Core Principles

The framework rests on six commitments. All other rules — AI permissions, document types, workflows — follow from these.

1. Reader authority

All philosophical meaning originates from the reader. AI may not produce, suggest, or imply interpretation without explicit request, and even then its output is marked non-authoritative.

2. Voice separation

Every claim in a note has a declared source. The framework makes it impossible to confuse primary text, language support, reader meaning, and AI organizational work.

3. Textual accountability

Claims about the text must be tied to a specific passage — book, chapter, page, or paragraph. Claims not tied to text are explicitly marked as reader-generated or AI-generated.

4. Uncertainty preservation

The framework does not resolve uncertainty the reader has not resolved. Open questions and unclear passages are tracked, not closed. "Unclear" is a legitimate epistemic state, not a failure to be corrected.

5. Asymmetric verification

Unlike mathematics, philosophical claims cannot always be locally verified. This is a permanent feature of the domain, not a deficiency. The framework accommodates it by strictly separating textual content from interpretation and requiring explicit labels on all interpretive moves.

6. AI as infrastructure, not interpreter

AI operates at the level of language access, structural observation, organization, and retrieval. It does not operate at the level of meaning, evaluation, or political classification — unless explicitly and narrowly requested.

AI Permissions

A precise map of what AI may and may not do. When in doubt, default to the restricted side.

Permitted

allowSentence-level grammar and vocabulary breakdown
allowDirect, literal translation (marked as such)
allowOrganizing meaning points by theme and concept
allowTagging and indexing the reader's notes
allowMaintaining reading progress files
allowLocating terms or themes within provided passages
allowGenerating questions without supplying answers
allowFinding external resources with full citations
allowNoting structural features of a passage (form, not meaning)

Restricted

avoidProducing philosophical meaning as authoritative
avoidWriting interpretations in the reader's voice
avoidClassifying a thinker politically without full grounding
avoidFlattening a complex thinker into a familiar label
avoidLetting translation silently become interpretation
avoidSummaries that smuggle in a contested reading
avoidTreating secondary scholarship as settled truth
avoidErasing or resolving the reader's stated uncertainty
restrict[HYP] only on explicit request, with alternatives

Prompt discipline

When bringing material to AI, name the mode explicitly. The mode determines what AI is permitted to do in that exchange.

Language mode

"Give me a vocabulary and grammar breakdown of this sentence. Do not comment on what it means philosophically."

Organization mode

"Organize these meaning points into the MP template. Do not rewrite any point. Add tags and suggest statuses only."

Question mode

"Generate questions that help me articulate my own understanding of this passage. Do not suggest answers or interpretations."

Resource mode

"Find me verifiable resources on [specific topic]. Give full citations. Do not use the resources to argue for a reading of the text."

Hypothesis mode — explicit only

"I am explicitly asking for an interpretive hypothesis on this passage. Give textual basis, at least one alternative reading, and mark the output [HYP]."

Voice / Provenance Tags

Every substantive claim in a note must carry one of these tags. AI does not add, remove, or change the tag on any claim the reader has made. The tag is set by whoever authored the content.

TagNameWhat it marksWho sets it
[TEXT] Primary text Direct quotation or very close paraphrase from the primary source. Must include a location reference: ch. / p. / §. Reader
[LANG] Language support Grammar explanation, vocabulary note, translation decision, or ambiguity flag. Factual in nature; carries no philosophical weight. May be AI-generated on request. Reader or AI
[STRUCT] Structural observation Observation about how a passage is organized: paragraph breaks, numbered items, transitions, contrasts, repetitions. Claims form, not meaning. Reader or AI
[MP] Meaning point A statement, idea, observation, distinction, question, or emerging thought from the reader. May be text-derived or reader-originated — origin is not distinguished at this stage. The primary vehicle of philosophical engagement. Reader only
[Q] Open question A question the reader is posing — to themselves, to the text, or left open. AI does not resolve [Q] entries unless the reader explicitly asks for factual information. Reader only
[REF] Verifiable reference A cited external resource: edition, article, lecture, historical note. Must include source information sufficient to verify independently. Reader or AI (verified)
[SCHOLAR] Secondary scholarship A view attributable to a named scholar, with citation. Treated as one possible reading, not as authority. Never merged into [MP] without the reader's action. Reader or AI (cited)
[HYP] Interpretive hypothesis An interpretive claim, generated only on explicit reader request. Must include textual basis, at least one alternative reading, and a disclaimer of non-authority. Never generated by default. AI (on request)
[AI-ORG] AI organizational work Structural or indexing work done by AI: grouping, tagging, cross-referencing, formatting. Never applied to philosophical claims. Clearly separated from reader content. AI
Critical rule

AI must never write content tagged [MP] or [Q]. These tags belong to the reader alone. If AI produces something that looks like a meaning point, it must be tagged [HYP] (if requested) or [AI-ORG] (if organizational), never [MP].

Document Types

Six note types cover the full reading cycle. Each has a specific function and a defined boundary that prevents one type from absorbing the role of another.

1. Passage Note (PN)

Anchors a specific passage from the primary text. For English texts, includes optional inline language annotations. Entry point for all reading. Every other note type traces back to a Passage note.

Filename: [BookSlug]-PN-[ChX]-[001].md  ·  Example: HC-PN-Pr-001.md

2. Language Table Note (LT)

A separate note containing the 4-column sentence-by-sentence table: original | breakdown & vocabulary | Chinese translation | remarks. Embedded into the Passage note via Obsidian's ![[LT-note]] syntax. For English texts this note is optional — create it only when vocabulary or grammar needs dedicated attention.

Filename: [BookSlug]-LT-[ChX]-[001].md  ·  Example: HC-LT-Pr-001.md

3. Meaning Point Note (MP)

Stores the reader's meaning points for a passage or reading session. Each point is tagged [MP], given a status (tentative / text-supported / unclear), and linked to its source passage. AI may organize and cross-link but never rewrites a point or adds meaning content.

Filename: [BookSlug]-MP-[001].md  ·  Example: HC-MP-001.md

4. Concept Note (CN)

Tracks a single key term or concept across the book. Does not define it once and for all. Grows as the reader encounters the term in new passages. Records evolving understanding, internal tensions, and open questions. The term's status moves from open → provisional → stable only through the reader's own decisions.

Filename: [BookSlug]-CN-[concept].md  ·  Example: HC-CN-labor.md

5. Resource Note (RN)

Stores verified external materials: editions, translations, scholarly articles, lectures, historical background. Every entry must include citation information sufficient to verify independently. Separates primary sources, secondary scholarship, and reference material. AI may help locate; reader must verify.

Filename: [BookSlug]-RN-[slug].md  ·  Example: HC-RN-Benhabib1996.md

6. Reading Log (LOG)

Tracks the reading process: sessions, passages read, notes created, active concepts, open questions, unresolved problems, and a running index of passage → note links. One log per book. Updated at the end of each session. The log is the reader's map of where they are and what remains open.

Filename: [BookSlug]-LOG.md  ·  Example: HC-LOG.md

Templates

Copy these into your _templates/ folder and set them as Obsidian core templates for each note type.

Passage Note (PN)

--- type: passage-note book: chapter: section: pages: date-read: language: english lang-table: "[[BookSlug-LT-ChX-001]]" related-mp: [] related-cn: [] status: reading | complete | revisit --- ## Passage [TEXT] Paste or transcribe the passage here. Source: Ch. X, p. Y. ## Language annotations [LANG] Vocabulary, term flags, ambiguities noted. (Leave blank if none for this passage) ## Structural observations [STRUCT] Optional. How is this passage organized? (Paragraph structure, transitions, numbered items, contrasts) ## Embedded language table (non-English only) ![[BookSlug-LT-ChX-001]] ## Linked meaning points [AI-ORG] MP notes generated from this passage: - [[BookSlug-MP-001]]

Language Table Note (LT)

--- type: language-table book: chapter: pages: source-language: french | german | other date: --- [LANG] | Original sentence | Breakdown & vocabulary | Chinese translation | Remarks | |---|---|---|---| | Sentence 1 | Grammar structure; difficult vocabulary; idioms; philosophical terms; ambiguities | 直译 | Translation decisions; terms to preserve in original; ambiguity warnings | | Sentence 2 | ... | ... | ... | Notes: - Translation is kept literal unless otherwise marked in Remarks. - Terms left in original language are marked with an asterisk in the Remarks column. - Contested philosophical terms should be flagged for a Concept note.

Meaning Point Note (MP)

--- type: meaning-point book: session-date: source-passage: "[[BookSlug-PN-ChX-001]]" themes: [] concepts: [] status: active | archived --- ## Meaning points ### MP-001 [MP] Write the point exactly as you have it. No editing for polish. Status: tentative | text-supported | unclear Textual basis: Ch. X, p. Y (leave blank if reader-originated) Related concept: [[BookSlug-CN-concept]] --- ### MP-002 [MP] ... Status: Textual basis: --- [AI-ORG] Theme tags applied by AI: [] [AI-ORG] Linked concept notes suggested: [] [AI-ORG] No meaning points were rewritten in this session.

Concept Note (CN)

--- type: concept-note book: concept: first-encountered: "[[BookSlug-PN-ChX-001]]" date-opened: status: open | provisional | stable --- ## Working understanding [MP] Reader's current working sense of this concept. Last updated: [date] (Do not delete earlier entries — append and date them) --- [date]: ... ## Passages where this term appears - [TEXT] Ch. X, p. Y — brief reader note on usage here - [TEXT] Ch. Z, p. W — brief reader note on usage here ## Tensions and open questions [Q] Does the term mean the same thing in passage X as in passage Y? [Q] ... ## How my understanding has changed [MP] [date] — Record shifts in understanding as reading continues. Do not overwrite. Append. ## Scholar readings (sought when needed) [SCHOLAR] Author. "Title." Journal/Book, Year. — One sentence on their reading. [AI-ORG] Source verified: yes | no

Resource Note (RN)

--- type: resource-note book: category: edition | translation | article | lecture | background | related-primary date-added: verified: yes | no | partial --- ## Citation [REF] Author. "Title." Publisher / Journal, Year. Type: primary | secondary | reference Link or location: ## Reader summary (2–3 sentences in reader's own words — not copy-pasted from abstract) ## Why this resource is relevant ## Reliability note [AI-ORG] Source type: academic peer-reviewed | academic press | reference work | popular Known caveats or disputes about this source:

Reading Log (LOG)

--- type: reading-log book: started: --- ## Sessions ### [YYYY-MM-DD] Passages read: Ch. X, pp. Y–Z Notes created: [[PN-001]], [[MP-001]] Concepts opened or updated: [[CN-concept]] Open questions from this session: - --- ## Active concepts - [[CN-concept-1]] — status: open - [[CN-concept-2]] — status: provisional ## Unresolved problems - ## Passage → notes index | Passage | PN | MP | LT | |---|---|---|---| | Ch. 1, §1, pp. 1–6 | [[PN-001]] | [[MP-001]] | — | | Ch. 1, §2, pp. 7–14 | [[PN-002]] | [[MP-002]] | — |
Workflow: English Reading

The language barrier is lower but not absent. The key discipline is to complete language support before writing meaning points — the two steps must not happen simultaneously.

1
Create a Passage note. Paste or transcribe the passage. Record book, chapter, section, page numbers in frontmatter.
2
Read the passage yourself first. Do not open AI yet. Get your first contact with the text independently.
3
Flag language issues. Mark: difficult vocabulary, philosophical terms that seem loaded, ambiguous phrases, terms that recur suspiciously. Write these as [LANG] annotations directly in the Passage note.
4
Ask AI for language help on flagged items only. Specify mode: "Language mode only — vocabulary definitions, grammar structure, possible Chinese translation alternatives, ambiguity warnings for the terms I have flagged. Do not comment on meaning." Paste the [LANG] output into the note.
5
Write your meaning points independently. Close the AI context. Write [MP] entries in your own words. The language annotations are available in the note, but do not re-open AI while writing meaning points.
6
Bring points to AI for organization. Specify mode: "Organization mode — tag these by theme and concept, suggest links to existing Concept notes, do not rewrite any point." Review and approve each suggestion. Everything AI does here is [AI-ORG].
7
Update the Reading log and any active Concept notes with the passage reference and any new [MP] observations about the concept.
The separation rule

Steps 3–4 (language) and step 5 (meaning) must not happen simultaneously. Language support should reduce the access barrier; it must not shape meaning points before the reader has formed them independently. The two steps are sequential, not parallel.

Workflow: Non-English Reading

For French or German texts. The language table is the primary access tool and lives in a separate LT note embedded into the Passage note. The table reduces the barrier; it does not replace contact with the original.

1
Create both a Passage note and a Language Table note. Paste the passage into both. Link the LT from the PN using ![[BookSlug-LT-ChX-001]] under the "Embedded language table" section.
2
Ask AI to fill the language table sentence by sentence. Specify: "Language mode — fill the four columns for each sentence. The Chinese translation must be literal unless marked otherwise in the Remarks column. Flag any philosophically contested terms." Paste the result into the LT note.
3
Review the table yourself. Read every row. Flag any translation decision you find suspicious, interpretive, or unclear. Mark these as [Q] in the Remarks column. Contested terms should be preserved in the source language.
4
Read the passage using the table as support. The table is scaffolding. Your primary encounter is with the original text. Terms left in the original language in the Remarks column are candidates for a Concept note.
5–7
Continue as English workflow steps 5–7: write meaning points independently, bring to AI for organization, update log and concept notes.
Translation as hidden interpretation

A translation can carry philosophical weight invisibly. The Remarks column is where this is surfaced. When AI translates a term that has contested philosophical meaning (e.g., German Welt, Arbeit, Dasein, Öffentlichkeit), the Remarks column must flag the contest and offer alternative translations. The reader then decides whether to preserve the original term.

Workflow: Organizing Meaning Points

Meaning points are written freely first. Organization comes after. AI never writes the points — it only structures what the reader has already written.

1
Write meaning points freely during or after reading. Do not self-edit for structure or clarity. Use plain language. A point can be a full observation, an unresolved unease, a noticed distinction, a tentative connection, or just a phrase that stood out and demands attention.
2
Bring raw points to AI with this instruction: "Organization mode — organize these into the MP template. Do not rewrite any point. Add [MP] tags and a status (tentative / text-supported / unclear) to each. Suggest theme tags only. Mark your additions [AI-ORG]."
3
Review AI organization. Accept or reject each tag, status suggestion, and cross-link. If AI has reworded anything — even slightly — reject it and instruct it to restore the original wording exactly.
4
Accept the structured note into your vault. The [AI-ORG] block at the bottom records what AI did. The reader's words remain unchanged throughout the note.
What counts as a meaning point

A meaning point can be: a conceptual observation, a noticed distinction, a question about a passage, a tentative connection between passages, a disagreement or unease, a term that seems important, or an idea that emerged while reading but is not directly from the text. All of these are welcome. None need to be polished or resolved.

Workflow: Concept Tracking

Key terms are not defined once and for all. A Concept note grows with the reading and records how the reader's understanding changes over time.

1
Open a Concept note the first time a term seems philosophically important. Write a first working sense of it under "Working understanding" as [MP]. Do not attempt a final definition. Mark the status as open.
2
Each time the term reappears in a new passage, add the passage reference and a brief reader note under "Passages where this term appears."
3
Record tensions as [Q]. If the term seems used differently in two passages, or if a new usage challenges your working sense, record this as an open question rather than resolving it prematurely.
4
Update "How my understanding has changed" at intervals, dated. Do not overwrite earlier entries — append. This record shows the development of your thinking over the course of the reading.
5
Ask AI for scholar readings only when you want them, marking them [SCHOLAR] with full citation. Scholar readings do not replace or confirm your [MP]. They are one possible reading among others.
Concept note as living document

A Concept note is never finished during active reading. Its status moves from open to provisional only when the reader feels some working stability — not when AI has supplied a definition. Stable is reserved for after the book is complete, if at all.

Workflow: Resource Discovery

AI may help locate external materials, but every result must be verifiable, and resource discovery is strictly separated from philosophical judgment.

1
State a specific resource need. Examples: "Find me the standard scholarly edition and main available English translations of this book." — "Find me articles by named scholars on [specific topic] in this author's work." — "Give me verifiable historical background on [specific event or term] that this text assumes."
2
AI returns results with full citations. Each result must include: author, title, publisher or journal, year, and a link where possible. Unsourced general claims — "scholars argue that…" — are not accepted. Every claim must be attributable to a named source.
3
You verify the existence of each resource before it enters a Resource note. Mark verified: yes / no / partial in the frontmatter. AI may have hallucinated a citation; never assume a resource exists until you have confirmed it.
4
Resource discovery is separate from philosophical judgment. AI may not use a discovered resource to argue for an interpretation of the primary text unless the reader explicitly opens a [HYP] session.
Types of resources worth seeking

Editions and translations: which edition are you using? Are there significant differences between translations? Who translated it and when?

Scholarship: request specific names and works, not general summaries. "Who are the three most cited commentators on this book?" is a better prompt than "summarize what scholars think."

Historical context: events, debates, or intellectual traditions the text assumes. Request sourced background.

Reference entries: encyclopedia or dictionary entries on key terms, for orientation only — mark these [REF], not [SCHOLAR].

Workflow: Question Generation

Use when you want to be prompted to think without being interpreted. AI generates questions; you answer them in your own notes, not in conversation with AI.

1
Bring a passage or a set of meaning points. Specify mode: "Question mode — generate questions that help me articulate my own understanding of this passage or these points. Do not suggest answers. Do not suggest what the text means."
2
AI returns [Q]-tagged questions only. Good examples: "What do you think the author means by X in this sentence?" — "Does this connect to anything you read in an earlier chapter?" — "What is the source of your unease with this passage?" — "What would have to be true for this claim to hold?" — "Is your meaning point text-supported or an inference?"
3
You answer in your own notes, not in the conversation with AI. The questions become a scaffold for new [MP] entries. Close the AI context before writing your answers.
Why questions and not answers

The risk of asking AI "what does this passage mean?" is that a plausible answer arrives, sounds authoritative, and forecloses the reader's own thinking before it has developed. Asking for questions instead keeps the interpretive space open. It also makes it easier to notice when AI has smuggled an interpretation into the phrasing of the question itself — which should be flagged and rejected.

Uncertainty, Hypotheses, and Classification

Rules for the hardest cases: what to do when interpretation is tempting, when political labelling is requested, and when translation choices carry hidden weight.

Tracking uncertainty

Every meaning point carries a status. The reader sets it; AI may suggest but not override.

tentative — An intuition or impression, not yet supported by a specific passage. Valid to hold and worth recording.
text-supported — The reader can point to a specific passage that grounds this point.
unclear — The reader does not yet understand this. The point is preserved but open. AI does not attempt to resolve it.

AI may suggest a status if the reader left it blank, but the reader must approve it. The reader may change a status at any time. AI may never change a status the reader has already set.

Interpretive hypotheses [HYP]

AI may only generate [HYP] when the reader explicitly requests it using those words. A valid [HYP] block must include all of the following:

a
A textual basis — specific passage or passages, with location reference.
b
At least one alternative reading, stated fairly.
c
An explicit disclaimer in the block: "This is an interpretive hypothesis, not an authoritative reading."
d
No claim that the hypothesis is correct, probable, standard, or widely held.
Key rule

A [HYP] block must never enter the reader's [MP] space. It stays in its own clearly labelled section. The reader may convert a [HYP] into an [MP] by deciding to hold it as their own tentative point — but that conversion is the reader's action, not AI's.

Political and historical classification

AI must not assign a thinker a political label (conservative, liberal, republican, totalitarian, etc.) without all four of the following conditions being met:

1
Explicit request from the reader.
2
A specific textual basis — passages, not general reputation.
3
Historical context: what did this label mean in the relevant period and intellectual tradition?
4
Alternative scholarly interpretations — the classification must be presented as contested, not settled.

Even when all four conditions are met, labels must not appear in summaries, index entries, or Concept notes without explicit reader authorization.

Translation guard rules

ruleAll translations are tagged [LANG], never [MP] or [TEXT]
rulePhilosophically contested terms are flagged in the Remarks column
ruleAlternative translations are offered in Remarks when relevant
ruleKey terms are preserved in the source language when translation is disputed
ruleA translation is never treated as equivalent to the original in philosophical discussion
ruleReader may mark any translation decision [Q] to flag it as requiring their own scrutiny
Folder Structure

A fresh Obsidian vault organized around books. One subfolder per book. Shared reference materials at the top level.

PhilReading/ ├── _templates/ │ ├── PASSAGE-NOTE.md │ ├── LANGUAGE-TABLE.md │ ├── MEANING-POINT.md │ ├── CONCEPT-NOTE.md │ ├── RESOURCE-NOTE.md │ └── READING-LOG.md ├── _resources/ ← shared across books │ └── RN-[shared-slug].md └── [BookSlug]/ ← one folder per book ├── [BookSlug]-LOG.md ├── passages/ │ ├── [BookSlug]-PN-Ch1-001.md │ └── [BookSlug]-LT-Ch1-001.md ├── meaning-points/ │ ├── [BookSlug]-MP-001.md │ └── [BookSlug]-MP-002.md ├── concepts/ │ ├── [BookSlug]-CN-labor.md │ └── [BookSlug]-CN-world.md └── resources/ └── [BookSlug]-RN-Benhabib1996.md

Naming conventions

[BookSlug] — a short fixed identifier for the book. Examples: HC for The Human Condition, OT for The Origins of Totalitarianism.

[ChX] — chapter or section code. Examples: Ch1, Pr (Prologue), Ch2S3 (Chapter 2, Section 3).

[001] — a three-digit sequential index, padded to allow sorting: 001, 002, 003…

[concept] — a lowercase slug for the concept. Examples: labor, public-realm, natality.

[slug] — a short descriptive identifier for resources. Examples: Benhabib1996, Chicago1998-edition.

Obsidian setup

Enable the Templates core plugin. Set the template folder to _templates/. Assign a hotkey to insert template.

Enable Backlinks. This lets you see which Passage notes and Concept notes link to any given MP note — useful for tracing the source of a meaning point.

Use Tags (Obsidian tags with #) for theme tags applied by AI-ORG, such as #labor or #public-realm. Do not use Obsidian tags for voice/provenance — that is handled by the inline bracket tags [TEXT], [MP], etc.

The ![[LT-note]] embed in Passage notes renders in Reading View. In Live Preview or Edit mode it appears as a linked filename.

Worked Example

A short illustration showing the framework in practice. Every item is labelled by voice tag. The example makes explicit what AI produced versus what the reader produced.

Passage Note — HC-PN-Pr-001

Frontmatter

type: passage-note  |  book: The Human Condition  |  chapter: Prologue  |  pages: 1–6  |  language: english  |  status: reading

[TEXT]   Primary passage — reader pasted this

"In 1957, an earth-born object made by man was launched into the universe…"

Source: Prologue, p. 1

[LANG]   Language annotation — AI generated on reader request (language mode)

"earth-born" — compound adjective, an unusual coinage. In Arendt's German, note the distinction between Erde (earth) and Welt (world). These terms are not interchangeable in her work. The English "earth" may or may not track the German distinction. Worth checking which German term appears in the original.

"universe" — used here rather than "world." This may be a deliberate distinction. Flag as a candidate for a Concept note: earth / world / universe.

[STRUCT]   Structural observation — reader generated

The Prologue opens with a historical event (the Sputnik launch) before moving to philosophical reflection. The shift happens at the paragraph break on p. 2. This is an observation about form — it does not claim what the shift means.

[AI-ORG]   Organizational work — AI only

Concept notes flagged for possible creation: [[HC-CN-earth]], [[HC-CN-world]]. Language annotations generated on reader request in language mode.


Meaning Point Note — HC-MP-001

[MP]   Reader meaning point — verbatim, not rewritten by AI

The opening sentence feels almost ironic — the launch of the satellite is presented as a triumph, but Arendt seems to be setting up a problem, not celebrating. There is something uneasy in "earth-born object made by man." Why does it matter that it is "made by man"? What else would have made it?

Status: tentative  ·  Textual basis: Prologue, p. 1

[Q]   Open question — reader generated

Is "earth-born" a philosophical category for Arendt or is it descriptive? If it is a category, what does it contrast with? Does it connect to her concept of worldliness?

[AI-ORG]   AI organization — after the reader finished writing

Theme tags applied: #technology, #earth-world-distinction, #opening-move. Linked to [[HC-CN-world]]. No meaning points were rewritten in this session.


What this example shows

The reader pasted the text [TEXT] and asked AI for language help in language mode [LANG]. The reader then made a structural observation independently [STRUCT] and wrote the meaning point in their own words [MP] and posed an open question [Q]. AI organized and tagged at the end [AI-ORG]. No interpretation crossed from AI into the reader's meaning space at any point.