Paper Citation Record · LEDGER

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation

As of 11 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 1 inbound Pith citation observation for arXiv:2604.21950.

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

pith.paper-citation-record.v1
2604.21950 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-09T21:37:28.871977Z

measured 17 of 17 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-09T03:36:57.168246Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-09T03:45:55.620157Z

Reference resolution

16 of 16 outbound references displayed

verified exact10
verified fuzzy6
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation eeaf6c0f-2425-4aa3-a9fd-1b14cf78e5e1 · outbound

This paper cites InProceedings of the Association for Computing Machinery on Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA).

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation InProceedings of the Association for Computing Machinery on Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA)

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T15:45:42.776654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 77b91d4e-2444-4753-abf6-d77ef3f2e278 · outbound

This paper cites Aflow: Automating agentic workflow generation.Interna- tional Conference on Learning Representations (ICLR).

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation Aflow: Automating agentic workflow generation.Interna- tional Conference on Learning Representations (ICLR)

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T15:45:42.789338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 671837c2-4330-4abd-a3f1-fa9270665479 · outbound

This paper cites EvoFlow: Evolving Diverse Agentic Workflows On The Fly.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation EvoFlow: Evolving Diverse Agentic Workflows On The Fly

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:31:07.890378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bb2a4b08-5827-4f18-bef0-3d142cb07401 · outbound

This paper cites Controlled Self-Evolution for Algorithmic Code Optimization, February 2026.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation Controlled Self-Evolution for Algorithmic Code Optimization, February 2026

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:31:07.805117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 562b5e7a-e3c1-4a9c-a1bd-78a73083dae8 · outbound

This paper cites Program Synthesis with Large Language Models.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation Program Synthesis with Large Language Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-11T14:31:07.876067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a4c2da5a-a67f-424e-813a-97fbe72eee0f · outbound

This paper cites FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:56:45.568475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f425f900-058d-4918-8108-8ff9f9ec285c · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation Evaluating Large Language Models Trained on Code

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-11T14:31:07.919913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 82a37914-04a0-4533-b163-9e85753931c6 · outbound

This paper cites DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:57:47.698794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3bb498d0-8929-4cc2-ad25-11f7561b7aac · outbound

This paper cites Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:31:07.900933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 35dd340d-c501-429b-8ee1-19853f73a2d7 · outbound

This paper cites Small models struggle to learn from strong reasoners.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation Small models struggle to learn from strong reasoners

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T15:45:42.798644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dc3a643a-575a-42f0-9e95-f2dfd9e78714 · outbound

This paper cites Ares: Adaptive red-teaming and end-to-end repair of policy-reward system.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation Ares: Adaptive red-teaming and end-to-end repair of policy-reward system

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T15:45:42.793971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 844867c2-dcc3-40d0-b4f5-4d5346bedd6b · outbound

This paper cites Ea4llm: A gradient- free approach to large language model optimization via evolutionary algo- rithms.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation Ea4llm: A gradient- free approach to large language model optimization via evolutionary algo- rithms

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:31:07.852095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6b48536a-3e6b-48b9-99c9-f2020747da9d · outbound

This paper cites Evolving neural networks through augmenting topologies.Evolutionary Computation, 10(2):99–127.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation Evolving neural networks through augmenting topologies.Evolutionary Computation, 10(2):99–127

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T15:45:42.785054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 02ec18e8-41a9-4afb-a021-dd6d0b9d0b39 · outbound

This paper cites Mixture-of-agents enhances large language model capabilities.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation Mixture-of-agents enhances large language model capabilities

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T15:45:42.780989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7ae454ed-52a5-48fa-bf48-e6cc0759c8c4 · outbound

This paper cites AgentConductor : Topology evolution for multi-agent competition-level code generation.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation AgentConductor : Topology evolution for multi-agent competition-level code generation

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:31:07.910047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 01c7b596-d4b0-4516-9eff-d078e2acfb5f · outbound

This paper cites EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers.

Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:11:49.925109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation 76b3d871-8d98-4c49-803f-6374ed0157fa · inbound

Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops cites this paper.

Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:45:55.621566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.