Paper Citation Record · LEDGER

Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 36 inbound Pith citation observations for arXiv:2504.07912.

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

pith.paper-citation-record.v1
2504.07912 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 36 of 36 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:32:13.065149Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation b1265abc-8c31-453d-8e78-17fdf1016739 · inbound

Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning cites this paper.

Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T14:41:42.861182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b14d4b8-a2bd-44ab-8590-7b87811c4b6e · inbound

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model cites this paper.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:04.977166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a25873b9-4bbb-48a7-b9d8-600f23a38b99 · inbound

Accelerating RL for LLM Reasoning with Optimal Advantage Regression cites this paper.

Accelerating RL for LLM Reasoning with Optimal Advantage Regression Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T13:55:56.838631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb07e421-7e4c-483a-8836-43bc5d0f129b · inbound

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning cites this paper.

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T12:32:24.730994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88fa932b-ec92-4839-a37e-5fcf057a7eeb · inbound

A Survey on Large Language Models for Mathematical Reasoning cites this paper.

A Survey on Large Language Models for Mathematical Reasoning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 108

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:47.584200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b7724ee-3cc2-4c91-8daa-3cf638a5b3d5 · inbound

Resa: Transparent Reasoning Models via SAEs cites this paper.

Resa: Transparent Reasoning Models via SAEs Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.749398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77f34f5e-32a2-486f-a497-2323514f9ea2 · inbound

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning cites this paper.

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T04:39:08.980643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f71c7fa-5d4b-4ef8-a912-a461dd82f61c · inbound

Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models cites this paper.

Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:36.795096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c34a1c97-537c-4a4d-a78e-267fce97c439 · inbound

RAST: Reasoning Activation in LLMs via Small-model Transfer cites this paper.

RAST: Reasoning Activation in LLMs via Small-model Transfer Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T12:19:59.473464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbb9ee45-ebdf-46fe-9dd0-c32d2aec739b · inbound

Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess cites this paper.

Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T21:13:15.416519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 928eb557-583d-4526-8c3c-d1d4ea2ada9b · inbound

Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling cites this paper.

Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:40:46.496771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 85c4f4bd-1b2b-4aca-830a-17452bf3b613 · inbound

CTR-Guided Generative Query Suggestion in Conversational Search cites this paper.

CTR-Guided Generative Query Suggestion in Conversational Search Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T20:00:55.387382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bc7292e-75cf-4773-bb90-8c07c170c430 · inbound

Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them cites this paper.

Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T17:52:01.701241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c8fce14-0754-438c-bcef-c2de1fb7f8e5 · inbound

EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning cites this paper.

EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T23:56:55.052234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ce4dbadb-8bdf-48de-bfa1-e2464ee72378 · inbound

Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration cites this paper.

Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-18T22:36:53.734614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cbe4cbfe-156e-46e5-874d-4a5c2542018f · inbound

Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought cites this paper.

Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T10:31:37.961065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 956c47bb-bede-428d-b782-c4f032804a4c · inbound

Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle cites this paper.

Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 235

Resolution: unresolved; no resolver link, observed 2026-08-04T16:07:48.002445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5cb03da-797e-420f-9839-d10cf6717f17 · inbound

Polychromic Objectives for Reinforcement Learning cites this paper.

Polychromic Objectives for Reinforcement Learning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:56:19.958923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9d30284e-7c29-4951-bac7-482e391095df · inbound

Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts cites this paper.

Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T10:39:29.812004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 822b0dd1-0a95-4955-87e4-6c232c4c4d42 · inbound

Value Drifts: Tracing Value Alignment During LLM Post-Training cites this paper.

Value Drifts: Tracing Value Alignment During LLM Post-Training Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-04T07:21:37.061716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ca369b3-50c4-4a06-bb76-78579f3f88a7 · inbound

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning cites this paper.

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 1378

Resolution: malformed identifier; no resolver link, observed 2026-08-03T05:52:38.582979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c196a99-ed67-402f-8213-df1727a0d125 · inbound

Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning cites this paper.

Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:27:36.462167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 48e5d4e4-67be-461b-a6bc-b400c58cffb1 · inbound

On the Emergence of Implicit Curriculum in RLVR Learning Dynamics cites this paper.

On the Emergence of Implicit Curriculum in RLVR Learning Dynamics Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T23:11:58.245425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06b01db8-7aa0-4d64-b9d3-7cfa93ece865 · inbound

From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning cites this paper.

From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-14T23:46:32.301737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9ddf425-8719-445e-847c-40d4f1f00e86 · inbound

OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning cites this paper.

OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-11T11:56:13.937770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8b2ea63d-c95a-43b5-80ab-c311e81f9c11 · inbound

AIPO: Learning to Reason from Active Interaction cites this paper.

AIPO: Learning to Reason from Active Interaction Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 79

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T08:06:31.196542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a63f88fc-7293-424e-be01-d1f745737a87 · inbound

AIPO: Learning to Reason from Active Interaction cites this paper.

AIPO: Learning to Reason from Active Interaction Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 79

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T18:07:42.335525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a8ae377b-f8f8-4fa1-9e10-a451ea56ac09 · inbound

Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR cites this paper.

Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:21:22.445555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2409b916-7add-4a41-9b0d-35e670a02646 · inbound

Reasoning Can Be Restored by Correcting a Few Decision Tokens cites this paper.

Reasoning Can Be Restored by Correcting a Few Decision Tokens Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T20:57:46.848006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 56707dc9-0357-4dfe-9935-42d6a653c18d · inbound

How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning cites this paper.

How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-07-05T10:20:57.200486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f67dd987-2349-4996-afd1-ab5850dba0dc · inbound

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning cites this paper.

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-06-27T01:20:20.569507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e419ae80-2f9d-411a-bc8c-2a8f4b32b3d2 · inbound

RL Post-Training Builds Compositional Reasoning Strategies cites this paper.

RL Post-Training Builds Compositional Reasoning Strategies Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-09T04:05:55.494223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fa86c831-0274-4832-9eba-19bc8f4e8c0e · inbound

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion cites this paper.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.084480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15009b28-60d0-476b-927b-4e68acfec58a · inbound

Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Models cites this paper.

Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Models Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 148

Resolution: unresolved; no resolver link, observed 2026-08-12T00:39:40.951940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91df57ff-200d-4d8b-b1c3-ad18867ce443 · inbound

Parameter Exploration for RLVR via Variational Learning cites this paper.

Parameter Exploration for RLVR via Variational Learning Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-11T10:32:13.129972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01c6da4f-5b98-4b78-ba78-d2c75dd6599c · inbound

LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure cites this paper.

LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-14T04:32:13.065149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.