Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T18:58:12.233861Z
Paper Citation Record · LEDGER
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
As of 23 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 7 inbound Pith citation observations for arXiv:2507.07341.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-15T14:17:57.147946Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-02T22:57:25.939777Z
Reference resolution
24 of 24 outbound references displayed
- verified exact0
- verified fuzzy16
- unresolved7
- parse uncertain1
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation fe69d402-7470-4b7d-9933-a0db35ac2131 · outbound
This paper cites an unresolved cited work.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment Unresolved cited work
Reference 1
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:58:12.423612Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 8a43ddb7-cfd5-456e-94af-d96a72e563cd · outbound
This paper cites , n− 1}, and computes s ← re mod n, where e = 2t is a tower of repeated squarings (i.e., t squarings of r).
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment , n− 1}, and computes s ← re mod n, where e = 2t is a tower of repeated squarings (i.e., t squarings of r)
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.415545Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 5baf7d0c-44c7-4ca3-962c-9eeeb3c24b6e · outbound
This paper cites Returns (Z, s).
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment Returns (Z, s)
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.408136Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation acd774a3-3239-41e0-b6f7-52350fcf5806 · outbound
This paper cites Note that Sol computes s using t repeated squarings, each of which is inexpensive, but the full process requires Θ(t) sequential steps.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment Note that Sol computes s using t repeated squarings, each of which is inexpensive, but the full process requires Θ(t) sequential steps
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.400530Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 8b291c00-dcc9-4a85-b140-1c913a702369 · outbound
This paper cites an unresolved cited work.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment Unresolved cited work
Reference 6
- Resolution
- parse uncertain
- raw_fallback, observed 2026-08-06T18:58:12.392727Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation d46fd4b8-f49b-4033-bc75-73fee52d2e27 · outbound
This paper cites , zi−1, before the if statement (step 8 of Algorithm 1) is executed, the distribution of q is uniform in [k].
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment , zi−1, before the if statement (step 8 of Algorithm 1) is executed, the distribution of q is uniform in [k]
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.385979Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation fad5a9c2-f919-47d0-9e85-9c97058d7ce3 · outbound
This paper cites an unresolved cited work.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment Unresolved cited work
Reference 8
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:58:12.378541Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation ecaaba91-1c55-41ff-a4ef-154395ac7631 · outbound
This paper cites an unresolved cited work.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:58:12.371479Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation dfa16466-05f2-49f2-be26-90984e80612c · outbound
This paper cites threshold randomness.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment threshold randomness
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.363827Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 691dccf3-bebd-4577-a6dc-eb29da9853b2 · outbound
This paper cites With probability 1 − λ−Ω(1) over z ← G the distributions M ′(z) and M (z) are equal.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment With probability 1 − λ−Ω(1) over z ← G the distributions M ′(z) and M (z) are equal
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.350294Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 1e515cec-d1a8-4e04-8766-9ad6dc5e8502 · outbound
This paper cites remember.
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.342434Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation ff162a5c-ffdc-4ecc-8778-200eb4f33e10 · outbound
This paper cites With all but negligible in λ probability over z ← G the distributions M ′(z) and M (z) are equal.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment With all but negligible in λ probability over z ← G the distributions M ′(z) and M (z) are equal
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.336253Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 9b583590-d2fd-4471-bcc5-214846fbcfc9 · outbound
This paper cites an unresolved cited work.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment Unresolved cited work
Reference 16
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:58:12.328507Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation cb9a0965-1034-4335-b85e-7193e0c32ff0 · outbound
This paper cites For every malicious prompt m ∈ SH, the following two distributions are close: {M ′(z) | z ← G′(m)} , {M (m)}.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment For every malicious prompt m ∈ SH, the following two distributions are close: {M ′(z) | z ← G′(m)} , {M (m)}
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.356904Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 8030ea81-0e17-4d5d-9be6-a7a7a7e91807 · outbound
This paper cites an unresolved cited work.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment Unresolved cited work
Reference 19
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:58:12.313074Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 77dd7ad5-381e-4cbc-8a27-e993a48fb012 · outbound
This paper cites For every malicious prompt m ∈ SH, with all but negligible in λ probability over z ← M ′(m),16 it holds that H′(z) = Ω Ez←M (m)[H(z)].
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment For every malicious prompt m ∈ SH, with all but negligible in λ probability over z ← M ′(m),16 it holds that H′(z) = Ω Ez←M (m)[H(z)]
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.306843Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation bb1bb0bc-dc53-4c78-9f22-9f5de51de429 · outbound
This paper cites With all but negligible probability in λ over z ← M ()17 H′(z) = H(z).
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment With all but negligible probability in λ over z ← M ()17 H′(z) = H(z)
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.299835Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation cd6aabf9-c86b-4db4-ba34-d1232c57496c · outbound
This paper cites running time.
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.292654Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation bd40fa10-5628-4348-bb1b-e73ff970e608 · outbound
This paper cites For every prompt-mitigation filter F running in polynomial-time with all but negligible in λ probability over z ← G′ it holds that F (z) = ⊥ or M ′(z) is harmful.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment For every prompt-mitigation filter F running in polynomial-time with all but negligible in λ probability over z ← G′ it holds that F (z) = ⊥ or M ′(z) is harmful
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.285864Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 01fc0440-95cf-4888-8da8-718ed9507b76 · outbound
This paper cites With all but negligible in λ probability over z ← G the distributions M ′(z) and M (z) are equal.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment With all but negligible in λ probability over z ← G the distributions M ′(z) and M (z) are equal
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.321567Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 02281eff-8c48-4e47-bc59-68ffce24dc43 · outbound
This paper cites For every algo- rithm running in polynomial-time the advantage in distinguishing outputs of G and G′ is negligible in λ.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment For every algo- rithm running in polynomial-time the advantage in distinguishing outputs of G and G′ is negligible in λ
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.278200Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 53cc2ef4-869b-4e1f-bf11-585c097852bc · outbound
This paper cites an unresolved cited work.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment Unresolved cited work
Reference 26
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:58:12.269202Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 4d45f48b-5366-48a4-ab81-8c896183cff9 · outbound
This paper cites E.4 Proof The proof requires a careful comparison of requirements of Theorem 11 and properties of watermark- ing schemes robust against classes of transformations.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment E.4 Proof The proof requires a careful comparison of requirements of Theorem 11 and properties of watermark- ing schemes robust against classes of transformations
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:58:12.261759Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 29fb1548-5629-450c-8d10-5f410caa377a · outbound
This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Reference 2000
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:58:12.164527Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation 9c73fe2c-2ab8-4d51-ac48-520cb5bbaebb · inbound
Spore: Efficient and Training-Free Privacy Extraction Attack on LLMs via Inference-Time Hybrid Probing cites this paper.
Spore: Efficient and Training-Free Privacy Extraction Attack on LLMs via Inference-Time Hybrid Probing On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T21:16:19.975892Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 7889dbcd-fc97-4143-a227-790564200922 · inbound
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning cites this paper.
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
Reference 113
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T21:52:48.244988Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 857653ea-e86a-4bc1-a68b-5f351d09e5d4 · inbound
Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense cites this paper.
Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-01T19:36:08.905765Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 247c9dce-fb0c-4caa-a103-4b422e058c2e · inbound
Emergence World: A Platform for Evaluating Long-Horizon Multi-Agent Autonomy cites this paper.
Emergence World: A Platform for Evaluating Long-Horizon Multi-Agent Autonomy On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
Reference 69
- Resolution
- verified exact
- arxiv_id, observed 2026-07-02T22:57:25.941483Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation a826c4d7-1022-49fe-b3e6-90123e186a9c · inbound
On the Limits of Support-Preserving Alignment and Bounded Filtering cites this paper.
On the Limits of Support-Preserving Alignment and Bounded Filtering On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T09:19:34.923841Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2f80ecdc-dcd6-4e20-bd07-30b267bc2e16 · inbound
Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs cites this paper.
Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-07-31T22:25:22.203096Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bf092eaf-f1b5-442a-9d68-aa8c9233828e · inbound
Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning cites this paper.
Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
Reference 184
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T14:17:57.147946Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.