Paper Citation Record · LEDGER

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability

As of 21 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2608.06503.

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

pith.paper-citation-record.v1
2608.06503 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T04:23:51.593019Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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

32 of 32 outbound references displayed

verified exact0
verified fuzzy19
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6697e6cd-0a90-4136-a9bc-9b3c1a343540 · outbound

This paper cites In Progress.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability In Progress

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:52.212170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 64b91d12-ef9a-47f8-9508-9e59cdaf1758 · outbound

This paper cites an unresolved cited work.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-10T04:23:52.148652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation feb454a8-3eff-4ef8-bf14-9b5be31b716c · outbound

This paper cites an unresolved cited work.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-10T04:23:52.133633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0c393e4c-0876-4ab4-af28-131935ca12dc · outbound

This paper cites N. ACTION target --- outcome [tool: name].

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability N. ACTION target --- outcome [tool: name]

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:52.196846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation daa5eaaf-a968-4a7b-9a3c-f46229a7da59 · outbound

This paper cites - Note how earlier steps influence later ones.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability - Note how earlier steps influence later ones

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:52.170933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6aa1182b-0550-45a5-9f65-e04ee72244ac · outbound

This paper cites So do not write code making calls to os-level modules and functions.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability So do not write code making calls to os-level modules and functions

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.896372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2689206d-78f2-4999-acd7-68fa10acb0b0 · outbound

This paper cites E.g., do NOT use`spotipy`for Spotify.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability E.g., do NOT use`spotipy`for Spotify

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.881304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c0c5bffb-52f9-4de5-b299-bc97b0d1dac4 · outbound

This paper cites an unresolved cited work.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-10T04:23:52.114677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 02b1645e-7bad-4303-bca5-b1672b8761f3 · outbound

This paper cites - Memory resets; re-create VARS before use.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability - Memory resets; re-create VARS before use

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:52.097882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d1c3b6ab-5b01-476f-bbda-76d788518d77 · outbound

This paper cites an unresolved cited work.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-10T04:23:52.081030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 53f41b56-dbea-47d5-8e3d-b4281848c5c5 · outbound

This paper cites an unresolved cited work.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-10T04:23:52.063544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 45474555-79e3-4ebf-9d11-d663f02cfe59 · outbound

This paper cites an unresolved cited work.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-10T04:23:52.049403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 51a1b717-ea35-418c-9676-2d3f3189c067 · outbound

This paper cites an unresolved cited work.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-10T04:23:52.030162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0dd09867-869a-404c-8dde-3e320a20f1ac · outbound

This paper cites global_rules.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability global_rules

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:52.011461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 602620e0-c473-48bf-b0a9-43ea6def8383 · outbound

This paper cites sections.critical_context.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability sections.critical_context

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.995298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 95a1cab1-35e7-4ac3-bf86-64d89ee2e82a · outbound

This paper cites spotify_password) in the example above were only for demonstration.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability spotify_password) in the example above were only for demonstration

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.978230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 18c28ec8-806a-4cae-b78a-48d533d518d8 · outbound

This paper cites Any thoughts should be put as code comments.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Any thoughts should be put as code comments

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.962201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation eea050d9-18ab-4919-9ff7-57d2955634e0 · outbound

This paper cites an unresolved cited work.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-10T04:23:51.944960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a288838d-2e0b-4b2f-8d27-bcac2622fec5 · outbound

This paper cites Make sure everything is working correctly before making any irreversible change.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Make sure everything is working correctly before making any irreversible change

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.927528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 676ccdb1-fabe-4d12-a8cf-c75db5468d12 · outbound

This paper cites But modules and functions that have a risk of affecting the underlying OS, file system or process are disabled.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability But modules and functions that have a risk of affecting the underlying OS, file system or process are disabled

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.910961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0c6315ad-5b74-43b1-8038-de2bbc209f3a · outbound

This paper cites All calls to APIs and parsing its outputs must be as per this documentation.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability All calls to APIs and parsing its outputs must be as per this documentation

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.864121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 21c742b2-9588-45ff-8956-816e9da9b4e2 · outbound

This paper cites an unresolved cited work.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-10T04:23:51.847401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a10613a4-7ad8-411f-8489-a243f68804e9 · outbound

This paper cites Do not rely on your existing knowledge of what the current date or time is.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Do not rely on your existing knowledge of what the current date or time is

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.827701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 78b76eb0-9f94-4c5d-b96c-b78e2a7edb67 · outbound

This paper cites All requests are concerning a single, default (no) time zone.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability All requests are concerning a single, default (no) time zone

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.811276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e6c3d94b-8287-4487-8388-d7f3211c1671 · outbound

This paper cites an unresolved cited work.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-10T04:23:51.790995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3ca97a44-8de4-4455-9d7a-d7dbbc054eba · outbound

This paper cites supervisor.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability supervisor

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.769973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7558bf3d-ca8b-4ffc-8470-27d09793a5d3 · outbound

This paper cites If the task asks for some information, return it as the answer argument, i.e.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability If the task asks for some information, return it as the answer argument, i.e

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.751520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 98cc1fd7-8cee-429a-8962-eba3af45604a · outbound

This paper cites How many songs are in the Spotify queue?.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability How many songs are in the Spotify queue?

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.735821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ca0d50f3-c5cc-4f79-a6a2-1c8a795de77e · outbound

This paper cites an unresolved cited work.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-10T04:23:51.720429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b84c59d6-0987-4584-9783-6f1c59b257bc · outbound

This paper cites preserve everything.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability preserve everything

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T04:23:51.705435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3ee02c37-d69b-40b5-9bfe-df6e80b46eaf · outbound

This paper cites OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-10T04:23:51.431618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0c222d7-13ad-478d-b77e-3986da8eb9a0 · outbound

This paper cites doi: 10.18653/v1/2025.acl-long.1219.

Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability doi: 10.18653/v1/2025.acl-long.1219

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-10T04:23:51.426275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.