What this project reads. This project currently only consumes data from an author's substack. Views expressed elsewhere are not currently integrated into the scoring. Only articles from the past 6 years (2020-2026) are evaluated to avoid bias from stale passages that no longer represent a writer's views.

How passages are evaluated. Every crux and vision axis is compared against a writer's full set of chunked passages using a small local embedding model (BAAI/bge-small-en-v1.5), which evaluates passages by similarity to a given crux/vision and selects the top 50. Claude Haiku then makes a yes/no relevance call for each passage and evaluates relevant passages for attribution (to check that the author isn't referencing someone else's opinion) and how much it supports the crux/vision axis on a scale of 1-5 for cruxes and −2-2 for axes.

How the average rating is calculated. Final score is calculated by weighted average according to passage recency. Passages written 5 years ago are given half the weight of newly written passages.

Specifically: recency = max(0, 1 − age_in_years / 10), and final_score = Σ(recency × passage_score) / Σ(recency).

How confidence is calculated. Confidence combines the quantity of recency weighted evidence and the consistency in scoring across that evidence. More passages generally means more confidence — but if a writer's own passages disagree sharply with each other, that pulls confidence back down even when there are a lot of them. Confidence is adjusted to account for the measurement noise found in Haiku's scoring.

Specifically: adjusted_weight = raw_weight / (1 + max(0, author_variance − 0.128)^1.5), where 0.128 is the measurement-noise floor found by repeat-scoring the same passages, and confidence = adjusted_weight / (adjusted_weight + 2). Displayed as low (adjusted_weight ≤ 0.67), unsure (between 0.67 and 6), or high (≥ 6).

Predicted vision: building the belief vector. Each writer's raw 1–5 crux scores are re-centered around the neutral midpoint, so a neutral “3” contributes nothing and stronger views in either direction contribute more.

Predicted vision: calculating alignment. The IAPS report maps each of the 9 visions to each of the 8 cruxes as supporting, opposing, or neutral. This project compares a writer's belief vector against the IAPS map by taking a normalized dot product of the two and evaluating which vectors are best aligned. To visualize the uncertainty in this judgement the project resamples available passages 400 times to produce a distribution of how consistently a given vision wins. You can view the distribution in the Landing Chart to see how decisively a view wins relative to other competing visions.

alignment = Σ(centered_score × crux_direction) / (2 × number_of_live_cruxes), displayed on the same 1–5 scale as everything else via displayed_score = 3 + 2 × alignment.

Advocated vision: the four axes. Grading each vision independently introduced significant inaccuracies. Different visions were held to different standards of what counted as relevant or in support which caused several relevant statements to be excluded in scoring. This error introduced a systematic bias towards certain visions (early iterations showed several writers supporting “Single Private Project” simply because they criticized specific regulations.)

To mitigate misattribution this project breaks the visions down across four unique axes to uniquely distinguish each view. Note: The IAPS paper breaks the visions down across only two axes (central vs distributed x private vs government) but to help the LLMs more cleanly distinguish between visions this project added Regulatory Intensity and Coalition size as well.

The four axes, and the exact statement each one is scored against:

• Concentration — “AI development should be concentrated in a single dominant organization or project, rather than remaining distributed and competitive across many independent developers.”
• Control — “AI development should be controlled and run by government or public institutions, rather than by private companies.”
• Coalition breadth — “AI governance and development should involve a broad, globally inclusive coalition of all major powers, rather than being unilateral or limited to a single nation.”
• Regulatory intensity — “Private AI development should be closely and strictly regulated by government, rather than left to light-touch, minimal regulation.”

Each axis is scored using the same mechanism as a crux (same passage retrieval, same Haiku relevance/attribution/scoring call, same recency-weighted average) but on a −2 to +2 scale centered on zero.

Advocated vision: matching axis positions to named visions. Each of the 9 IAPS visions is itself mapped onto the same four axes (for example, “Single private project” sits at high concentration / low control, while “Global coordinated regulator” sits at low concentration / N/A control / high coalition breadth / high regulatory intensity). A writer's advocated alignment with a given vision is the normalized dot product of their 4-axis position against that vision's 4-axis position — the same mechanism as predicted-vision alignment above, just computed over axes instead of cruxes. If a vision doesn't take a position on one of the four axes, that axis is excluded from the comparison for that vision entirely, rather than treated as neutral.

advocated_score = 3 + 2 × [Σ(writer_axis × vision_axis) / (4 × number_of_live_axes)], displayed on the same 1–5 scale as everything else.

Cruxes and axes with no data. If a writer hasn't written enough about a given crux or axis to score at all, that dimension defaults to neutral (3/5, or 0 on the axis scale) with the lowest possible confidence.

What this project reads. This project currently only consumes data from an author's substack. Views expressed elsewhere are not currently integrated into the scoring. Only articles from the past 6 years (2020-2026) are evaluated to avoid bias from stale passages that no longer represent a writer's views.

How passages are evaluated. Every crux and vision axis is compared against a writer's full set of chunked passages using a small local embedding model (BAAI/bge-small-en-v1.5), which evaluates passages by similarity to a given crux/vision and selects the top 50. Claude Haiku then makes a yes/no relevance call for each passage and evaluates relevant passages for attribution (to check that the author isn't referencing someone else's opinion) and how much it supports the crux/vision axis on a scale of 1-5 for cruxes and −2-2 for axes.

How the average rating is calculated. Final score is calculated by weighted average according to passage recency. Passages written 5 years ago are given half the weight of newly written passages.

Specifically: recency = max(0, 1 − age_in_years / 10), and final_score = Σ(recency × passage_score) / Σ(recency).

How confidence is calculated. Confidence combines the quantity of recency weighted evidence and the consistency in scoring across that evidence. More passages generally means more confidence — but if a writer's own passages disagree sharply with each other, that pulls confidence back down even when there are a lot of them. Confidence is adjusted to account for the measurement noise found in Haiku's scoring.

Specifically: adjusted_weight = raw_weight / (1 + max(0, author_variance − 0.128)^1.5), where 0.128 is the measurement-noise floor found by repeat-scoring the same passages, and confidence = adjusted_weight / (adjusted_weight + 2). Displayed as low (adjusted_weight ≤ 0.67), unsure (between 0.67 and 6), or high (≥ 6).

Predicted vision: building the belief vector. Each writer's raw 1–5 crux scores are re-centered around the neutral midpoint, so a neutral “3” contributes nothing and stronger views in either direction contribute more.

Predicted vision: calculating alignment. The IAPS report maps each of the 9 visions to each of the 8 cruxes as supporting, opposing, or neutral. This project compares a writer's belief vector against the IAPS map by taking a normalized dot product of the two and evaluating which vectors are best aligned. To visualize the uncertainty in this judgement the project resamples available passages 400 times to produce a distribution of how consistently a given vision wins. You can view the distribution in the Landing Chart to see how decisively a view wins relative to other competing visions.

alignment = Σ(centered_score × crux_direction) / (2 × number_of_live_cruxes), displayed on the same 1–5 scale as everything else via displayed_score = 3 + 2 × alignment.

Advocated vision: the four axes. Grading each vision independently introduced significant inaccuracies. Different visions were held to different standards of what counted as relevant or in support which caused several relevant statements to be excluded in scoring. This error introduced a systematic bias towards certain visions (early iterations showed several writers supporting “Single Private Project” simply because they criticized specific regulations.)

To mitigate misattribution this project breaks the visions down across four unique axes to uniquely distinguish each view. Note: The IAPS paper breaks the visions down across only two axes (central vs distributed x private vs government) but to help the LLMs more cleanly distinguish between visions this project added Regulatory Intensity and Coalition size as well.

The four axes, and the exact statement each one is scored against:

• Concentration — “AI development should be concentrated in a single dominant organization or project, rather than remaining distributed and competitive across many independent developers.”
• Control — “AI development should be controlled and run by government or public institutions, rather than by private companies.”
• Coalition breadth — “AI governance and development should involve a broad, globally inclusive coalition of all major powers, rather than being unilateral or limited to a single nation.”
• Regulatory intensity — “Private AI development should be closely and strictly regulated by government, rather than left to light-touch, minimal regulation.”

Each axis is scored using the same mechanism as a crux (same passage retrieval, same Haiku relevance/attribution/scoring call, same recency-weighted average) but on a −2 to +2 scale centered on zero.

Advocated vision: matching axis positions to named visions. Each of the 9 IAPS visions is itself mapped onto the same four axes (for example, “Single private project” sits at high concentration / low control, while “Global coordinated regulator” sits at low concentration / N/A control / high coalition breadth / high regulatory intensity). A writer's advocated alignment with a given vision is the normalized dot product of their 4-axis position against that vision's 4-axis position — the same mechanism as predicted-vision alignment above, just computed over axes instead of cruxes. If a vision doesn't take a position on one of the four axes, that axis is excluded from the comparison for that vision entirely, rather than treated as neutral.

advocated_score = 3 + 2 × [Σ(writer_axis × vision_axis) / (4 × number_of_live_axes)], displayed on the same 1–5 scale as everything else.

Cruxes and axes with no data. If a writer hasn't written enough about a given crux or axis to score at all, that dimension defaults to neutral (3/5, or 0 on the axis scale) with the lowest possible confidence.

What this project reads. This project currently only consumes data from an author's substack. Views expressed elsewhere are not currently integrated into the scoring. Only articles from the past 6 years (2020-2026) are evaluated to avoid bias from stale passages that no longer represent a writer's views.

How passages are evaluated. Every crux and vision axis is compared against a writer's full set of chunked passages using a small local embedding model (BAAI/bge-small-en-v1.5), which evaluates passages by similarity to a given crux/vision and selects the top 50. Claude Haiku then makes a yes/no relevance call for each passage and evaluates relevant passages for attribution (to check that the author isn't referencing someone else's opinion) and how much it supports the crux/vision axis on a scale of 1-5 for cruxes and −2-2 for axes.

How the average rating is calculated. Final score is calculated by weighted average according to passage recency. Passages written 5 years ago are given half the weight of newly written passages.

Specifically: recency = max(0, 1 − age_in_years / 10), and final_score = Σ(recency × passage_score) / Σ(recency).

How confidence is calculated. Confidence combines the quantity of recency weighted evidence and the consistency in scoring across that evidence. More passages generally means more confidence — but if a writer's own passages disagree sharply with each other, that pulls confidence back down even when there are a lot of them. Confidence is adjusted to account for the measurement noise found in Haiku's scoring.

Specifically: adjusted_weight = raw_weight / (1 + max(0, author_variance − 0.128)^1.5), where 0.128 is the measurement-noise floor found by repeat-scoring the same passages, and confidence = adjusted_weight / (adjusted_weight + 2). Displayed as low (adjusted_weight ≤ 0.67), unsure (between 0.67 and 6), or high (≥ 6).

Predicted vision: building the belief vector. Each writer's raw 1–5 crux scores are re-centered around the neutral midpoint, so a neutral “3” contributes nothing and stronger views in either direction contribute more.

Predicted vision: calculating alignment. The IAPS report maps each of the 9 visions to each of the 8 cruxes as supporting, opposing, or neutral. This project compares a writer's belief vector against the IAPS map by taking a normalized dot product of the two and evaluating which vectors are best aligned. To visualize the uncertainty in this judgement the project resamples available passages 400 times to produce a distribution of how consistently a given vision wins. You can view the distribution in the Landing Chart to see how decisively a view wins relative to other competing visions.

alignment = Σ(centered_score × crux_direction) / (2 × number_of_live_cruxes), displayed on the same 1–5 scale as everything else via displayed_score = 3 + 2 × alignment.

Advocated vision: the four axes. Grading each vision independently introduced significant inaccuracies. Different visions were held to different standards of what counted as relevant or in support which caused several relevant statements to be excluded in scoring. This error introduced a systematic bias towards certain visions (early iterations showed several writers supporting “Single Private Project” simply because they criticized specific regulations.)

To mitigate misattribution this project breaks the visions down across four unique axes to uniquely distinguish each view. Note: The IAPS paper breaks the visions down across only two axes (central vs distributed x private vs government) but to help the LLMs more cleanly distinguish between visions this project added Regulatory Intensity and Coalition size as well.

The four axes, and the exact statement each one is scored against:

• Concentration — “AI development should be concentrated in a single dominant organization or project, rather than remaining distributed and competitive across many independent developers.”
• Control — “AI development should be controlled and run by government or public institutions, rather than by private companies.”
• Coalition breadth — “AI governance and development should involve a broad, globally inclusive coalition of all major powers, rather than being unilateral or limited to a single nation.”
• Regulatory intensity — “Private AI development should be closely and strictly regulated by government, rather than left to light-touch, minimal regulation.”

Each axis is scored using the same mechanism as a crux (same passage retrieval, same Haiku relevance/attribution/scoring call, same recency-weighted average) but on a −2 to +2 scale centered on zero.

Advocated vision: matching axis positions to named visions. Each of the 9 IAPS visions is itself mapped onto the same four axes (for example, “Single private project” sits at high concentration / low control, while “Global coordinated regulator” sits at low concentration / N/A control / high coalition breadth / high regulatory intensity). A writer's advocated alignment with a given vision is the normalized dot product of their 4-axis position against that vision's 4-axis position — the same mechanism as predicted-vision alignment above, just computed over axes instead of cruxes. If a vision doesn't take a position on one of the four axes, that axis is excluded from the comparison for that vision entirely, rather than treated as neutral.

advocated_score = 3 + 2 × [Σ(writer_axis × vision_axis) / (4 × number_of_live_axes)], displayed on the same 1–5 scale as everything else.

Cruxes and axes with no data. If a writer hasn't written enough about a given crux or axis to score at all, that dimension defaults to neutral (3/5, or 0 on the axis scale) with the lowest possible confidence.

What this project reads. This project currently only consumes data from an author's substack. Views expressed elsewhere are not currently integrated into the scoring. Only articles from the past 6 years (2020-2026) are evaluated to avoid bias from stale passages that no longer represent a writer's views.

How passages are evaluated. Every crux and vision axis is compared against a writer's full set of chunked passages using a small local embedding model (BAAI/bge-small-en-v1.5), which evaluates passages by similarity to a given crux/vision and selects the top 50. Claude Haiku then makes a yes/no relevance call for each passage and evaluates relevant passages for attribution (to check that the author isn't referencing someone else's opinion) and how much it supports the crux/vision axis on a scale of 1-5 for cruxes and −2-2 for axes.

How the average rating is calculated. Final score is calculated by weighted average according to passage recency. Passages written 5 years ago are given half the weight of newly written passages.

Specifically: recency = max(0, 1 − age_in_years / 10), and final_score = Σ(recency × passage_score) / Σ(recency).

How confidence is calculated. Confidence combines the quantity of recency weighted evidence and the consistency in scoring across that evidence. More passages generally means more confidence — but if a writer's own passages disagree sharply with each other, that pulls confidence back down even when there are a lot of them. Confidence is adjusted to account for the measurement noise found in Haiku's scoring.

Specifically: adjusted_weight = raw_weight / (1 + max(0, author_variance − 0.128)^1.5), where 0.128 is the measurement-noise floor found by repeat-scoring the same passages, and confidence = adjusted_weight / (adjusted_weight + 2). Displayed as low (adjusted_weight ≤ 0.67), unsure (between 0.67 and 6), or high (≥ 6).

Predicted vision: building the belief vector. Each writer's raw 1–5 crux scores are re-centered around the neutral midpoint, so a neutral “3” contributes nothing and stronger views in either direction contribute more.

Predicted vision: calculating alignment. The IAPS report maps each of the 9 visions to each of the 8 cruxes as supporting, opposing, or neutral. This project compares a writer's belief vector against the IAPS map by taking a normalized dot product of the two and evaluating which vectors are best aligned. To visualize the uncertainty in this judgement the project resamples available passages 400 times to produce a distribution of how consistently a given vision wins. You can view the distribution in the Landing Chart to see how decisively a view wins relative to other competing visions.

alignment = Σ(centered_score × crux_direction) / (2 × number_of_live_cruxes), displayed on the same 1–5 scale as everything else via displayed_score = 3 + 2 × alignment.

Advocated vision: the four axes. Grading each vision independently introduced significant inaccuracies. Different visions were held to different standards of what counted as relevant or in support which caused several relevant statements to be excluded in scoring. This error introduced a systematic bias towards certain visions (early iterations showed several writers supporting “Single Private Project” simply because they criticized specific regulations.)

To mitigate misattribution this project breaks the visions down across four unique axes to uniquely distinguish each view. Note: The IAPS paper breaks the visions down across only two axes (central vs distributed x private vs government) but to help the LLMs more cleanly distinguish between visions this project added Regulatory Intensity and Coalition size as well.

The four axes, and the exact statement each one is scored against:

• Concentration — “AI development should be concentrated in a single dominant organization or project, rather than remaining distributed and competitive across many independent developers.”
• Control — “AI development should be controlled and run by government or public institutions, rather than by private companies.”
• Coalition breadth — “AI governance and development should involve a broad, globally inclusive coalition of all major powers, rather than being unilateral or limited to a single nation.”
• Regulatory intensity — “Private AI development should be closely and strictly regulated by government, rather than left to light-touch, minimal regulation.”

Each axis is scored using the same mechanism as a crux (same passage retrieval, same Haiku relevance/attribution/scoring call, same recency-weighted average) but on a −2 to +2 scale centered on zero.

Advocated vision: matching axis positions to named visions. Each of the 9 IAPS visions is itself mapped onto the same four axes (for example, “Single private project” sits at high concentration / low control, while “Global coordinated regulator” sits at low concentration / N/A control / high coalition breadth / high regulatory intensity). A writer's advocated alignment with a given vision is the normalized dot product of their 4-axis position against that vision's 4-axis position — the same mechanism as predicted-vision alignment above, just computed over axes instead of cruxes. If a vision doesn't take a position on one of the four axes, that axis is excluded from the comparison for that vision entirely, rather than treated as neutral.

advocated_score = 3 + 2 × [Σ(writer_axis × vision_axis) / (4 × number_of_live_axes)], displayed on the same 1–5 scale as everything else.

Cruxes and axes with no data. If a writer hasn't written enough about a given crux or axis to score at all, that dimension defaults to neutral (3/5, or 0 on the axis scale) with the lowest possible confidence.

What this project reads. This project currently only consumes data from an author's substack. Views expressed elsewhere are not currently integrated into the scoring. Only articles from the past 6 years (2020-2026) are evaluated to avoid bias from stale passages that no longer represent a writer's views.

How passages are evaluated. Every crux and vision axis is compared against a writer's full set of chunked passages using a small local embedding model (BAAI/bge-small-en-v1.5), which evaluates passages by similarity to a given crux/vision and selects the top 50. Claude Haiku then makes a yes/no relevance call for each passage and evaluates relevant passages for attribution (to check that the author isn't referencing someone else's opinion) and how much it supports the crux/vision axis on a scale of 1-5 for cruxes and −2-2 for axes.

How the average rating is calculated. Final score is calculated by weighted average according to passage recency. Passages written 5 years ago are given half the weight of newly written passages.

Specifically: recency = max(0, 1 − age_in_years / 10), and final_score = Σ(recency × passage_score) / Σ(recency).

How confidence is calculated. Confidence combines the quantity of recency weighted evidence and the consistency in scoring across that evidence. More passages generally means more confidence — but if a writer's own passages disagree sharply with each other, that pulls confidence back down even when there are a lot of them. Confidence is adjusted to account for the measurement noise found in Haiku's scoring.

Specifically: adjusted_weight = raw_weight / (1 + max(0, author_variance − 0.128)^1.5), where 0.128 is the measurement-noise floor found by repeat-scoring the same passages, and confidence = adjusted_weight / (adjusted_weight + 2). Displayed as low (adjusted_weight ≤ 0.67), unsure (between 0.67 and 6), or high (≥ 6).

Predicted vision: building the belief vector. Each writer's raw 1–5 crux scores are re-centered around the neutral midpoint, so a neutral “3” contributes nothing and stronger views in either direction contribute more.

Predicted vision: calculating alignment. The IAPS report maps each of the 9 visions to each of the 8 cruxes as supporting, opposing, or neutral. This project compares a writer's belief vector against the IAPS map by taking a normalized dot product of the two and evaluating which vectors are best aligned. To visualize the uncertainty in this judgement the project resamples available passages 400 times to produce a distribution of how consistently a given vision wins. You can view the distribution in the Landing Chart to see how decisively a view wins relative to other competing visions.

alignment = Σ(centered_score × crux_direction) / (2 × number_of_live_cruxes), displayed on the same 1–5 scale as everything else via displayed_score = 3 + 2 × alignment.

Advocated vision: the four axes. Grading each vision independently introduced significant inaccuracies. Different visions were held to different standards of what counted as relevant or in support which caused several relevant statements to be excluded in scoring. This error introduced a systematic bias towards certain visions (early iterations showed several writers supporting “Single Private Project” simply because they criticized specific regulations.)

To mitigate misattribution this project breaks the visions down across four unique axes to uniquely distinguish each view. Note: The IAPS paper breaks the visions down across only two axes (central vs distributed x private vs government) but to help the LLMs more cleanly distinguish between visions this project added Regulatory Intensity and Coalition size as well.

The four axes, and the exact statement each one is scored against:

• Concentration — “AI development should be concentrated in a single dominant organization or project, rather than remaining distributed and competitive across many independent developers.”
• Control — “AI development should be controlled and run by government or public institutions, rather than by private companies.”
• Coalition breadth — “AI governance and development should involve a broad, globally inclusive coalition of all major powers, rather than being unilateral or limited to a single nation.”
• Regulatory intensity — “Private AI development should be closely and strictly regulated by government, rather than left to light-touch, minimal regulation.”

Each axis is scored using the same mechanism as a crux (same passage retrieval, same Haiku relevance/attribution/scoring call, same recency-weighted average) but on a −2 to +2 scale centered on zero.

Advocated vision: matching axis positions to named visions. Each of the 9 IAPS visions is itself mapped onto the same four axes (for example, “Single private project” sits at high concentration / low control, while “Global coordinated regulator” sits at low concentration / N/A control / high coalition breadth / high regulatory intensity). A writer's advocated alignment with a given vision is the normalized dot product of their 4-axis position against that vision's 4-axis position — the same mechanism as predicted-vision alignment above, just computed over axes instead of cruxes. If a vision doesn't take a position on one of the four axes, that axis is excluded from the comparison for that vision entirely, rather than treated as neutral.

advocated_score = 3 + 2 × [Σ(writer_axis × vision_axis) / (4 × number_of_live_axes)], displayed on the same 1–5 scale as everything else.

Cruxes and axes with no data. If a writer hasn't written enough about a given crux or axis to score at all, that dimension defaults to neutral (3/5, or 0 on the axis scale) with the lowest possible confidence.

What this project reads. This project currently only consumes data from an author's substack. Views expressed elsewhere are not currently integrated into the scoring. Only articles from the past 6 years (2020-2026) are evaluated to avoid bias from stale passages that no longer represent a writer's views.

How passages are evaluated. Every crux and vision axis is compared against a writer's full set of chunked passages using a small local embedding model (BAAI/bge-small-en-v1.5), which evaluates passages by similarity to a given crux/vision and selects the top 50. Claude Haiku then makes a yes/no relevance call for each passage and evaluates relevant passages for attribution (to check that the author isn't referencing someone else's opinion) and how much it supports the crux/vision axis on a scale of 1-5 for cruxes and −2-2 for axes.

How the average rating is calculated. Final score is calculated by weighted average according to passage recency. Passages written 5 years ago are given half the weight of newly written passages.

Specifically: recency = max(0, 1 − age_in_years / 10), and final_score = Σ(recency × passage_score) / Σ(recency).

How confidence is calculated. Confidence combines the quantity of recency weighted evidence and the consistency in scoring across that evidence. More passages generally means more confidence — but if a writer's own passages disagree sharply with each other, that pulls confidence back down even when there are a lot of them. Confidence is adjusted to account for the measurement noise found in Haiku's scoring.

Specifically: adjusted_weight = raw_weight / (1 + max(0, author_variance − 0.128)^1.5), where 0.128 is the measurement-noise floor found by repeat-scoring the same passages, and confidence = adjusted_weight / (adjusted_weight + 2). Displayed as low (adjusted_weight ≤ 0.67), unsure (between 0.67 and 6), or high (≥ 6).

Predicted vision: building the belief vector. Each writer's raw 1–5 crux scores are re-centered around the neutral midpoint, so a neutral “3” contributes nothing and stronger views in either direction contribute more.

Predicted vision: calculating alignment. The IAPS report maps each of the 9 visions to each of the 8 cruxes as supporting, opposing, or neutral. This project compares a writer's belief vector against the IAPS map by taking a normalized dot product of the two and evaluating which vectors are best aligned. To visualize the uncertainty in this judgement the project resamples available passages 400 times to produce a distribution of how consistently a given vision wins. You can view the distribution in the Landing Chart to see how decisively a view wins relative to other competing visions.

alignment = Σ(centered_score × crux_direction) / (2 × number_of_live_cruxes), displayed on the same 1–5 scale as everything else via displayed_score = 3 + 2 × alignment.

Advocated vision: the four axes. Grading each vision independently introduced significant inaccuracies. Different visions were held to different standards of what counted as relevant or in support which caused several relevant statements to be excluded in scoring. This error introduced a systematic bias towards certain visions (early iterations showed several writers supporting “Single Private Project” simply because they criticized specific regulations.)

To mitigate misattribution this project breaks the visions down across four unique axes to uniquely distinguish each view. Note: The IAPS paper breaks the visions down across only two axes (central vs distributed x private vs government) but to help the LLMs more cleanly distinguish between visions this project added Regulatory Intensity and Coalition size as well.

The four axes, and the exact statement each one is scored against:

• Concentration — “AI development should be concentrated in a single dominant organization or project, rather than remaining distributed and competitive across many independent developers.”
• Control — “AI development should be controlled and run by government or public institutions, rather than by private companies.”
• Coalition breadth — “AI governance and development should involve a broad, globally inclusive coalition of all major powers, rather than being unilateral or limited to a single nation.”
• Regulatory intensity — “Private AI development should be closely and strictly regulated by government, rather than left to light-touch, minimal regulation.”

Each axis is scored using the same mechanism as a crux (same passage retrieval, same Haiku relevance/attribution/scoring call, same recency-weighted average) but on a −2 to +2 scale centered on zero.

Advocated vision: matching axis positions to named visions. Each of the 9 IAPS visions is itself mapped onto the same four axes (for example, “Single private project” sits at high concentration / low control, while “Global coordinated regulator” sits at low concentration / N/A control / high coalition breadth / high regulatory intensity). A writer's advocated alignment with a given vision is the normalized dot product of their 4-axis position against that vision's 4-axis position — the same mechanism as predicted-vision alignment above, just computed over axes instead of cruxes. If a vision doesn't take a position on one of the four axes, that axis is excluded from the comparison for that vision entirely, rather than treated as neutral.

advocated_score = 3 + 2 × [Σ(writer_axis × vision_axis) / (4 × number_of_live_axes)], displayed on the same 1–5 scale as everything else.

Cruxes and axes with no data. If a writer hasn't written enough about a given crux or axis to score at all, that dimension defaults to neutral (3/5, or 0 on the axis scale) with the lowest possible confidence.

What this project reads. This project currently only consumes data from an author's substack. Views expressed elsewhere are not currently integrated into the scoring. Only articles from the past 6 years (2020-2026) are evaluated to avoid bias from stale passages that no longer represent a writer's views.

How passages are evaluated. Every crux and vision axis is compared against a writer's full set of chunked passages using a small local embedding model (BAAI/bge-small-en-v1.5), which evaluates passages by similarity to a given crux/vision and selects the top 50. Claude Haiku then makes a yes/no relevance call for each passage and evaluates relevant passages for attribution (to check that the author isn't referencing someone else's opinion) and how much it supports the crux/vision axis on a scale of 1-5 for cruxes and −2-2 for axes.

How the average rating is calculated. Final score is calculated by weighted average according to passage recency. Passages written 5 years ago are given half the weight of newly written passages.

Specifically: recency = max(0, 1 − age_in_years / 10), and final_score = Σ(recency × passage_score) / Σ(recency).

How confidence is calculated. Confidence combines the quantity of recency weighted evidence and the consistency in scoring across that evidence. More passages generally means more confidence — but if a writer's own passages disagree sharply with each other, that pulls confidence back down even when there are a lot of them. Confidence is adjusted to account for the measurement noise found in Haiku's scoring.

Specifically: adjusted_weight = raw_weight / (1 + max(0, author_variance − 0.128)^1.5), where 0.128 is the measurement-noise floor found by repeat-scoring the same passages, and confidence = adjusted_weight / (adjusted_weight + 2). Displayed as low (adjusted_weight ≤ 0.67), unsure (between 0.67 and 6), or high (≥ 6).

Predicted vision: building the belief vector. Each writer's raw 1–5 crux scores are re-centered around the neutral midpoint, so a neutral “3” contributes nothing and stronger views in either direction contribute more.

Predicted vision: calculating alignment. The IAPS report maps each of the 9 visions to each of the 8 cruxes as supporting, opposing, or neutral. This project compares a writer's belief vector against the IAPS map by taking a normalized dot product of the two and evaluating which vectors are best aligned. To visualize the uncertainty in this judgement the project resamples available passages 400 times to produce a distribution of how consistently a given vision wins. You can view the distribution in the Landing Chart to see how decisively a view wins relative to other competing visions.

alignment = Σ(centered_score × crux_direction) / (2 × number_of_live_cruxes), displayed on the same 1–5 scale as everything else via displayed_score = 3 + 2 × alignment.

Advocated vision: the four axes. Grading each vision independently introduced significant inaccuracies. Different visions were held to different standards of what counted as relevant or in support which caused several relevant statements to be excluded in scoring. This error introduced a systematic bias towards certain visions (early iterations showed several writers supporting “Single Private Project” simply because they criticized specific regulations.)

To mitigate misattribution this project breaks the visions down across four unique axes to uniquely distinguish each view. Note: The IAPS paper breaks the visions down across only two axes (central vs distributed x private vs government) but to help the LLMs more cleanly distinguish between visions this project added Regulatory Intensity and Coalition size as well.

The four axes, and the exact statement each one is scored against:

• Concentration — “AI development should be concentrated in a single dominant organization or project, rather than remaining distributed and competitive across many independent developers.”
• Control — “AI development should be controlled and run by government or public institutions, rather than by private companies.”
• Coalition breadth — “AI governance and development should involve a broad, globally inclusive coalition of all major powers, rather than being unilateral or limited to a single nation.”
• Regulatory intensity — “Private AI development should be closely and strictly regulated by government, rather than left to light-touch, minimal regulation.”

Each axis is scored using the same mechanism as a crux (same passage retrieval, same Haiku relevance/attribution/scoring call, same recency-weighted average) but on a −2 to +2 scale centered on zero.

Advocated vision: matching axis positions to named visions. Each of the 9 IAPS visions is itself mapped onto the same four axes (for example, “Single private project” sits at high concentration / low control, while “Global coordinated regulator” sits at low concentration / N/A control / high coalition breadth / high regulatory intensity). A writer's advocated alignment with a given vision is the normalized dot product of their 4-axis position against that vision's 4-axis position — the same mechanism as predicted-vision alignment above, just computed over axes instead of cruxes. If a vision doesn't take a position on one of the four axes, that axis is excluded from the comparison for that vision entirely, rather than treated as neutral.

advocated_score = 3 + 2 × [Σ(writer_axis × vision_axis) / (4 × number_of_live_axes)], displayed on the same 1–5 scale as everything else.

Cruxes and axes with no data. If a writer hasn't written enough about a given crux or axis to score at all, that dimension defaults to neutral (3/5, or 0 on the axis scale) with the lowest possible confidence.

What this project reads. This project currently only consumes data from an author's substack. Views expressed elsewhere are not currently integrated into the scoring. Only articles from the past 6 years (2020-2026) are evaluated to avoid bias from stale passages that no longer represent a writer's views.

How passages are evaluated. Every crux and vision axis is compared against a writer's full set of chunked passages using a small local embedding model (BAAI/bge-small-en-v1.5), which evaluates passages by similarity to a given crux/vision and selects the top 50. Claude Haiku then makes a yes/no relevance call for each passage and evaluates relevant passages for attribution (to check that the author isn't referencing someone else's opinion) and how much it supports the crux/vision axis on a scale of 1-5 for cruxes and −2-2 for axes.

How the average rating is calculated. Final score is calculated by weighted average according to passage recency. Passages written 5 years ago are given half the weight of newly written passages.

Specifically: recency = max(0, 1 − age_in_years / 10), and final_score = Σ(recency × passage_score) / Σ(recency).

How confidence is calculated. Confidence combines the quantity of recency weighted evidence and the consistency in scoring across that evidence. More passages generally means more confidence — but if a writer's own passages disagree sharply with each other, that pulls confidence back down even when there are a lot of them. Confidence is adjusted to account for the measurement noise found in Haiku's scoring.

Specifically: adjusted_weight = raw_weight / (1 + max(0, author_variance − 0.128)^1.5), where 0.128 is the measurement-noise floor found by repeat-scoring the same passages, and confidence = adjusted_weight / (adjusted_weight + 2). Displayed as low (adjusted_weight ≤ 0.67), unsure (between 0.67 and 6), or high (≥ 6).

Predicted vision: building the belief vector. Each writer's raw 1–5 crux scores are re-centered around the neutral midpoint, so a neutral “3” contributes nothing and stronger views in either direction contribute more.

Predicted vision: calculating alignment. The IAPS report maps each of the 9 visions to each of the 8 cruxes as supporting, opposing, or neutral. This project compares a writer's belief vector against the IAPS map by taking a normalized dot product of the two and evaluating which vectors are best aligned. To visualize the uncertainty in this judgement the project resamples available passages 400 times to produce a distribution of how consistently a given vision wins. You can view the distribution in the Landing Chart to see how decisively a view wins relative to other competing visions.

alignment = Σ(centered_score × crux_direction) / (2 × number_of_live_cruxes), displayed on the same 1–5 scale as everything else via displayed_score = 3 + 2 × alignment.

Advocated vision: the four axes. Grading each vision independently introduced significant inaccuracies. Different visions were held to different standards of what counted as relevant or in support which caused several relevant statements to be excluded in scoring. This error introduced a systematic bias towards certain visions (early iterations showed several writers supporting “Single Private Project” simply because they criticized specific regulations.)

To mitigate misattribution this project breaks the visions down across four unique axes to uniquely distinguish each view. Note: The IAPS paper breaks the visions down across only two axes (central vs distributed x private vs government) but to help the LLMs more cleanly distinguish between visions this project added Regulatory Intensity and Coalition size as well.

The four axes, and the exact statement each one is scored against:

• Concentration — “AI development should be concentrated in a single dominant organization or project, rather than remaining distributed and competitive across many independent developers.”
• Control — “AI development should be controlled and run by government or public institutions, rather than by private companies.”
• Coalition breadth — “AI governance and development should involve a broad, globally inclusive coalition of all major powers, rather than being unilateral or limited to a single nation.”
• Regulatory intensity — “Private AI development should be closely and strictly regulated by government, rather than left to light-touch, minimal regulation.”

Each axis is scored using the same mechanism as a crux (same passage retrieval, same Haiku relevance/attribution/scoring call, same recency-weighted average) but on a −2 to +2 scale centered on zero.

Advocated vision: matching axis positions to named visions. Each of the 9 IAPS visions is itself mapped onto the same four axes (for example, “Single private project” sits at high concentration / low control, while “Global coordinated regulator” sits at low concentration / N/A control / high coalition breadth / high regulatory intensity). A writer's advocated alignment with a given vision is the normalized dot product of their 4-axis position against that vision's 4-axis position — the same mechanism as predicted-vision alignment above, just computed over axes instead of cruxes. If a vision doesn't take a position on one of the four axes, that axis is excluded from the comparison for that vision entirely, rather than treated as neutral.

advocated_score = 3 + 2 × [Σ(writer_axis × vision_axis) / (4 × number_of_live_axes)], displayed on the same 1–5 scale as everything else.

Cruxes and axes with no data. If a writer hasn't written enough about a given crux or axis to score at all, that dimension defaults to neutral (3/5, or 0 on the axis scale) with the lowest possible confidence.

What this project reads. This project currently only consumes data from an author's substack. Views expressed elsewhere are not currently integrated into the scoring. Only articles from the past 6 years (2020-2026) are evaluated to avoid bias from stale passages that no longer represent a writer's views.

How passages are evaluated. Every crux and vision axis is compared against a writer's full set of chunked passages using a small local embedding model (BAAI/bge-small-en-v1.5), which evaluates passages by similarity to a given crux/vision and selects the top 50. Claude Haiku then makes a yes/no relevance call for each passage and evaluates relevant passages for attribution (to check that the author isn't referencing someone else's opinion) and how much it supports the crux/vision axis on a scale of 1-5 for cruxes and −2-2 for axes.

How the average rating is calculated. Final score is calculated by weighted average according to passage recency. Passages written 5 years ago are given half the weight of newly written passages.

Specifically: recency = max(0, 1 − age_in_years / 10), and final_score = Σ(recency × passage_score) / Σ(recency).

How confidence is calculated. Confidence combines the quantity of recency weighted evidence and the consistency in scoring across that evidence. More passages generally means more confidence — but if a writer's own passages disagree sharply with each other, that pulls confidence back down even when there are a lot of them. Confidence is adjusted to account for the measurement noise found in Haiku's scoring.

Specifically: adjusted_weight = raw_weight / (1 + max(0, author_variance − 0.128)^1.5), where 0.128 is the measurement-noise floor found by repeat-scoring the same passages, and confidence = adjusted_weight / (adjusted_weight + 2). Displayed as low (adjusted_weight ≤ 0.67), unsure (between 0.67 and 6), or high (≥ 6).

Predicted vision: building the belief vector. Each writer's raw 1–5 crux scores are re-centered around the neutral midpoint, so a neutral “3” contributes nothing and stronger views in either direction contribute more.

Predicted vision: calculating alignment. The IAPS report maps each of the 9 visions to each of the 8 cruxes as supporting, opposing, or neutral. This project compares a writer's belief vector against the IAPS map by taking a normalized dot product of the two and evaluating which vectors are best aligned. To visualize the uncertainty in this judgement the project resamples available passages 400 times to produce a distribution of how consistently a given vision wins. You can view the distribution in the Landing Chart to see how decisively a view wins relative to other competing visions.

alignment = Σ(centered_score × crux_direction) / (2 × number_of_live_cruxes), displayed on the same 1–5 scale as everything else via displayed_score = 3 + 2 × alignment.

Advocated vision: the four axes. Grading each vision independently introduced significant inaccuracies. Different visions were held to different standards of what counted as relevant or in support which caused several relevant statements to be excluded in scoring. This error introduced a systematic bias towards certain visions (early iterations showed several writers supporting “Single Private Project” simply because they criticized specific regulations.)

To mitigate misattribution this project breaks the visions down across four unique axes to uniquely distinguish each view. Note: The IAPS paper breaks the visions down across only two axes (central vs distributed x private vs government) but to help the LLMs more cleanly distinguish between visions this project added Regulatory Intensity and Coalition size as well.

The four axes, and the exact statement each one is scored against:

• Concentration — “AI development should be concentrated in a single dominant organization or project, rather than remaining distributed and competitive across many independent developers.”
• Control — “AI development should be controlled and run by government or public institutions, rather than by private companies.”
• Coalition breadth — “AI governance and development should involve a broad, globally inclusive coalition of all major powers, rather than being unilateral or limited to a single nation.”
• Regulatory intensity — “Private AI development should be closely and strictly regulated by government, rather than left to light-touch, minimal regulation.”

Each axis is scored using the same mechanism as a crux (same passage retrieval, same Haiku relevance/attribution/scoring call, same recency-weighted average) but on a −2 to +2 scale centered on zero.

Advocated vision: matching axis positions to named visions. Each of the 9 IAPS visions is itself mapped onto the same four axes (for example, “Single private project” sits at high concentration / low control, while “Global coordinated regulator” sits at low concentration / N/A control / high coalition breadth / high regulatory intensity). A writer's advocated alignment with a given vision is the normalized dot product of their 4-axis position against that vision's 4-axis position — the same mechanism as predicted-vision alignment above, just computed over axes instead of cruxes. If a vision doesn't take a position on one of the four axes, that axis is excluded from the comparison for that vision entirely, rather than treated as neutral.

advocated_score = 3 + 2 × [Σ(writer_axis × vision_axis) / (4 × number_of_live_axes)], displayed on the same 1–5 scale as everything else.

Cruxes and axes with no data. If a writer hasn't written enough about a given crux or axis to score at all, that dimension defaults to neutral (3/5, or 0 on the axis scale) with the lowest possible confidence.

What this project reads. This project currently only consumes data from an author's substack. Views expressed elsewhere are not currently integrated into the scoring. Only articles from the past 6 years (2020-2026) are evaluated to avoid bias from stale passages that no longer represent a writer's views.

How passages are evaluated. Every crux and vision axis is compared against a writer's full set of chunked passages using a small local embedding model (BAAI/bge-small-en-v1.5), which evaluates passages by similarity to a given crux/vision and selects the top 50. Claude Haiku then makes a yes/no relevance call for each passage and evaluates relevant passages for attribution (to check that the author isn't referencing someone else's opinion) and how much it supports the crux/vision axis on a scale of 1-5 for cruxes and −2-2 for axes.

How the average rating is calculated. Final score is calculated by weighted average according to passage recency. Passages written 5 years ago are given half the weight of newly written passages.

Specifically: recency = max(0, 1 − age_in_years / 10), and final_score = Σ(recency × passage_score) / Σ(recency).

How confidence is calculated. Confidence combines the quantity of recency weighted evidence and the consistency in scoring across that evidence. More passages generally means more confidence — but if a writer's own passages disagree sharply with each other, that pulls confidence back down even when there are a lot of them. Confidence is adjusted to account for the measurement noise found in Haiku's scoring.

Specifically: adjusted_weight = raw_weight / (1 + max(0, author_variance − 0.128)^1.5), where 0.128 is the measurement-noise floor found by repeat-scoring the same passages, and confidence = adjusted_weight / (adjusted_weight + 2). Displayed as low (adjusted_weight ≤ 0.67), unsure (between 0.67 and 6), or high (≥ 6).

Predicted vision: building the belief vector. Each writer's raw 1–5 crux scores are re-centered around the neutral midpoint, so a neutral “3” contributes nothing and stronger views in either direction contribute more.

Predicted vision: calculating alignment. The IAPS report maps each of the 9 visions to each of the 8 cruxes as supporting, opposing, or neutral. This project compares a writer's belief vector against the IAPS map by taking a normalized dot product of the two and evaluating which vectors are best aligned. To visualize the uncertainty in this judgement the project resamples available passages 400 times to produce a distribution of how consistently a given vision wins. You can view the distribution in the Landing Chart to see how decisively a view wins relative to other competing visions.

alignment = Σ(centered_score × crux_direction) / (2 × number_of_live_cruxes), displayed on the same 1–5 scale as everything else via displayed_score = 3 + 2 × alignment.

Advocated vision: the four axes. Grading each vision independently introduced significant inaccuracies. Different visions were held to different standards of what counted as relevant or in support which caused several relevant statements to be excluded in scoring. This error introduced a systematic bias towards certain visions (early iterations showed several writers supporting “Single Private Project” simply because they criticized specific regulations.)

To mitigate misattribution this project breaks the visions down across four unique axes to uniquely distinguish each view. Note: The IAPS paper breaks the visions down across only two axes (central vs distributed x private vs government) but to help the LLMs more cleanly distinguish between visions this project added Regulatory Intensity and Coalition size as well.

The four axes, and the exact statement each one is scored against:

• Concentration — “AI development should be concentrated in a single dominant organization or project, rather than remaining distributed and competitive across many independent developers.”
• Control — “AI development should be controlled and run by government or public institutions, rather than by private companies.”
• Coalition breadth — “AI governance and development should involve a broad, globally inclusive coalition of all major powers, rather than being unilateral or limited to a single nation.”
• Regulatory intensity — “Private AI development should be closely and strictly regulated by government, rather than left to light-touch, minimal regulation.”

Each axis is scored using the same mechanism as a crux (same passage retrieval, same Haiku relevance/attribution/scoring call, same recency-weighted average) but on a −2 to +2 scale centered on zero.

Advocated vision: matching axis positions to named visions. Each of the 9 IAPS visions is itself mapped onto the same four axes (for example, “Single private project” sits at high concentration / low control, while “Global coordinated regulator” sits at low concentration / N/A control / high coalition breadth / high regulatory intensity). A writer's advocated alignment with a given vision is the normalized dot product of their 4-axis position against that vision's 4-axis position — the same mechanism as predicted-vision alignment above, just computed over axes instead of cruxes. If a vision doesn't take a position on one of the four axes, that axis is excluded from the comparison for that vision entirely, rather than treated as neutral.

advocated_score = 3 + 2 × [Σ(writer_axis × vision_axis) / (4 × number_of_live_axes)], displayed on the same 1–5 scale as everything else.

Cruxes and axes with no data. If a writer hasn't written enough about a given crux or axis to score at all, that dimension defaults to neutral (3/5, or 0 on the axis scale) with the lowest possible confidence.

What this project reads. This project currently only consumes data from an author's substack. Views expressed elsewhere are not currently integrated into the scoring. Only articles from the past 6 years (2020-2026) are evaluated to avoid bias from stale passages that no longer represent a writer's views.

How passages are evaluated. Every crux and vision axis is compared against a writer's full set of chunked passages using a small local embedding model (BAAI/bge-small-en-v1.5), which evaluates passages by similarity to a given crux/vision and selects the top 50. Claude Haiku then makes a yes/no relevance call for each passage and evaluates relevant passages for attribution (to check that the author isn't referencing someone else's opinion) and how much it supports the crux/vision axis on a scale of 1-5 for cruxes and −2-2 for axes.

How the average rating is calculated. Final score is calculated by weighted average according to passage recency. Passages written 5 years ago are given half the weight of newly written passages.

Specifically: recency = max(0, 1 − age_in_years / 10), and final_score = Σ(recency × passage_score) / Σ(recency).

How confidence is calculated. Confidence combines the quantity of recency weighted evidence and the consistency in scoring across that evidence. More passages generally means more confidence — but if a writer's own passages disagree sharply with each other, that pulls confidence back down even when there are a lot of them. Confidence is adjusted to account for the measurement noise found in Haiku's scoring.

Specifically: adjusted_weight = raw_weight / (1 + max(0, author_variance − 0.128)^1.5), where 0.128 is the measurement-noise floor found by repeat-scoring the same passages, and confidence = adjusted_weight / (adjusted_weight + 2). Displayed as low (adjusted_weight ≤ 0.67), unsure (between 0.67 and 6), or high (≥ 6).

Predicted vision: building the belief vector. Each writer's raw 1–5 crux scores are re-centered around the neutral midpoint, so a neutral “3” contributes nothing and stronger views in either direction contribute more.

Predicted vision: calculating alignment. The IAPS report maps each of the 9 visions to each of the 8 cruxes as supporting, opposing, or neutral. This project compares a writer's belief vector against the IAPS map by taking a normalized dot product of the two and evaluating which vectors are best aligned. To visualize the uncertainty in this judgement the project resamples available passages 400 times to produce a distribution of how consistently a given vision wins. You can view the distribution in the Landing Chart to see how decisively a view wins relative to other competing visions.

alignment = Σ(centered_score × crux_direction) / (2 × number_of_live_cruxes), displayed on the same 1–5 scale as everything else via displayed_score = 3 + 2 × alignment.

Advocated vision: the four axes. Grading each vision independently introduced significant inaccuracies. Different visions were held to different standards of what counted as relevant or in support which caused several relevant statements to be excluded in scoring. This error introduced a systematic bias towards certain visions (early iterations showed several writers supporting “Single Private Project” simply because they criticized specific regulations.)

To mitigate misattribution this project breaks the visions down across four unique axes to uniquely distinguish each view. Note: The IAPS paper breaks the visions down across only two axes (central vs distributed x private vs government) but to help the LLMs more cleanly distinguish between visions this project added Regulatory Intensity and Coalition size as well.

The four axes, and the exact statement each one is scored against:

• Concentration — “AI development should be concentrated in a single dominant organization or project, rather than remaining distributed and competitive across many independent developers.”
• Control — “AI development should be controlled and run by government or public institutions, rather than by private companies.”
• Coalition breadth — “AI governance and development should involve a broad, globally inclusive coalition of all major powers, rather than being unilateral or limited to a single nation.”
• Regulatory intensity — “Private AI development should be closely and strictly regulated by government, rather than left to light-touch, minimal regulation.”

Each axis is scored using the same mechanism as a crux (same passage retrieval, same Haiku relevance/attribution/scoring call, same recency-weighted average) but on a −2 to +2 scale centered on zero.

Advocated vision: matching axis positions to named visions. Each of the 9 IAPS visions is itself mapped onto the same four axes (for example, “Single private project” sits at high concentration / low control, while “Global coordinated regulator” sits at low concentration / N/A control / high coalition breadth / high regulatory intensity). A writer's advocated alignment with a given vision is the normalized dot product of their 4-axis position against that vision's 4-axis position — the same mechanism as predicted-vision alignment above, just computed over axes instead of cruxes. If a vision doesn't take a position on one of the four axes, that axis is excluded from the comparison for that vision entirely, rather than treated as neutral.

advocated_score = 3 + 2 × [Σ(writer_axis × vision_axis) / (4 × number_of_live_axes)], displayed on the same 1–5 scale as everything else.

Cruxes and axes with no data. If a writer hasn't written enough about a given crux or axis to score at all, that dimension defaults to neutral (3/5, or 0 on the axis scale) with the lowest possible confidence.