Paper Citation Record · LEDGER

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels

As of 23 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2504.12557.

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

pith.paper-citation-record.v1
2504.12557 v3

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:36:41.887506Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+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

39 of 39 outbound references displayed

verified exact1
verified fuzzy23
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation db834ad8-2448-43ac-bdfd-fd9080df8ab6 · outbound

This paper cites Constrained policy optimization.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Constrained policy optimization

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.430456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 58761e91-1cf1-4ca9-b7e0-6458a2990987 · outbound

This paper cites Constrained markov decision processes with total cost criteria: Lagrangian approach and dual linear program.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Constrained markov decision processes with total cost criteria: Lagrangian approach and dual linear program

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.418024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4a4314f8-eb62-439d-9730-01706c60a187 · outbound

This paper cites Pattern recognition and machine learning, volume 4.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Pattern recognition and machine learning, volume 4

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.656330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38784651-cad7-484b-a0f2-439b00037213 · outbound

This paper cites Safety through feedback in constrained RL.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Safety through feedback in constrained RL

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.395444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 110a8904-a278-4451-a80a-8bc4d40c1154 · outbound

This paper cites Learning constraints from demonstrations, 2019.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Learning constraints from demonstrations, 2019

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.382354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3c88a293-5349-4bb2-81bd-e29ec1027f47 · outbound

This paper cites Learning parametric constraints in high dimensions from demonstrations.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Learning parametric constraints in high dimensions from demonstrations

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.369797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 21939fd4-3c55-4aab-926a-02026b1d445d · outbound

This paper cites Risk-constrained reinforcement learning with percentile risk criteria.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Risk-constrained reinforcement learning with percentile risk criteria

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.787417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0304cd27-0363-4fa1-83ee-2d8b56a6d9b9 · outbound

This paper cites Deep learning, volume 1.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Deep learning, volume 1

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.790694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63a886f0-4c05-4dab-a4b0-f23f8a7ca69b · outbound

This paper cites Bullet-safety-gym: A framework for constrained reinforcement learning.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Bullet-safety-gym: A framework for constrained reinforcement learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.793818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed77f75e-10c0-4da8-ba88-054c55c5034f · outbound

This paper cites Learning to walk in the real world with minimal human effort.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Learning to walk in the real world with minimal human effort

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.330965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f6d8eca7-a32a-4d97-8139-21495b724518 · outbound

This paper cites The elements of statistical learning: data mining, inference, and prediction, 2017.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels The elements of statistical learning: data mining, inference, and prediction, 2017

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.318986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c7a918ad-8c00-4362-8307-eae79965236d · outbound

This paper cites Safety gymnasium: A unified safe reinforcement learning benchmark.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Safety gymnasium: A unified safe reinforcement learning benchmark

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.307135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 50096365-36ce-430a-8596-6bcb5eb797b5 · outbound

This paper cites Omnisafe: An infrastructure for accelerating safe reinforcement learning research.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Omnisafe: An infrastructure for accelerating safe reinforcement learning research

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.295065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f2e5b44e-a3ce-4a45-acf6-a8b96c5c1638 · outbound

This paper cites Deep reinforcement learning for autonomous driving: A survey.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Deep reinforcement learning for autonomous driving: A survey

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.809239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd1a32a3-297a-4af5-b740-3b28218f924b · outbound

This paper cites Penalizing side effects using stepwise relative reachability.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Penalizing side effects using stepwise relative reachability

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.812315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec1e86aa-62e4-4508-9231-0f97879f70ca · outbound

This paper cites an unresolved cited work.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:36:42.273954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0c556bd0-9fa8-4448-8114-23590d18e721 · outbound

This paper cites Benchmarking constraint inference in inverse reinforcement learning.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Benchmarking constraint inference in inverse reinforcement learning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.262088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e003f9f4-82d2-4e0e-a976-580469585b0a · outbound

This paper cites Datasets and benchmarks for offline safe reinforcement learning.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Datasets and benchmarks for offline safe reinforcement learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.821476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93c0d676-8997-45ae-8b0c-95ac9977220e · outbound

This paper cites Inverse constrained reinforcement learning.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Inverse constrained reinforcement learning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.239202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b3ae1378-4288-412f-90b7-3938adbfe0e0 · outbound

This paper cites Algorithms for inverse reinforcement learning.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Algorithms for inverse reinforcement learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.827433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29e35af0-9cfb-4b0b-9b29-1f38567331a6 · outbound

This paper cites Puterman.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Puterman

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.218787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 480eab5c-7607-40a5-a969-021318ced5d9 · outbound

This paper cites Benchmarking Batch Deep Reinforcement Learning Algorithms.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Benchmarking Batch Deep Reinforcement Learning Algorithms

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.833362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7a87914-3372-4822-adec-9b4da6ad4d70 · outbound

This paper cites Catastrophic forgetting, rehearsal and pseudorehearsal.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Catastrophic forgetting, rehearsal and pseudorehearsal

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.207648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8d762e3b-84bb-4186-a81d-a7db9fe61b41 · outbound

This paper cites Avoiding negative side effects due to incomplete knowledge of AI systems.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Avoiding negative side effects due to incomplete knowledge of AI systems

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.195544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6214cded-eada-48ae-abd4-8e8b597252c0 · outbound

This paper cites Avoiding negative side effects of autonomous systems in the open world.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Avoiding negative side effects of autonomous systems in the open world

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.181858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation eddb70d4-b60a-4d50-9b66-41dd6f60c555 · outbound

This paper cites Proximal Policy Optimization Algorithms.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Proximal Policy Optimization Algorithms

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.845203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa8c6021-b0a0-4bf2-977b-8c4b572e0fd1 · outbound

This paper cites Preferences implicit in the state of the world.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Preferences implicit in the state of the world

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.169376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d77d9460-905e-4cd2-bf2e-300e33bf7462 · outbound

This paper cites Responsive safety in reinforcement learning by pid lagrangian methods.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Responsive safety in reinforcement learning by pid lagrangian methods

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.156624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 63316d3f-87ba-45e9-8840-0b44beb65e24 · outbound

This paper cites Introduction to reinforcement learning, 1998.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Introduction to reinforcement learning, 1998

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.144729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 11a5385d-7207-4a31-b213-81a098d25e7e · outbound

This paper cites Reward constrained policy optimization.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Reward constrained policy optimization

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.126432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0f7d8899-f112-4283-a6a0-d259817bd5bf · outbound

This paper cites Mujoco: A physics engine for model-based control.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Mujoco: A physics engine for model-based control

Reference 31

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-16T12:36:41.957688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 04b6c6d2-fa03-4468-ab37-007352c1ef8a · outbound

This paper cites Avoiding side effects in complex environments.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Avoiding side effects in complex environments

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.108917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 88ca42f7-1b6d-4758-a71b-3fbe2d100e57 · outbound

This paper cites Conservative agency via attainable utility preservation.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Conservative agency via attainable utility preservation

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.092787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4b283082-b5c4-4357-a4a7-16f7b6cf2d0f · outbound

This paper cites Minimax-regret querying on side effects for safe optimality in factored markov decision processes.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Minimax-regret querying on side effects for safe optimality in factored markov decision processes

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.077061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b227f4fb-8f39-4938-90f0-7503fa21b151 · outbound

This paper cites Deep reinforcement learning for power system applications: An overview.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Deep reinforcement learning for power system applications: An overview

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:36:42.062029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9a90f31d-231d-45de-ba73-667e7d84ebba · outbound

This paper cites write newline.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels write newline

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.875365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7103a27f-e484-41c4-9850-26b1ce66548b · outbound

This paper cites @esa (Ref.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels @esa (Ref

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.879800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edec5826-2e65-4a3e-b885-4dbdff15b48d · outbound

This paper cites an unresolved cited work.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.883847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a0f0014-6cf0-4473-99f4-92e1dff401ba · outbound

This paper cites an unresolved cited work.

TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T12:36:41.887506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.