Pith. sign in

Paper Citation Record · LEDGER

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

As of 22 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 1 inbound Pith citation observation for arXiv:2606.31825.

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

pith.paper-citation-record.v1
2606.31825 v1

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-01T06:03:12.182207Z

measured 14 of 14 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-08T05:22:50.462331Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-08T05:24:31.802601Z

Reference resolution

13 of 13 outbound references displayed

  • verified exact3
  • verified fuzzy5
  • unresolved2
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 391de103-519a-486b-b9ea-c60ed180301b · outbound

This paper cites arXiv preprint arXiv:2503.13939 , year=.

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning arXiv preprint arXiv:2503.13939 , year=

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-07-01T09:55:40.921648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-01T06:03:12.182207Z digest=sha256:46096fbc52415d57338a52899e6f762cf1f89020ff4c177f28b5bbd4b70e7946

Observation bef98d89-4b53-4285-9591-c3ef4a30bfed · outbound

This paper cites Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos.

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos

Reference 2

Resolution
metadata mismatch
arxiv_id, observed 2026-07-01T09:55:40.928780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-01T06:03:12.182207Z digest=sha256:9f958e7050e6a19ea7b1e55b9d0869aab73500afeb128085bec499932df56561

Observation 1d1d2a86-09f8-4388-80bf-ea728822a117 · outbound

This paper cites Gtpo and grpo-s: Token and sequence-level reward shaping with policy entropy.arXiv preprint arXiv:2508.04349.

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Gtpo and grpo-s: Token and sequence-level reward shaping with policy entropy.arXiv preprint arXiv:2508.04349

Reference 3

Resolution
verified exact
arxiv_id, observed 2026-07-01T09:55:40.925415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-01T06:03:12.182207Z digest=sha256:e77e4726b2809fa4205a302744d0f1e7b934bbfad016bb233f0ab1136b272d5a

Observation 847f69e5-aa7a-4c5d-9380-c41f42571d61 · outbound

This paper cites arXiv preprint arXiv:2506.13793 (2025).

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning arXiv preprint arXiv:2506.13793 (2025)

Reference 4

Resolution
metadata mismatch
arxiv_id, observed 2026-07-01T09:55:40.932224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-01T06:03:12.182207Z digest=sha256:cdc728b1030e8f444638d7dcbb448b948e60644d6d09a6c32cc3744a828c015a

Observation 4c54032d-1369-4b42-9250-a271c57e6cd2 · outbound

This paper cites Medgr ^ 2 : Breaking the data barrier for medical reasoning via generative reward learning.

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Medgr ^ 2 : Breaking the data barrier for medical reasoning via generative reward learning

Reference 5

Resolution
metadata mismatch
arxiv_id, observed 2026-07-01T09:55:40.922027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-01T06:03:12.182207Z digest=sha256:ef199466c473e19d09324985543172cddfaac7bb42ab9d7d6b32e43d35561fd8

Observation 8f5369d4-37b6-40b6-973f-e20775bf7b0c · outbound

This paper cites Our imple- mentation builds on VLM-R1 (Shen et al., 2025), an open-source GRPO framework for VLMs.

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Our imple- mentation builds on VLM-R1 (Shen et al., 2025), an open-source GRPO framework for VLMs

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T19:42:52.016022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-01T06:03:12.182207Z digest=sha256:8045f128e5d25b85c619037e64d0e340216b6b81c898c2705542d23f04dbc76b

Observation 880a61e7-868c-4a23-ab28-0d2b83701c18 · outbound

This paper cites consistent with.

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning consistent with

Reference 7

Resolution
verified exact
arxiv_id, observed 2026-07-01T09:55:40.919462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-01T06:03:12.182207Z digest=sha256:e8668854bac9a2677caad801eddc8314f07da91038e5c6bc8566c9bb5c34d17e

Observation f1b47ad8-bb2a-49e2-911e-0153f571c989 · outbound

This paper cites Step2 It has a deep reddish-brown color, a lobulated shape, and a granular, nodular cut surface.

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Step2 It has a deep reddish-brown color, a lobulated shape, and a granular, nodular cut surface

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T19:42:52.007455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-01T06:03:12.182207Z digest=sha256:dcaee56643649da3687c5000348010dd8256a5b049b6712fba777060a1125034

Observation ea312527-37a9-4c37-8b32-21d584feb6f5 · outbound

This paper cites an unresolved cited work.

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Unresolved cited work

Reference 9

Resolution
unresolved
raw_fallback, observed 2026-07-06T19:42:52.005101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-01T06:03:12.182207Z digest=sha256:d088f701ed001a7190330e7d11ab8f4e5b34e3ce1c70c5d2ac1ca4be169806a6

Observation 1a381f95-1bc9-498a-890a-ef5224ae6e2b · outbound

This paper cites Step2 The dark regions in and around the liver look like fluid, suggesting a fluid- sensitive T2 sequence.

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Step2 The dark regions in and around the liver look like fluid, suggesting a fluid- sensitive T2 sequence

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T19:42:52.009928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-01T06:03:12.182207Z digest=sha256:11ba41702a0928d2cf015425259e297e6f27167f9707c6d9634932ca2a9006eb

Observation 9d09fcc0-7c04-4877-94b4-a857eddab13d · outbound

This paper cites an unresolved cited work.

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Unresolved cited work

Reference 11

Resolution
unresolved
raw_fallback, observed 2026-07-06T19:42:52.017932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-01T06:03:12.182207Z digest=sha256:9c5d7a349435024d45fa16c28968df89607f66cf755a6e35e24c9b29e3c5a40b

Observation 6d724102-70fa-4c29-b98e-7a25e18d61aa · outbound

This paper cites lobulated,.

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning lobulated,

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T19:42:52.011750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-01T06:03:12.182207Z digest=sha256:95a249c08fc502b354c8b3f4b039163f01374fe20468624a5b0298d209cb8936

Observation 435e1e5a-80ec-4845-b10a-d888ae7869d8 · outbound

This paper cites lobulated.

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning lobulated

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-07-06T19:42:52.013434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-01T06:03:12.182207Z digest=sha256:09e830a383f2fac8e2a2397736dd24c2bd528df7cd8203d31be05162688d4e5d

Pith citing papers

Observation e32c882c-8e53-4c7e-a5b8-867115386abb · inbound

From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b cites this paper.

From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

Reference 7

Resolution
verified exact
local_arxiv, observed 2026-07-08T05:24:31.804241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-07-08T05:22:50.462331Z digest=sha256:3db9db09b5e795b16a41b41603e518eee6abdd4131fca44a1936f0af4f81c7ce