# User: \\\\\\\\\\\\\\"## Bengson et al.'s Framework\\\\\\\\\\\\\\" can you give me much more information on this by checking t... ## Retrieval Notes - Session id: `a88b0bdb-1c68-49fc-8002-d355d2619952` - Last activity: `2026-01-23T11:01:57.168Z` ## My Notes <!-- Add your notes here. This section is preserved across syncs. --> ## Conversation ### User User: "## Bengson et al.'s Framework" can you give me much more information on this by checking the text thoroughly? I am in particular interested in the '6 properties for understanding'.. I am also interested in how these ideas can be connected up to a paper called 'what is philosophical progress?' which is also in the learning folder. Assistant: I'll read the current note first, then find both papers in the Learning folder to give you detailed information.Found both papers. Let me check their sizes and extract the text safely.The Bengson PDF is 199 pages (15MB) - too large to read directly. I see from the note that you already have extracted texts in Attachments. Let me check those and extract the progress paper.Let me extract to the Attachments folder and search the Bengson text for the specific content about the 6 properties. [Thinking: 5 block(s), 8.0s total] [Tool Read input: file_path=/Users/nickyoung/My Obsidian Vault/Notes/Metaphilosophy Landscape.md status=completed] [Tool Bash input: command=ls -la "/Users/nickyoung/Library/CloudStorage/[email protected]/My Drive/Sync/Learnin..., description=Find Bengson and philosophical progress papers in Learning folder status=completed] [Tool Bash input: command=pdfinfo "/Users/nickyoung/Library/CloudStorage/[email protected]/My Drive/Sync/Learni..., description=Check Bengson PDF metadata status=completed] [Tool Bash input: command=pdfinfo "/Users/nickyoung/Library/CloudStorage/[email protected]/My Drive/Sync/Learni..., description=Check Dellsén PDF metadata status=completed] [Tool Read input: file_path=/Users/nickyoung/My Obsidian Vault/Attachments/bengson_methodology_full.txt status=error] error: File content (337.2KB) exceeds maximum allowed size (256KB). Please use offset and limit parameters to read specific portions of the file, or use the GrepTool to search for specific content. [Tool Bash input: command=pdftotext "/Users/nickyoung/Library/CloudStorage/[email protected]/My Drive/Sync/Lear..., description=Extract Dellsén progress paper to text status=blocked] error: Access denied: Command path "/tmp/dellsen_progress.txt" is outside the vault. Agent is restricted to vault directory only. [Tool Bash input: command=pdftotext "/Users/nickyoung/Library/CloudStorage/[email protected]/My Drive/Sync/Lear..., description=Extract Dellsén progress paper to Attachments status=completed] [Tool Grep input: pattern=understanding|accurate|reason-based|robust|illuminating|orderly|coherent, path=Attachments/bengson_methodology_full.txt, output_mode=content, -i=true, -C=3 status=completed] [Tool Read input: file_path=/Users/nickyoung/.claude/projects/-Users-nickyoung-My-Obsidian-Vault/4312f5ca-c6e5-4b84-9f71-69a5262... status=completed] [Tool Read input: file_path=/Users/nickyoung/My Obsidian Vault/Attachments/dellsen_progress.txt status=error] error: File content (29615 tokens) exceeds maximum allowed tokens (25000). Please use offset and limit parameters to read specific portions of the file, or use the GrepTool to search for specific content. User: did you get cut off? Assistant: Yes, let me continue. I need to search more specifically for the 6 properties and read the Dellsén paper in chunks.Let me get more detail on each of the six properties and continue reading the Dellsén paper:Let me get the rest of the Dellsén paper to see their conclusions:Now I have enough detail. Here's the comprehensive information: --- ## Bengson et al.'s Six Properties for Theoretical Understanding From *The Rationalist Spirit* (2024), Bengson, Cuneo & Shafer-Landau argue that the **ultimate proper goal of philosophical inquiry is theoretical understanding**—not merely knowledge or true belief. Theoretical understanding is "the state that agents possess just when they fully grasp a theory" with these **six properties**: ### The Six Properties 1. **Accuracy** — The theory possesses a high degree of accuracy, since largely inaccurate theories fail to dispel confusion (characteristic of misunderstanding). 2. **Reason-based** — The theory is positively supported by considerations, beyond mere coherence, that speak in favor of its accuracy. Without such support, "signing on to the theory would be arbitrary or haphazard." 3. **Robust** — The theory answers "a multitude of questions about the most important features of the domain under investigation." A theory that neglects or dodges such questions "leaves out just what's needed to yield comprehension." 4. **Illuminating** — The theory's answers must "at least sometimes be not just general but also genuinely explanatory, going beyond a mere description of those features to explain why each exists or is instantiated." 5. **Orderly** — The theory doesn't just offer feature-specific explanations but also affords "a broader view of the domain by revealing how those (and other) features, as well as the proposed explanations, gel or hang together—for example, by exposing basic relations or systematic connections among them." This avoids miscellany—"the paradigm of which is a mere list." 6. **Coherent** — The theory fits well not only internally but also externally, with "a wide range of understanding-providing theories of other domains." A theory that massively conflicts with other accurate, reason-based, robust, illuminating, and orderly theories "does not further comprehension but muddles it." ### Hierarchical Structure Bengson et al. make a crucial structural point: **the first four properties are fundamental**, while the latter two (orderliness and coherence) only **conditionally** contribute to understanding: > "The orderliness and coherence of a theory contribute to its ability to supply understanding only if the theory possesses the other four features to at least some extent." This means you can have an orderly, coherent theory that provides no understanding if it lacks accuracy, reasons, robustness, or illumination. ### Theoretical Understanding vs. Knowledge They argue this understanding is **irreducible to** justified true belief, ordinary knowledge, or their conjunction: > "The function of such understanding is, inter alia, to illuminate, in a robust, orderly, coherent fashion, the portion of reality under investigation, and not simply to state a series of known truths or justified beliefs about it." --- ## Dellsén et al.'s "Enabling Noeticism" The paper "What is Philosophical Progress?" (Dellsén, Firing, Lawler & Norton, 2024) develops a distinct understanding-based account called **Enabling Noeticism**: > **Enabling Noeticism**: The discipline of philosophy makes progress regarding some phenomenon to the extent that philosophical research **puts people in a position** to increase their understanding of that phenomenon. ### Key Differences from Bengson et al. Dellsén et al. explicitly engage with Bengson (they cite them in footnote 6), but develop a **different notion of understanding**: | Bengson et al. | Dellsén et al. | |----------------|----------------| | Understanding = fully grasping a theory with six properties | Understanding = accurately & comprehensively representing **dependence relations** | | Focus on theory-possession | Focus on representing how phenomena depend on each other | | Six qualitative properties | Two quantitative dimensions: accuracy + comprehensiveness | | Requires reason-based support | Explicitly **doesn't require justification** | ### Understanding as Dependence Relations For Dellsén et al., understanding X is a matter of representing: - How X **depends on** various other phenomena - How other phenomena **depend on X** - Including "negative" facts (what X *doesn't* depend on) This is measured by: - **Accuracy** — how correctly you represent the dependencies - **Comprehensiveness** — how much of the network you represent ### The "Enabling" Dimension A critical innovation: progress isn't about philosophers *actually* gaining understanding, but about **making understanding publicly available**. The Dr. N. thought experiment (from Bird 2010) illustrates this: when Dr. N.'s paper sits in a journal unread for years, the discipline hasn't regressed—people are still *in a position* to gain understanding. This is a **for-whom** rather than **by-whom** conception: progress benefits anyone who might access the publicly available resources. ### Epistemically Undemanding Crucially, Dellsén et al. argue understanding **doesn't require justification or knowledge**: > "Justification is best seen as something that promotes, rather than constitutes, progress—e.g., in the way that argumentation and evidence frequently leads us to accept better theories." This sidesteps pessimistic arguments from disagreement: even if philosophers can't have justified beliefs due to persistent expert disagreement, they can still make progress by putting people in a position to understand. --- ## Connecting the Two Accounts ### Points of Convergence 1. **Understanding over knowledge**: Both reject the view that philosophical progress = accumulating true/justified beliefs 2. **Accuracy matters**: Both require connection to how things actually are 3. **Systematicity**: Both value seeing how things "hang together" (Sellars) 4. **Anti-list**: Both reject mere accumulation of facts without integration ### Points of Tension 1. **What is understanding?** - Bengson: Six qualitative properties of a theory - Dellsén: Representing dependence networks (accuracy × comprehensiveness) 2. **Role of reasons/justification** - Bengson: Theory must be "reason-based" (property #2) - Dellsén: Justification **promotes** but doesn't **constitute** progress 3. **Individual vs. social** - Bengson: Focus on inquirers grasping theories - Dellsén: Focus on public availability—"for whom" progress is made 4. **Illumination** - Bengson: Explicit requirement for explanatory content (property #4) - Dellsén: Implicit in dependence relations (explaining = showing dependencies) ### Philosophical Stakes The key disagreement may be about **what constitutes vs. promotes** progress: - For Bengson, satisfying the six properties (including being reason-based) **is** what understanding amounts to - For Dellsén, having reasons **helps you get to** understanding but isn't part of what understanding is This matters for whether philosophy can make progress despite persistent disagreement. Bengson's account might be more demanding but also more defensible as "progress worth making." --- Want me to capture these connections in a note? This could be valuable for any metaphilosophy or progress-related writing. [Thinking: 4 block(s), 6.0s total] [Tool Grep input: pattern=six (properties|features)|6 (properties|features)|properties of understanding, path=Attachments/bengson_methodology_full.txt, output_mode=content, -i=true, -C=5 status=completed] [Tool Grep input: pattern=\(i\).*\(ii\).*\(iii\)|accurate.*robust.*illuminating, path=Attachments/bengson_methodology_full.txt, output_mode=content, -i=true, -C=3 status=completed] [Tool Read input: file_path=/Users/nickyoung/My Obsidian Vault/Attachments/dellsen_progress.txt, offset=1, limit=500 status=completed] [Tool Read input: file_path=/Users/nickyoung/My Obsidian Vault/Attachments/bengson_methodology_full.txt, offset=1039, limit=100 status=completed] [Tool Read input: file_path=/Users/nickyoung/My Obsidian Vault/Attachments/dellsen_progress.txt, offset=500, limit=500 status=completed] [Tool Read input: file_path=/Users/nickyoung/My Obsidian Vault/Attachments/dellsen_progress.txt, offset=1000, limit=300 status=completed] User: "Bengson et al. make a crucial structural point: the first four properties are fundamental, while the latter two (orderliness and coherence) only conditionally contribute to understanding: "The orderliness and coherence of a theory contribute to its ability to supply understanding only if the theory possesses the other four features to at least some extent." This means you can have an orderly, coherent theory that provides no understanding if it lacks accuracy, reasons, robustness, or illumination." do they give any examples of stuff that would fail? I have a few diea but i want to know what the authors say. "A critical innovation: progress isn't about philosophers actually gaining understanding, but about making understanding publicly available. The Dr. N. thought experiment (from Bird 2010) illustrates this: when Dr. N.'s paper sits in a journal unread for years, the discipline hasn't regressed—people are still in a position to gain understanding. " i am not interested in what they say about progress, only their concept of understanding. Also, is there a paper by delsen and others that focusses more specifically on understanding? ### Assistant Let me search for examples in Bengson and find Dellsén's understanding-focused paper. ### Assistant Found Dellsén's understanding-focused paper. Let me search for more context on the Bengson examples and extract the Dellsén paper: ### Assistant Found the key example. Let me now extract the Dellsén understanding paper (it's small, 26 pages): ### Assistant Now I have the full picture. Here's what you asked for: --- ## Bengson et al.'s Example of Orderly/Coherent but Non-Understanding-Providing Theories Yes, they give a clear example: **the Method of Reflective Equilibrium**. From *The Rationalist Spirit* (pp. 102-103): > "Successfully implementing the Method of Reflective Equilibrium guarantees that a theory will at least be robust, orderly, and coherent. **But the method infamously fails to put inquirers on track to achieve even a modicum of accuracy**; nor is it clear that it plumps for outputs that are reason-based in the indicated sense." They elaborate further: > "If the modifications, additions, or abandonments that help inquirers achieve equilibrium are wide of the mark, lack support, or undermine robustness, then the equilibrium attained will fail to promote theoretical understanding." So the example is: a theory produced via Reflective Equilibrium can be internally orderly and cohere with other views, but if the initial judgments being balanced were themselves inaccurate (or if the adjustments made to achieve equilibrium track something other than truth), you end up with a **systematically wrong but elegant theory**. The orderliness and coherence become mere aesthetic properties of a confused system. They also mention the **Cost-Benefit Method** as problematic in a different way—it licenses trading off accuracy for other benefits: > "If a theory manages to be highly illuminating, robust, orderly, and coherent at the expense of accuracy, then the method licenses treating the last as expendable." --- ## Dellsén's Understanding Paper Yes! The paper you want is: **"Beyond Explanation: Understanding as Dependency Modelling"** Finnur Dellsén, *British Journal for the Philosophy of Science* 71 (2020): 1261-1286 This is where Dellsén develops his **Dependency Modelling Account (DMA)** of understanding: > **DMA**: S understands a phenomenon, P, if and only if S grasps a sufficiently accurate and comprehensive dependency model of P (or its contextually relevant parts); S's degree of understanding of P is proportional to the accuracy and comprehensiveness of that dependency model. ### Key Features of DMA **1. Understanding = Grasping Dependence Relations** Understanding X means having a model of: - How X depends on other things (causes, grounds, etc.) - How other things depend on X - Which things X does *not* depend on ("negative" facts) > "A dependency model better represents P to the extent that the network of dependence relations that P stands in is correctly depicted by the model." **2. Two Dimensions (Not Six Properties)** | Dimension | What it measures | |-----------|------------------| | **Accuracy** | How correctly you represent the dependencies | | **Comprehensiveness** | How much of the network you represent | These can trade off: - More comprehensiveness may sacrifice accuracy (idealization) - More accuracy may sacrifice comprehensiveness (abstraction) **3. Not Explanation-Based** This is the paper's main thesis—understanding can come apart from explanation. Dellsén identifies three types of cases: 1. **Explanatory Bruteness**: Phenomena with no explanation at all (e.g., fundamental constants, chancy events). You can still understand them by grasping that they *don't* depend on anything. 2. **Explanatory Targetedness**: Understanding a phenomenon without having explanations of its specific features (the paper goes into this in sections I didn't extract). 3. **Explanatory Disconnectedness**: Understanding how things relate without having explanations that connect them. **4. Gradability Built In** Understanding is inherently a matter of degree—you can always have more or less accurate, more or less comprehensive models. --- ## Comparing the Two Accounts on Understanding | Feature | Bengson et al. | Dellsén | |---------|---------------|---------| | **What you grasp** | A *theory* with 6 properties | A *dependency model* | | **Core properties** | Accuracy, reason-based, robust, illuminating, orderly, coherent | Accuracy + comprehensiveness | | **Gradability** | Implicit | Explicit (quantitative dimensions) | | **Explanation required?** | Implicitly yes (illumination = explanatory) | Explicitly no | | **Scope** | Philosophical inquiry | Scientific understanding (but generalizable) | Dellsén's account is *leaner*—two dimensions instead of six—but covers different ground. Bengson's is richer on what makes understanding *good* (the reason-based requirement, the illumination requirement), while Dellsén is focused on *what understanding is* independent of how you got it. --- I've extracted the Dellsén paper to [[Attachments/dellsen_understanding.txt]] if you want to dig deeper into specific sections.