Paper Citation Record · LEDGER

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees

As of 13 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 2 inbound Pith citation observations for arXiv:2603.08761.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2603.08761 v2

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-15T13:02:17.646650Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-12T11:23:07.646178Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-01T16:35:50.616569Z

Reference resolution

26 of 26 outbound references displayed

verified exact0
verified fuzzy0
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6037aec7-6571-45d7-9c67-62fbfa86aa93 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Constitutional AI: Harmlessness from AI Feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00ddaf68-7c5c-4235-bd32-b52b9edfd365 · outbound

This paper cites Interpreting Blackbox Models via Model Extraction.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Interpreting Blackbox Models via Model Extraction

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2a5a7a8-53f2-4459-9fbc-9adaa9ef969c · outbound

This paper cites On the computational power of transformers and its implications in sequence modelling.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees On the computational power of transformers and its implications in sequence modelling

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aef6ed17-c87f-4952-b6ac-b017fb495070 · outbound

This paper cites an unresolved cited work.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d1a708c-ab56-415f-b365-29c858dd3b0c · outbound

This paper cites F., Leike, J., Brown, T., et al.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees F., Leike, J., Brown, T., et al

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f36c983-2c63-4844-bc9a-7cd7c84ecb63 · outbound

This paper cites Scal- ing laws for reward model overoptimisation.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Scal- ing laws for reward model overoptimisation

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d147be2-aa8c-474e-9ad8-d2155af40def · outbound

This paper cites Cambridge University Press,.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Cambridge University Press,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a422284-5d09-460c-adaf-9e773cf006a9 · outbound

This paper cites Safety verification of deep neural networks.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Safety verification of deep neural networks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b0d41ef-2fd0-48e4-8bf1-7063747d6770 · outbound

This paper cites L., et al.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees L., et al

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0749642a-33ea-459b-86d5-4bbd00cc0000 · outbound

This paper cites Catastrophic Goodhart: Regularizing RLHF with KL divergence does not mitigate heavy-tailed re- ward misspecification.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Catastrophic Goodhart: Regularizing RLHF with KL divergence does not mitigate heavy-tailed re- ward misspecification

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4066ac89-e194-43f5-8c9f-01f71a998268 · outbound

This paper cites and Wang, Y.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees and Wang, Y

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 367e1092-7f46-44d8-95d5-01ba4aeb3956 · outbound

This paper cites and Sabharwal, A.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees and Sabharwal, A

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26247e10-3b07-471c-99c7-0bc58a73eaf1 · outbound

This paper cites F., Pascanu, R., Cho, K., and Bengio, Y.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees F., Pascanu, R., Cho, K., and Bengio, Y

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fda8c6f1-4643-411e-83ee-3774ca88b5ef · outbound

This paper cites Training language models to follow instructions with human feedback.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Training language models to follow instructions with human feedback

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73726faf-4801-42c1-8cb4-7f0f7fde8002 · outbound

This paper cites Attention is Turing-complete.JMLR, 22(75):1–35,.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Attention is Turing-complete.JMLR, 22(75):1–35,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c997dc31-0632-4b51-b832-d04c147bf1e5 · outbound

This paper cites Direct preference optimisation: Your lan- guage model is secretly a reward model.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Direct preference optimisation: Your lan- guage model is secretly a reward model

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 839ad3f8-c814-4f45-b94d-3acd905ae3f0 · outbound

This paper cites an unresolved cited work.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dfc9893-3fe5-40b6-928f-1cb8dd32b0da · outbound

This paper cites Defining and characterising reward hacking.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Defining and characterising reward hacking

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0cde0c2-f317-4aa4-8c95-a29c7b97496a · outbound

This paper cites an unresolved cited work.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5feb9ec1-53ce-4e46-9472-4c06e82e0d9c · outbound

This paper cites Beta- CROWN: Efficient bound propagation with per-neuron split constraints for complete and incomplete neural network verification.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Beta- CROWN: Efficient bound propagation with per-neuron split constraints for complete and incomplete neural network verification

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b549d1-ef8f-4513-9a0a-59f32c18f1ec · outbound

This paper cites GPT-4 Technical Report.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees GPT-4 Technical Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fcfbfa2-35ac-4556-b63c-d8d2fe3ebcc8 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Gemini: A Family of Highly Capable Multimodal Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82315b21-319d-46d7-8aae-3969ddbc388c · outbound

This paper cites and Lynch, N.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees and Lynch, N

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63eb35eb-790d-495b-b351-9eeb3d177c39 · outbound

This paper cites Cambridge University Press,.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees Cambridge University Press,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d01331c-d1cd-40bd-af5a-c9fadcb9e31e · outbound

This paper cites and Cousot, R.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees and Cousot, R

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61152d4e-1b63-42c7-8b67-a64d9c477d17 · outbound

This paper cites On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models.

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-15T13:02:17.646650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 8bea21c5-cd11-4455-a35f-aa16af95a4a3 · inbound

The Unverifiability of Artificial General Intelligence (AGI) Alignment, Static and Dynamic: From Trakhtenbrot's Wall to the Safety-Generality Tension cites this paper.

The Unverifiability of Artificial General Intelligence (AGI) Alignment, Static and Dynamic: From Trakhtenbrot's Wall to the Safety-Generality Tension No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-01T16:35:50.617796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation edf234ba-823a-4c23-a09a-6f83f31e5342 · inbound

The Unverifiability of Artificial General Intelligence (AGI) Alignment, Static and Dynamic: From Trakhtenbrot's Wall to the Safety-Generality Tension cites this paper.

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-12T11:23:07.646178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.