Paper Citation Record · LEDGER

Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 28 inbound Pith citation observations for arXiv:2410.02725.

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

pith.paper-citation-record.v1
2410.02725 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 28 of 28 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:53:40.156297Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-08T04:04:29.259300Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 99907d5d-b151-473e-b0e7-32f1c5d08195 · inbound

Teaching LLMs to Refine with Tools cites this paper.

Teaching LLMs to Refine with Tools Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T06:05:31.171365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d18c18b-4bee-4166-80bd-08c1da95a386 · inbound

Efficiently Scaling LLM Reasoning with Certaindex cites this paper.

Efficiently Scaling LLM Reasoning with Certaindex Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-10T23:09:44.504344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4934237-0cef-47d4-8266-8f599cd14eab · inbound

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs cites this paper.

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-13T15:51:29.352729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f9273b68-16a6-4870-9b06-e369653745e5 · inbound

Reasoning Language Models: A Blueprint cites this paper.

Reasoning Language Models: A Blueprint Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 106

Resolution: unresolved; no resolver link, observed 2026-08-10T18:36:54.811964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e961423-758f-48a8-8a61-d77fb777ff38 · inbound

An Annotated Reading of 'The Singer of Tales' in the LLM Era cites this paper.

An Annotated Reading of 'The Singer of Tales' in the LLM Era Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:32.595939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28dbae4a-9763-4ab2-b62d-6bb555d23956 · inbound

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling cites this paper.

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T14:40:36.007327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28ba310e-d39f-456c-b61b-de74027e2517 · inbound

A Survey of Scaling in Large Language Model Reasoning cites this paper.

A Survey of Scaling in Large Language Model Reasoning Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 133

Resolution: verified exact; arxiv_id, observed 2026-05-22T21:22:08.909332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 21472e94-2c9a-4cd6-904b-aca7f72a6b45 · inbound

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint cites this paper.

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:40.156297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e19c568-cd48-456a-b334-b9c32ba8e09b · inbound

S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models cites this paper.

S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T22:16:38.328031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e752f4b3-7b39-4de7-b8c4-3264b7c11ae7 · inbound

SLOT: Sample-specific Language Model Optimization at Test-time cites this paper.

SLOT: Sample-specific Language Model Optimization at Test-time Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:38:16.962058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81762ead-249f-4aca-8442-37830a99087e · inbound

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling cites this paper.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:36.638727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bc78be8-9657-4311-8b15-9ee5d12d9fcb · inbound

Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection cites this paper.

Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:54.020289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2aaa8f3-3bff-438d-87e5-5815c8ca0e76 · inbound

Temporal Sampling for Forgotten Reasoning in LLMs cites this paper.

Temporal Sampling for Forgotten Reasoning in LLMs Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:02:23.966532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98034956-2a7c-447a-ab41-25cca8119c50 · inbound

DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling cites this paper.

DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T23:48:23.944186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30fd29c9-404d-46f5-9d34-d6f2248beb88 · inbound

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs cites this paper.

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T20:43:10.441733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7704e66-d691-4b81-848a-b35c82a5aa27 · inbound

Energy-Based Transformers are Scalable Learners and Thinkers cites this paper.

Energy-Based Transformers are Scalable Learners and Thinkers Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 144

Resolution: unresolved; no resolver link, observed 2026-08-06T20:42:40.110205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2e41f12-3f29-4dfb-aa4a-277a3e5aa3a1 · inbound

TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization cites this paper.

TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T13:12:14.503038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93fe9e35-f1cc-4da3-94b5-bd7c185a8674 · inbound

Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness cites this paper.

Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-18T17:31:41.518634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 148a439c-bdf6-4a70-abdf-bfae5441b0e9 · inbound

ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation cites this paper.

ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-16T17:28:10.134591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4c4e0fcd-30cc-4117-b030-7906676a7676 · inbound

Quantum Circuit Generation via test-time learning with large language models cites this paper.

Quantum Circuit Generation via test-time learning with large language models Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T05:02:35.900921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ecc6883-6d92-4384-a569-db1710c99e04 · inbound

Adaptive Test-Time Compute Allocation with Evolving In-Context Demonstrations cites this paper.

Adaptive Test-Time Compute Allocation with Evolving In-Context Demonstrations Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:51:05.453989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 91fadf79-b955-4330-b141-0bbeb1c443d9 · inbound

ATLAS: Agentic Test-time Learning-to-Allocate Scaling cites this paper.

ATLAS: Agentic Test-time Learning-to-Allocate Scaling Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-07-01T22:26:17.074072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3e831cad-a8a7-4145-a1a7-e22b4c8de4be · inbound

AVIS: Adaptive Test-Time Scaling for Vision-Language Models cites this paper.

AVIS: Adaptive Test-Time Scaling for Vision-Language Models Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-03T08:17:45.848719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bce4c447-23a7-4c53-a44f-59c1c57e0f2b · inbound

Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains cites this paper.

Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T11:21:40.881716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db3501d7-41c3-41e7-9ea6-357bf2a55238 · inbound

Hard or Just Unreached? Diagnosing the Sampling Blind Spot in Math-Reasoning Difficulty Estimation cites this paper.

Hard or Just Unreached? Diagnosing the Sampling Blind Spot in Math-Reasoning Difficulty Estimation Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 34

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T01:09:18.637930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d41d606d-7ba0-4050-aa3d-d9b226d5811d · inbound

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade cites this paper.

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T04:04:29.260568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 72f2585a-3ce4-4857-8dcb-e23485e3f759 · inbound

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade cites this paper.

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T08:18:05.198672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7314de4d-bd1f-4887-a915-23c7ca31f8c5 · inbound

Accuracy Hides How Language Models Fail: Measuring Failure States Under Matched Output Budgets cites this paper.

Accuracy Hides How Language Models Fail: Measuring Failure States Under Matched Output Budgets Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T15:31:50.420577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.