheduling** Güte", „Anker für **Überschriften**"), that named block IS the parent — demote to it. Do not keep such an entry just because you would scan the whole list; the parent is right there in the title.
+- **Sub-form/variant of a base entry** that is itself in the list: „ATX-Überschrift" and „Setext-Überschrift" are forms of „Überschriften"; „Even-Knapsack" is an exercise-tweaked variant of „Rucksackproblem". → parent = the base entry. (A genuinely different concept with its own rules stays its own block — see the sibling rule above.)
+- The following patterns are typical for THEORY-SCRIPT topics (use them when they fit, ignore them otherwise):
+  - **Bare theorem / proof reference**: „Satz 6.12: P ⊆ NP", „Beweis Satz 6.16 (⇒)", „Satz 7.20 (Sahni)" — a restated inclusion/membership or a bare „Satz N"/„Beweis …" is a proof detail. → parent = the object it is about.
+  - **Proof/reduction gadget or variable**: „αEnde", „A-Komponente", „Dummy Items", „Austausch-Argument". → parent = the theorem/reduction in whose proof it appears.
+  - **Bound/guarantee/runtime facet**: „ETH untere Schranke HITTING SET", „Güte 2 − 1/m", „O(|V|⁴) Verifizierer-Laufzeit", „Reduktion in O(|E|)". → parent = the problem/algorithm it bounds.
 
 ## What is an EXERCISE ARTEFACT (no concept at all → hard-drop)?
 Rare, and applied cautiously. ONLY clear exercise-sheet / cross-reference scaffolding that is neither a learnable concept nor a fragment of one AND has no parent in the list. These forms all count, no matter where the marker sits:
@@ -37,13 +35,13 @@ Rare, and applied cautiously. ONLY clear exercise-sheet / cross-reference scaffo
 - a bare sheet/task reference: „Blatt 10", „Aufgabe 3", „Übung 7.31";
 - a worked-example / table / figure reference: „Scheduling Beispiel Tab. 7.1", „Beispiel 3.2", „Abbildung 4.5";
 - a one-off framing with no standalone content.
-Put its number in `drop`. NEVER drop anything that names a real problem/method/definition/theorem/reduction — if there is any doubt, keep it (or demote it as a fragment with a parent). A **named theorem WITH its own statement** („Satz 6.24 Cook/Levin — SAT ist NP-vollständig") is a real block, never an artefact. If it has a parent in the list, prefer demoting (fragment) over dropping.
+Put its number in `drop`. NEVER drop anything that names a real concept/element/method/definition/theorem — if there is any doubt, keep it (or demote it as a fragment with a parent). A **named theorem WITH its own statement** is a real block, never an artefact. If it has a parent in the list, prefer demoting (fragment) over dropping.
 
 ## Rules
 - A fragment is demoted ONLY if its **parent block is in the list** (give its number). If you find no parent → keep it (don't list it).
-- The doubt concerns STANDALONE-NESS: if it's unclear whether an entry stands on its own → keep it. But a clear property/notation/proof part WITH a parent in the list IS a fragment — don't keep it out of caution.
-- A standalone **reduction between two problems** is a block, NOT a fragment („3-SAT ≤ Clique").
-- A **named theorem WITH its own relational statement** — a biconditional/implication/reduction between two named objects („Satz 6.37: 3-SAT ≤ 3-Färbung … ⇔ …") — is a block; keep it even if it references other blocks. Only a BARE label with no statement („Satz 7.18", „Remark 7.28"), a unary status („X ist NP-vollständig", „X ∈ NP"), or a güte/bound/proof-size facet is a fragment.
+- The doubt concerns STANDALONE-NESS: if it's unclear whether an entry stands on its own → keep it. But a clear property/sub-form/detail WITH a parent in the list IS a fragment — don't keep it out of caution.
+- A standalone **relation between two named things** is a block, NOT a fragment („3-SAT ≤ Clique").
+- A **named theorem WITH its own relational statement** — a biconditional/implication/reduction between two named objects — is a block; keep it even if it references other blocks. Only a BARE label with no statement, a unary status („X ist NP-vollständig"), or a bound/proof facet is a fragment.
 - Judge by the CONTENT (after the „—"), not the title.
 
 Write ONLY the JSON file to: {out_path}

templates/Prompt/Guide-Outline-Review.md

@@ -0,0 +1,16 @@
+Topic "{topic}". Below is the final chapter outline of a learning guide. Your ONLY job: find blocks that sit in the WRONG chapter and name the chapter where they belong. This is a placement check, not a redesign.
+
+OUTLINE (chapters are numbered, blocks carry their block number):
+{chapters}
+
+## Rules
+- Go through every block: does its subject match the chapter's theme better than any other chapter's?
+- Report ONLY clear misplacements. A defensible placement is NOT a misplacement — leave it.
+- Do NOT rename chapters, do NOT create chapters, do NOT reorder within a chapter.
+- If everything fits, report no moves.
+{extra}
+
+Write ONLY the JSON file to: {out_path}
+
+Format — `moves` maps a misplaced BLOCK number to the target CHAPTER number (may be empty):
+{{"moves": {{"7": 2, "15": 4}}}}