Paper Citation Record · LEDGER

MemHarness: Memory Is Reconstructed, Not Replayed

As of 7 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 1 inbound Pith citation observation for arXiv:2607.28272.

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

pith.paper-citation-record.v1
2607.28272 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-31T12:39:14.368486Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:14:14.565512Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T00:14:19.529738Z

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 a18c6404-ad7b-4053-94c1-239f135d712e · outbound

This paper cites Introspective Tips: Large Language Model for In-Context Decision Making.

MemHarness: Memory Is Reconstructed, Not Replayed Introspective Tips: Large Language Model for In-Context Decision Making

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:13.979151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de88d169-e33f-42db-84fb-bd6104d45256 · outbound

This paper cites Re-searcher: Robust agentic search with goal-oriented planning and self-reflection.

MemHarness: Memory Is Reconstructed, Not Replayed Re-searcher: Robust agentic search with goal-oriented planning and self-reflection

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:13.993771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4036f96b-0a3a-4922-bc27-bc058bed6d9e · outbound

This paper cites Search-r1: Training llms to reason and leverage search engines with reinforcement learning, 2025.

MemHarness: Memory Is Reconstructed, Not Replayed Search-r1: Training llms to reason and leverage search engines with reinforcement learning, 2025

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.005622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09a51526-e474-4168-9506-abd0a408f3fd · outbound

This paper cites O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering.

MemHarness: Memory Is Reconstructed, Not Replayed O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.014060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47e63ae8-7773-4860-b15d-3abcca0b5008 · outbound

This paper cites A comprehensive survey of continual learning: Theory, method and application, 2024.

MemHarness: Memory Is Reconstructed, Not Replayed A comprehensive survey of continual learning: Theory, method and application, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.022617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe573b4c-663f-4fac-8b7d-838deee0b0cc · outbound

This paper cites Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning.

MemHarness: Memory Is Reconstructed, Not Replayed Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.029343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c26a3c47-e8fc-4cce-b928-511d175f2a59 · outbound

This paper cites A-mem: Agentic memory for llm agents.Advances in Neural Information Processing Systems, 38:17577–17604, 2026.

MemHarness: Memory Is Reconstructed, Not Replayed A-mem: Agentic memory for llm agents.Advances in Neural Information Processing Systems, 38:17577–17604, 2026

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.042424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b6e151f-6dd7-40b1-9909-f98bc1c9763b · outbound

This paper cites Towards self-evolving agents: Enabling autonomy through interactive experience refinement.

MemHarness: Memory Is Reconstructed, Not Replayed Towards self-evolving agents: Enabling autonomy through interactive experience refinement

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.051183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d945a192-b391-46db-82c5-4aa68951cba1 · outbound

This paper cites G-memory: Tracing hierarchical memory for multi-agent systems, 2025.

MemHarness: Memory Is Reconstructed, Not Replayed G-memory: Tracing hierarchical memory for multi-agent systems, 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.058265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50481e2d-f1d2-4042-96ab-095a1b4c568e · outbound

This paper cites Memgen: Weaving generative latent memory for self-evolving agents.arXiv preprint arXiv:2509.24704, 2025.

MemHarness: Memory Is Reconstructed, Not Replayed Memgen: Weaving generative latent memory for self-evolving agents.arXiv preprint arXiv:2509.24704, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.068402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c850c88-fb5e-449a-ba99-326bcc1de44a · outbound

This paper cites Reconstruction of automobile destruction: An example of the interaction between language and memory.Journal of verbal learning and verbal behavior, 13(5):585–589, 1974.

MemHarness: Memory Is Reconstructed, Not Replayed Reconstruction of automobile destruction: An example of the interaction between language and memory.Journal of verbal learning and verbal behavior, 13(5):585–589, 1974

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.085217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf80551f-dbf5-427d-ae85-934840faff82 · outbound

This paper cites React: Synergizing reasoning and acting in language models, 2023.

MemHarness: Memory Is Reconstructed, Not Replayed React: Synergizing reasoning and acting in language models, 2023

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.091507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 915a783e-a950-4768-8e71-743cf8a7f921 · outbound

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

MemHarness: Memory Is Reconstructed, Not Replayed Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824–24837, 2022

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.101535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccf978cb-135a-44ff-bcf0-9cafca7be93a · outbound

This paper cites Reflexion: Language agents with verbal reinforcement learning, 2023.

MemHarness: Memory Is Reconstructed, Not Replayed Reflexion: Language agents with verbal reinforcement learning, 2023

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.112117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3eddf87-eab4-4d92-ae99-865fd66be7ad · outbound

This paper cites Correctad: A self-correcting agentic system to improve end-to-end planning in autonomous driving.

MemHarness: Memory Is Reconstructed, Not Replayed Correctad: A self-correcting agentic system to improve end-to-end planning in autonomous driving

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.121965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fa38185-fa82-4721-912c-4dbbb45d8b91 · outbound

This paper cites Agent-flan: Designing data and methods of effective agent tuning for large language models.

MemHarness: Memory Is Reconstructed, Not Replayed Agent-flan: Designing data and methods of effective agent tuning for large language models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.142743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f20d570-efd7-4c93-ab90-7707693ad3a7 · outbound

This paper cites FireAct: Toward Language Agent Fine-tuning.

MemHarness: Memory Is Reconstructed, Not Replayed FireAct: Toward Language Agent Fine-tuning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.155269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e2233f0-20a4-4849-97c2-a7268a72e52b · outbound

This paper cites Proximal Policy Optimization Algorithms.

MemHarness: Memory Is Reconstructed, Not Replayed Proximal Policy Optimization Algorithms

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.161655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58f6ff02-ac4c-4ad9-9ae5-551f3363353d · outbound

This paper cites Back to basics: Revisiting REINFORCE-style optimization for learning from human feedback in LLMs.

MemHarness: Memory Is Reconstructed, Not Replayed Back to basics: Revisiting REINFORCE-style optimization for learning from human feedback in LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.168144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbabd18a-84db-4fb0-9269-d03923f21f69 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

MemHarness: Memory Is Reconstructed, Not Replayed DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.184750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 937c00e7-5500-4439-a158-d7f8c0ce1f18 · outbound

This paper cites Group-in-group policy optimization for llm agent training.Advances in Neural Information Processing Systems, 38:46375–46408, 2026.

MemHarness: Memory Is Reconstructed, Not Replayed Group-in-group policy optimization for llm agent training.Advances in Neural Information Processing Systems, 38:46375–46408, 2026

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.194039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49f68abb-8aa5-44fe-93fd-83a8b3803a3c · outbound

This paper cites Expel: Llm agents are experiential learners, 2024.

MemHarness: Memory Is Reconstructed, Not Replayed Expel: Llm agents are experiential learners, 2024

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.209402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 610905a6-994c-4365-9c19-ab3389f42972 · outbound

This paper cites Memp: Exploring agent procedural memory.

MemHarness: Memory Is Reconstructed, Not Replayed Memp: Exploring agent procedural memory

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.218469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfab8442-935c-4bd9-8da1-e5fa4547299f · outbound

This paper cites Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory.

MemHarness: Memory Is Reconstructed, Not Replayed Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.229527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b944d89-6043-4542-b402-5fdc09134c74 · outbound

This paper cites SimpleMem: Efficient Lifelong Memory for LLM Agents.

MemHarness: Memory Is Reconstructed, Not Replayed SimpleMem: Efficient Lifelong Memory for LLM Agents

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.236279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c080738-af7f-4424-92e0-58e8ece96331 · outbound

This paper cites MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory.

MemHarness: Memory Is Reconstructed, Not Replayed MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.252240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3457d988-770e-41bd-a42a-9751a0b777fb · outbound

This paper cites EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle.

MemHarness: Memory Is Reconstructed, Not Replayed EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.261536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c26450b0-f544-4bb8-bd64-5a36da53d535 · outbound

This paper cites ALFWorld: Aligning Text and Embodied Environments for Interactive Learning.

MemHarness: Memory Is Reconstructed, Not Replayed ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.271247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb984070-f2e2-42f1-b82c-c1820b3d1a50 · outbound

This paper cites Webshop: Towards scalable real-world web interaction with grounded language agents.

MemHarness: Memory Is Reconstructed, Not Replayed Webshop: Towards scalable real-world web interaction with grounded language agents

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.280917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60f0886f-ce53-4528-915f-197ad3fd3282 · outbound

This paper cites GPT-4o System Card.

MemHarness: Memory Is Reconstructed, Not Replayed GPT-4o System Card

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.293899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0357afa7-ce32-430f-96be-504a8e7378ec · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

MemHarness: Memory Is Reconstructed, Not Replayed Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.305492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 520365b6-03f7-4e5c-a886-4f1ad8df1b3a · outbound

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

MemHarness: Memory Is Reconstructed, Not Replayed DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.315284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be77f111-5239-42f9-a5c6-4784a98824d5 · outbound

This paper cites Qwen2.5 technical report, 2025.

MemHarness: Memory Is Reconstructed, Not Replayed Qwen2.5 technical report, 2025

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.321863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b948cb7-716b-45da-8ea1-e7e4f66beb57 · outbound

This paper cites M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation.

MemHarness: Memory Is Reconstructed, Not Replayed M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.332232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9cdb622-dc33-4f2b-8cbd-fb3eb5d1a53a · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

MemHarness: Memory Is Reconstructed, Not Replayed HybridFlow: A Flexible and Efficient RLHF Framework

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.339493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21d78a7c-e535-4953-bf95-1d6bd4d5a722 · outbound

This paper cites Gon- zalez, Hao Zhang, and Ion Stoica.

MemHarness: Memory Is Reconstructed, Not Replayed Gon- zalez, Hao Zhang, and Ion Stoica

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.348545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a14c70bc-7d73-47bf-9fcf-596093e2b815 · outbound

This paper cites Milvus: A purpose-built vector data management system.

MemHarness: Memory Is Reconstructed, Not Replayed Milvus: A purpose-built vector data management system

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.360834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38923b67-8a01-45e2-ae3b-2167657286a6 · outbound

This paper cites Buy Now” button. •Original State (s +):... “Price: $19.99.

MemHarness: Memory Is Reconstructed, Not Replayed Buy Now” button. •Original State (s +):... “Price: $19.99

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-31T12:39:14.368486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 15317e70-87c0-48d3-bbb8-4649e4134d12 · inbound

Quo Vadis, World Modeling? cites this paper.

Quo Vadis, World Modeling? MemHarness: Memory Is Reconstructed, Not Replayed

Reference 174

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:14:19.609655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.