Pith. sign in

Paper Citation Record · LEDGER

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness

As of 17 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2607.08046.

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

pith.paper-citation-record.v1
2607.08046 v1

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-10T01:09:53.133146Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

20 of 20 outbound references displayed

  • verified exact4
  • verified fuzzy6
  • unresolved1
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch9

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 143c7272-25c5-46e9-af0c-569334f0e823 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness Understanding intermediate layers using linear classifier probes

Reference 1

Resolution
verified exact
local_arxiv, observed 2026-07-10T01:16:41.378979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:3092a025ae66cee19f2b5d185e2c103154f080382e7e6e41ee380dfb42433fcf

Observation 2a7a1a1f-1b9d-4428-a9a0-368112909fad · outbound

This paper cites Probing Classifiers: Promises, Shortcomings, and Advances.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness Probing Classifiers: Promises, Shortcomings, and Advances

Reference 2

Resolution
verified exact
local_arxiv, observed 2026-07-10T01:16:41.367762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:4c8f1122d6c96f5e2b465300ca2fb01cd19bfe012d66ab4ef3f7a085d1f32374

Observation 9b84128e-f349-4870-acd8-9ba961f81d4d · outbound

This paper cites Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought

Reference 3

Resolution
metadata mismatch
local_arxiv, observed 2026-07-10T01:16:41.376385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:c9f40be6392fb8d7415004666421822975b791d6fb61a400e5ef00de2f7c323a

Observation c5b067d3-60d0-4d19-b79d-af339a284728 · outbound

This paper cites arXiv preprint arXiv:2512.25070 , year =.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness arXiv preprint arXiv:2512.25070 , year =

Reference 4

Resolution
metadata mismatch
arxiv_id, observed 2026-07-10T01:16:41.376309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:671a0e353df0dd6ed7690ce59741b79e8f98cf57338982cff9a0e0151adcb1f0

Observation e13225bf-52b7-4951-86b6-efb0cd9277f5 · outbound

This paper cites Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty

Reference 5

Resolution
metadata mismatch
local_arxiv, observed 2026-07-10T01:16:41.379275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:84a69fdd81fbb32ab8be5e248c9a3d5e909b0a0dcc124163936ab94c772af657

Observation 5a3c86a3-1461-44b2-94eb-ab31af16f2cd · outbound

This paper cites GLM Team and Zhipu AI.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness GLM Team and Zhipu AI

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-07-10T01:26:44.054198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:478414e98aa96d390eb96d2073aa57875a0e274c99b103fc657e551d13d6d4c9

Observation 4cca3f23-51ea-48fd-a970-c86c7f6b0152 · outbound

This paper cites FutureSim: Replaying World Events to Evaluate Adaptive Agents.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness FutureSim: Replaying World Events to Evaluate Adaptive Agents

Reference 7

Resolution
verified exact
local_arxiv, observed 2026-07-10T01:16:41.387127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:85bb682304a1c67030925d31f1d9015989f27e0374f68f1929702c8d11ecd125

Observation af63ff8f-3371-476f-a5dc-d1364c579a8c · outbound

This paper cites FutureSim: Replaying World Events to Evaluate Adaptive Agents.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness FutureSim: Replaying World Events to Evaluate Adaptive Agents

Reference 8

Resolution
metadata mismatch
local_arxiv, observed 2026-07-10T01:16:40.475691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:e4181d9d368ed4faf5f7e17da1cd503386624b6321dcf4592d7461631ca2141f

Observation b81a63c5-82ce-436a-b1d5-444bd4af4357 · outbound

This paper cites A Survey on LLM-as-a-Judge.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness A Survey on LLM-as-a-Judge

Reference 9

Resolution
metadata mismatch
local_arxiv, observed 2026-07-10T01:16:41.389783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:ec5ca599e8a403d6afc35bf801e988ad1ab33cbb7ff002c37ef382de70d69f41

Observation c7767332-5b37-456c-8dae-ea9c97ab7d1f · outbound

This paper cites Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth

Reference 10

Resolution
metadata mismatch
local_arxiv, observed 2026-07-10T01:16:41.384847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:44d6879e6714a22deec79386cb86bf9133024e21359a26fc056b88fc556c0ea1

Observation c021c0d0-14f8-453c-a211-74667a28abda · outbound

This paper cites Toni J.B.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness Toni J.B

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-07-10T01:26:44.056018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:c59b622d4431d11eed1ebd101e6ff8c19c939644559302b17c84c0242b2b24f5

Observation c803a02a-88fb-4a55-b227-0ddb9ac60c19 · outbound

This paper cites URLhttps://aclanthology.org/2024.emnlp-main.842/.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness URLhttps://aclanthology.org/2024.emnlp-main.842/

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-07-10T01:26:44.057843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:bbbbda5080093937f2d09e1ca775a693d51784e1eb93bc460c9f9dcec9fb35c8

Observation 9970aff0-bf3a-46fb-9b38-86896c95b3e6 · outbound

This paper cites Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards

Reference 13

Resolution
verified exact
local_arxiv, observed 2026-07-10T01:16:41.381696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:53aabd62ad60f4994ddacc8360e652b1adbc1ad0e35c9fbad204fdc443b3ae54

Observation 08f1d861-37fc-41fd-ab95-59282066a9cd · outbound

This paper cites T., Dooms, T., Yamamoto, R., Meehl, J., Molnar, C., Bissell, M., Hazra, D., Fang, C., Nguyen, N., Anderson, M., Osborne, C., Duffy, P., Toomey, B., Klee, E., Myasoedova, E., Ryu, A.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness T., Dooms, T., Yamamoto, R., Meehl, J., Molnar, C., Bissell, M., Hazra, D., Fang, C., Nguyen, N., Anderson, M., Osborne, C., Duffy, P., Toomey, B., Klee, E., Myasoedova, E., Ryu, A

Reference 14

Resolution
metadata mismatch
doi, observed 2026-07-10T01:16:40.477545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:ce361006af250efa32b7ec1ce9947f4bd350869af82b9f44e686301cf7aa27a3

Observation 9883e102-f572-4e45-85f1-4152eef1c7cf · outbound

This paper cites Park, Rafael Valdece Sousa Bastos, and Philip E.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness Park, Rafael Valdece Sousa Bastos, and Philip E

Reference 15

Resolution
metadata mismatch
doi, observed 2026-07-10T01:16:40.479446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:ddd41ce04b120077c4937fef55bc55b3f94b0777df0a25516a3e042312e9dda4

Observation 2831b9f5-d52f-4ceb-b674-7a9bc165cc5f · outbound

This paper cites Qwen3 Technical Report.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness Qwen3 Technical Report

Reference 16

Resolution
metadata mismatch
local_arxiv, observed 2026-07-10T01:16:41.390276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:13d83cedf06948fafbedfd5069b180eaf709c187170753cca7366839b7cf4dc4

Observation bb2c40c2-4d18-459a-8723-399a25e6e666 · outbound

This paper cites an unresolved cited work.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness Unresolved cited work

Reference 17

Resolution
unresolved
raw_fallback, observed 2026-07-10T01:26:44.050693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:dac61bb12ffb02aee3d738b1b2d1640e4c6ae522c6e7c8581e64a36b9c9383ac

Observation d887d1d6-bf7d-40fc-94d0-f146967437b3 · outbound

This paper cites Your answer will be evaluated using the BRIER SCORING RULE which is basically (- (1 - p)^2) if your answer is correct and (- 1 - p^2) if your answer is incorrect.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness Your answer will be evaluated using the BRIER SCORING RULE which is basically (- (1 - p)^2) if your answer is correct and (- 1 - p^2) if your answer is incorrect

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-07-10T01:26:44.052413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:6a08e1d981d41c77d629928d9f42422e4663175ba7d266e1c282532228f7e2be

Observation 982e7cc8-b74b-4788-9658-813018049119 · outbound

This paper cites Then the value of log2(x4y3z2) is m n wheremandnare relatively prime positive integers.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness Then the value of log2(x4y3z2) is m n wheremandnare relatively prime positive integers

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-07-10T01:26:44.047382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:ca51130e69ddbe626be413d650d36126e484bd2075d99444bcd2166cfd579c61

Observation 455e6733-6fc8-4205-9d5d-62081035ba37 · outbound

This paper cites Models and decode.We compare the untrained Qwen3-8B base model with ourQwen3-8B model trained according to the DCPO recipe of Ma et al.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness Models and decode.We compare the untrained Qwen3-8B base model with ourQwen3-8B model trained according to the DCPO recipe of Ma et al

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-07-10T01:26:44.049097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-10T01:09:53.133146Z digest=sha256:492e278e8a1717ad37e059d6ac7eb560f0aab10f6af60829ae97da19228dd24b

Pith citing papers

No inbound Pith citation observations are available.