Paper Citation Record · LEDGER

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback

As of 10 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2606.01081.

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

pith.paper-citation-record.v1
2606.01081 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T17:49:58.484710Z

measured 12 of 12 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

12 of 12 outbound references displayed

verified exact1
verified fuzzy0
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 23d07746-e462-4689-94c4-33a6fe27e6a9 · outbound

This paper cites an unresolved cited work.

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-28T17:49:58.484710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dbad068-a05e-4407-827d-57adf908cc41 · outbound

This paper cites predict, then optimize.

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback predict, then optimize

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:52:27.362704Z

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 5f93699a-b264-4f2d-9468-2f3a5e4e89eb · outbound

This paper cites an unresolved cited work.

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-28T17:49:58.484710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f9ea7ff-0009-4df9-8a73-86cba540bcb0 · outbound

This paper cites Applying the triangle inequality,∥w ⋆(ˆc)∥ ≤BS, and (12) yields ∥∇θw⋆ θ(x)− ∇ θw⋆ θ′(x)∥ ≤B S Z ∥∇θpθ(ˆc|x)− ∇ θpθ′(ˆc|x)∥dˆc≤B S M∇ ∥θ−θ ′∥.

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback Applying the triangle inequality,∥w ⋆(ˆc)∥ ≤BS, and (12) yields ∥∇θw⋆ θ(x)− ∇ θw⋆ θ′(x)∥ ≤B S Z ∥∇θpθ(ˆc|x)− ∇ θpθ′(ˆc|x)∥dˆc≤B S M∇ ∥θ−θ ′∥

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-28T17:49:58.484710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7523f714-ed8a-4da0-a637-4dbe55a06f1c · outbound

This paper cites At the beginning of period t, the context is drawn as xt ∼ N(0, I p), with default p= 25.

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback At the beginning of period t, the context is drawn as xt ∼ N(0, I p), with default p= 25

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-28T17:49:58.484710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea3b30ac-1ccf-4324-a9eb-f51c10c8ac23 · outbound

This paper cites Algorithm 2:Greedy contextual bandit (GREEDYCB) Input:Initial parametersθ 1 ∈R dθ; stepsizeη t >0 fort= 1,2,.

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback Algorithm 2:Greedy contextual bandit (GREEDYCB) Input:Initial parametersθ 1 ∈R dθ; stepsizeη t >0 fort= 1,2,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-28T17:49:58.484710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f57c3e71-037d-4593-9295-5723987dcddb · outbound

This paper cites Figure 4 reports the same comparison on the three remaining benchmarks: top-k selection, shortest path, and energy scheduling.

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback Figure 4 reports the same comparison on the three remaining benchmarks: top-k selection, shortest path, and energy scheduling

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-28T17:49:58.484710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c66c33e-a458-4317-bd7c-a8a604fc3a0c · outbound

This paper cites an unresolved cited work.

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T17:49:58.484710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a38bccb6-9b4d-4f17-87ec-6ae1500a5354 · outbound

This paper cites an unresolved cited work.

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T17:49:58.484710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b5f4a9c-b729-430d-a8af-2ad911bee0b2 · outbound

This paper cites The negative signs on the softmax arguments convert cost minimization to score maximization for the listwise ranking step.

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback The negative signs on the softmax arguments convert cost minimization to score maximization for the listwise ranking step

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-28T17:49:58.484710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3624af3b-4922-40b4-9270-3bb0004cde83 · outbound

This paper cites an unresolved cited work.

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-28T17:49:58.484710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ee09b42-e634-4d28-84d8-6a44786fd1b6 · outbound

This paper cites On top- k the gap is more modest at low degrees (around 2× at deg = 2 ) and widens to roughly 4–5× at deg≥4.

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback On top- k the gap is more modest at low degrees (around 2× at deg = 2 ) and widens to roughly 4–5× at deg≥4

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-28T17:49:58.484710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.