Paper Citation Record · LEDGER

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning

As of 10 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2607.15736.

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

pith.paper-citation-record.v1
2607.15736 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T22:30:30.736777Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

38 of 38 outbound references displayed

verified exact0
verified fuzzy0
unresolved38
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 804d9cb0-e422-4b48-9a42-df52fb8bc6b0 · outbound

This paper cites On-policy distillation of language models: Learning from self-generated mistakes.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning On-policy distillation of language models: Learning from self-generated mistakes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:26.312230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ca6bead-6994-420f-a141-59d3a0c82426 · outbound

This paper cites L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:26.382580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71580838-4a00-4043-b714-62b35e844fac · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Evaluating Large Language Models Trained on Code

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:26.437579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2d756ed-7aef-46f3-a18d-08c8796c2180 · outbound

This paper cites Over-reasoning and redundant calculation of large language models.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Over-reasoning and redundant calculation of large language models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:26.574381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4aec21af-58bb-4c93-8c00-71d71bec22cb · outbound

This paper cites Ctrlcot: Dual-granularity chain-of-thought compression for controllable reasoning.arXiv preprint arXiv:2601.20467, 2026.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Ctrlcot: Dual-granularity chain-of-thought compression for controllable reasoning.arXiv preprint arXiv:2601.20467, 2026

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:26.709576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23771348-14da-43d3-85e7-1bf00c307d4e · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:26.806144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc4ec9f7-12a1-45a4-9c29-d8702dac0d2d · outbound

This paper cites FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:26.949438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0584c0fa-fd79-4637-b482-b9222a1d19ad · outbound

This paper cites Lora: Low-rank adaptation of large language models.Iclr, 1(2):3, 2022.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Lora: Low-rank adaptation of large language models.Iclr, 1(2):3, 2022

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:27.059754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71436f62-523a-4f94-b8c9-41869fc84566 · outbound

This paper cites CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular Reasoning.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular Reasoning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:27.185941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce4b9a58-09c5-4fde-a45f-392571590ab6 · outbound

This paper cites Stepwise penalization for length-efficient chain-of-thought reasoning.arXiv preprint arXiv:2603.00296, 2026.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Stepwise penalization for length-efficient chain-of-thought reasoning.arXiv preprint arXiv:2603.00296, 2026

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:27.342651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b7fbd9e-57fc-47ec-bd72-7c61dbc45b65 · outbound

This paper cites Leash: Adaptive length penalty and reward shaping for efficient large reasoning model.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Leash: Adaptive length penalty and reward shaping for efficient large reasoning model

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:27.465715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ba74e4f-fc37-4b55-8f29-fcc8a19eb7ab · outbound

This paper cites Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:27.604900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ee0426e-f059-4a07-9eb6-34c0452fb5c5 · outbound

This paper cites Making slow thinking faster: Compressing llm chain-of-thought via step entropy.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Making slow thinking faster: Compressing llm chain-of-thought via step entropy

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:27.734791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7e33486-b871-43fb-80cd-52bcf714811c · outbound

This paper cites Cot-valve: Length- compressible chain-of-thought tuning.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Cot-valve: Length- compressible chain-of-thought tuning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:27.867246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a0d4f9a-1cc5-4e56-9b8c-dcc1d45a5c81 · outbound

This paper cites Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:27.977843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afa4a953-3909-43b0-aa0b-fafb28be5eb1 · outbound

This paper cites The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:28.075136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe6823c0-5e7f-4cbe-82eb-c29ce392c66e · outbound

This paper cites CRISP: Compressed Reasoning via Iterative Self-Policy Distillation.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning CRISP: Compressed Reasoning via Iterative Self-Policy Distillation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:28.143346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b00ecb9-7a1c-44af-8f27-118e5554b71f · outbound

This paper cites Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:28.188121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 270477ff-04a5-465b-a9fb-d2544c49303c · outbound

This paper cites Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:28.272756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38483ab5-3502-41d5-8e6b-e19e2bfebca4 · outbound

This paper cites SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:28.401425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82c46945-f09b-4956-9e47-cd4997d2cdd5 · outbound

This paper cites Mitigating overthinking in large reasoning models via difficulty-aware reinforcement learning.arXiv preprint arXiv:2601.21418, 2026.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Mitigating overthinking in large reasoning models via difficulty-aware reinforcement learning.arXiv preprint arXiv:2601.21418, 2026

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:28.521507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78dd7ee1-1831-4003-8622-8a91d09a4dcc · outbound

This paper cites Pointrft: Explicit reinforcement fine-tuning for point cloud few-shot learning.arXiv preprint arXiv:2603.23957, 2026.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Pointrft: Explicit reinforcement fine-tuning for point cloud few-shot learning.arXiv preprint arXiv:2603.23957, 2026

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:28.646872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87e7945c-1293-4074-a41a-cd85eacc6e7c · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824–24837, 2022.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824–24837, 2022

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:28.751256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cfc9306-1f12-4bd2-8e43-202a8f59d53e · outbound

This paper cites Stop spinning wheels: Mitigating llm overthinking via mining patterns for early reasoning exit.arXiv preprint arXiv:2508.17627, 2025.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Stop spinning wheels: Mitigating llm overthinking via mining patterns for early reasoning exit.arXiv preprint arXiv:2508.17627, 2025

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:28.856639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d425e2d-bf39-4158-b6a5-3991ea88868d · outbound

This paper cites Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:29.031776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d6ea4e8-f89d-47ae-8438-c12168969145 · outbound

This paper cites Tokenskip: Controllable chain-of- thought compression in llms.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Tokenskip: Controllable chain-of- thought compression in llms

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:29.190178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c24fd4d-33e7-4894-9235-6b49b96cef7d · outbound

This paper cites TIP: Token Importance in On-Policy Distillation.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning TIP: Token Importance in On-Policy Distillation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:29.298845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 724d3a4e-c076-4d70-ac1f-017cd7a5a2e8 · outbound

This paper cites Qwen3 Technical Report.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Qwen3 Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:29.435203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42a0bf48-4449-4bce-af68-bd9b3541a50f · outbound

This paper cites Dynamic early exit in reasoning models.arXiv preprint arXiv:2504.15895, 2025.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Dynamic early exit in reasoning models.arXiv preprint arXiv:2504.15895, 2025

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:29.581049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df229ce0-1db5-4f8c-80cc-8ecb0b81639e · outbound

This paper cites Dapo: An open-source llm reinforcement learning system at scale.Advances in Neural Information Processing Systems, 38:113222–113244, 2026.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Dapo: An open-source llm reinforcement learning system at scale.Advances in Neural Information Processing Systems, 38:113222–113244, 2026

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:29.705899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05a0f91a-5b99-4951-8846-aec3d412fd80 · outbound

This paper cites Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:29.855076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d6f8778-4ca5-491c-af35-36fc05297cde · outbound

This paper cites Not all queries need deep thought: Coficot for adaptive coarse-to-fine stateful refinement.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Not all queries need deep thought: Coficot for adaptive coarse-to-fine stateful refinement

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:29.983687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 963e6cda-bb0b-4ced-a1b5-ba1ac8760988 · outbound

This paper cites Pointcot: A multi-modal benchmark for explicit 3d geometric reasoning.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Pointcot: A multi-modal benchmark for explicit 3d geometric reasoning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:30.130283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c450edfb-9a75-4e2c-aadd-849da054a64c · outbound

This paper cites Chain-of- thought compression should not be blind: V-skip for efficient multimodal reasoning via dual-path anchoring.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Chain-of- thought compression should not be blind: V-skip for efficient multimodal reasoning via dual-path anchoring

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:30.246127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa0c6422-aac5-40c6-ad1c-39a49fad9520 · outbound

This paper cites find the time 1000 days later.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning find the time 1000 days later

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:30.383699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55b36b39-b8ab-4adb-aa77-48b40343be77 · outbound

This paper cites OPSDL: On-Policy Self-Distillation for Long-Context Language Models.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning OPSDL: On-Policy Self-Distillation for Long-Context Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:30.506956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ce0a45e-fefc-4f5a-88a4-1f59748e649e · outbound

This paper cites Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:30.618642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aae79c50-4483-4cf4-ba8b-7467a79da262 · outbound

This paper cites ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:30.736777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.