Paper Citation Record · LEDGER

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching

As of 9 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 1 inbound Pith citation observation for arXiv:2603.27044.

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

pith.paper-citation-record.v1
2603.27044 v3

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-13T17:19:02.982053Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-27T10:27:47.896922Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T09:17:48.486940Z

Reference resolution

15 of 15 outbound references displayed

verified exact2
verified fuzzy0
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c6f2957b-b364-48a5-898e-e78144beab08 · outbound

This paper cites Variational Option Discovery Algorithms.

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching Variational Option Discovery Algorithms

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T17:19:02.982053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0330c2a1-e371-4af3-bd20-6cb4fb262cb0 · outbound

This paper cites Learning policy representations for steerable behavior synthesis.arXiv preprint arXiv:2601.22350,.

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching Learning policy representations for steerable behavior synthesis.arXiv preprint arXiv:2601.22350,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T17:19:02.982053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f812df9f-ea7e-4330-9a72-71f35508d3b0 · outbound

This paper cites Mirco Mutti, Stefano Del Col, and Marcello Restelli.

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching Mirco Mutti, Stefano Del Col, and Marcello Restelli

Reference 3

Resolution: verified exact; doi, observed 2026-07-13T17:19:46.580425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ca27d3bb-591e-47ae-bfde-499053712d75 · outbound

This paper cites Learning to Learn with Generative Models of Neural Network Checkpoints.

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching Learning to Learn with Generative Models of Neural Network Checkpoints

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T17:19:02.982053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92533859-3fc2-4755-b603-cfdd1cd6c4ad · outbound

This paper cites Proximal Policy Optimization Algorithms.

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching Proximal Policy Optimization Algorithms

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-13T17:19:02.982053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88fa4cd6-1d89-48e4-b752-77dd7d5ad0b9 · outbound

This paper cites 11 Supplementary Materials The following content was not necessarily subject to peer review.

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching 11 Supplementary Materials The following content was not necessarily subject to peer review

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-13T17:19:46.588097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f2d34d48-87ea-4a6b-8c80-e8a6f2c7a393 · outbound

This paper cites In supervised learning, hyper-representations(Schürholt et al., 2021; 2022.

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching In supervised learning, hyper-representations(Schürholt et al., 2021; 2022

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T17:19:02.982053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac37e8c2-3056-48c6-bdf2-8a9e20dda9d0 · outbound

This paper cites To circumvent this, recent works in supervised learning supplement standard parameter reconstruction losses with behavioral output matching (Meynent et al., 2025).

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching To circumvent this, recent works in supervised learning supplement standard parameter reconstruction losses with behavioral output matching (Meynent et al., 2025)

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T17:19:02.982053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d6f86ff-f04d-42fa-9052-1d4c3b63b889 · outbound

This paper cites Similar architectures have been applied in Quality Diversity to improve the sample efficiency of diversity-based search (Rakicevic et al.,.

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching Similar architectures have been applied in Quality Diversity to improve the sample efficiency of diversity-based search (Rakicevic et al.,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T17:19:02.982053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39f8e67d-daa9-4265-8785-bacdee8dd9df · outbound

This paper cites Notably, these methods rely onparameter-reconstruction losses, which fundamentally restrict their compression ratios (e.g., up to 19 : 1 in Hegde et al.

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching Notably, these methods rely onparameter-reconstruction losses, which fundamentally restrict their compression ratios (e.g., up to 19 : 1 in Hegde et al

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-13T17:19:02.982053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecaca591-6f3c-4726-ba4c-ce03679ce71d · outbound

This paper cites an unresolved cited work.

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-13T17:19:02.982053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8018d7ca-3319-4b25-9668-26cebbd90ce7 · outbound

This paper cites Our contribution scales these concepts from single-expert matching to population-level alignment by developing a mixture-occupancy matching objective.

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching Our contribution scales these concepts from single-expert matching to population-level alignment by developing a mixture-occupancy matching objective

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T17:19:02.982053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a323aede-a36a-4f31-ac88-5b01ff0ced6a · outbound

This paper cites an unresolved cited work.

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-13T17:19:02.982053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fac1c43-d117-4862-b2a8-714a13a148db · outbound

This paper cites Proof.By the definition of the mixture, m(x) =w ipi(x)+P j̸=i wjpj(x).

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching Proof.By the definition of the mixture, m(x) =w ipi(x)+P j̸=i wjpj(x)

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T17:19:02.982053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36a663ca-7f4d-488a-842d-7dced679c0e9 · outbound

This paper cites Reacher (RC).RC features a two-jointed robotic arm moving in a 2D plane.

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching Reacher (RC).RC features a two-jointed robotic arm moving in a 2D plane

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-13T17:19:02.982053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 068c1dd5-793c-4edf-aa67-363193e9e106 · inbound

Implicit Neural Representations of Individual Behavior cites this paper.

Implicit Neural Representations of Individual Behavior Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching

Reference 99

Resolution: verified exact; arxiv_id, observed 2026-07-07T03:18:14.563422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.