Paper Citation Record · LEDGER

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data

As of 4 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 0 inbound Pith citation observations for arXiv:2605.15417.

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

pith.paper-citation-record.v1
2605.15417 v1

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-19T16:00:39.078055Z

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+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

13 of 13 outbound references displayed

verified exact0
verified fuzzy7
unresolved4
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9b1d4c80-0ce7-4b63-878f-a2b528b33025 · outbound

This paper cites 20251026.

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data 20251026

Reference 1

Resolution: malformed identifier; doi_truncated, observed 2026-05-19T16:02:38.443349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1b1c9134-9953-4af1-8d9a-5ead138f5c49 · outbound

This paper cites an unresolved cited work.

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-05-19T16:02:39.640787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 47da5985-2fba-4832-a600-227f2d7484f6 · outbound

This paper cites an unresolved cited work.

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-05-19T16:02:39.633181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 85fbb3ab-f941-40f8-8276-1a70e07ecadc · outbound

This paper cites an unresolved cited work.

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-05-19T16:02:39.638385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4567574c-8942-4d80-b9ae-58f9fe29c403 · outbound

This paper cites •Gradient Weight: wDG i = ∆i −E B[∆(y)].

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data •Gradient Weight: wDG i = ∆i −E B[∆(y)]

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T16:02:39.635772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3f821bbf-5c1f-41dd-96f0-d38e2d6a0603 · outbound

This paper cites •Gradient Weight: wDG i = 1− e−∆i EB[e−∆(y)].

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data •Gradient Weight: wDG i = 1− e−∆i EB[e−∆(y)]

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T16:02:39.642817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b5c4e892-f19c-46e8-8fbc-045be4412407 · outbound

This paper cites •Gradient Weight: wDG i = e∆i EB[e∆(y)] −1.

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data •Gradient Weight: wDG i = e∆i EB[e∆(y)] −1

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T16:02:39.622129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6f6c3890-c59c-495b-8c78-5985698b5582 · outbound

This paper cites •Gradient Weight: wDG i = 1 2 1− e−2∆i EB[e−2∆(y)].

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data •Gradient Weight: wDG i = 1 2 1− e−2∆i EB[e−2∆(y)]

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T16:02:39.616358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6f4d4c19-1634-4c16-befe-8657f95b74a2 · outbound

This paper cites 22 f-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs •Gradient Weight: wDG i = 2 1− e−∆i/2 EB[e−∆(y)/2].

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data 22 f-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs •Gradient Weight: wDG i = 2 1− e−∆i/2 EB[e−∆(y)/2]

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T16:02:39.619481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e4212b6a-8e1d-475e-8cec-415738e617d5 · outbound

This paper cites •Gradient Weight: wDG i =sgn(∆ i −Median({∆(y)})).

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data •Gradient Weight: wDG i =sgn(∆ i −Median({∆(y)}))

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T16:02:39.624839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 12f132f5-a898-4106-9d41-cecc8c96a1a0 · outbound

This paper cites •Gradient Weight: wDG i = 1 α−1 e(α−1)∆i EB[e(α−1)∆(y)] −1 E.

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data •Gradient Weight: wDG i = 1 α−1 e(α−1)∆i EB[e(α−1)∆(y)] −1 E

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T16:02:39.627394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1d088c6e-9c60-48ef-9eb9-1967c1514c44 · outbound

This paper cites an unresolved cited work.

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-05-19T16:02:39.630083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6d1b84c6-2333-4d16-991b-ce9bca8a9ef4 · outbound

This paper cites We also provide the following plots for on policy training with the same losses, showing a similar trend: (a)JSD vs.

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data We also provide the following plots for on policy training with the same losses, showing a similar trend: (a)JSD vs

Reference 13

Resolution: malformed identifier; raw_fallback, observed 2026-05-19T16:02:39.613432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

No inbound Pith citation observations are available.