Pith. sign in

Paper Citation Record · LEDGER

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization

As of 18 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 1 inbound Pith citation observation for arXiv:2504.18026.

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

pith.paper-citation-record.v1
2504.18026 v4

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:32:52.346773Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-21T05:46:42.018851Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-21T05:49:41.004360Z

Reference resolution

27 of 27 outbound references displayed

  • verified exact2
  • verified fuzzy5
  • unresolved20
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a1e809b6-201d-496b-91ba-2ccec29e57f1 · outbound

This paper cites an unresolved cited work.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Unresolved cited work

Reference 4

Resolution
unresolved
raw_fallback, observed 2026-08-16T10:32:52.794727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-16T10:32:52.342825Z digest=sha256:ca480df4259d44183bada852ba0c4a7ce3855f21ae10be9bcc04e1c5cec3147e

Observation e95794fe-aaa6-4b2c-bfc5-4338b584ff5f · outbound

This paper cites Categorical Reparameterization with Gumbel-Softmax.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Categorical Reparameterization with Gumbel-Softmax

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.259694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.259694Z digest=sha256:c35116b687c604edb6c3e1925e74d989b858c9b68e6d715d1da0fdb302ce535c

Observation 0e549341-0767-4bfc-a553-e96b4382158e · outbound

This paper cites Auto-Encoding Variational Bayes.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Auto-Encoding Variational Bayes

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.268296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.268296Z digest=sha256:c7e7d1479c1889dacdcbe8750221edc10839336b1996576ec90d59bdb5d8e90f

Observation 0079a857-2ee3-49f1-b19c-ebff7a8fdfb9 · outbound

This paper cites When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.276927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.276927Z digest=sha256:dc88083617635dd52d1a938438b3de3b47256a33f37b3c1f6428287d43c1bcfa

Observation a92f3e4b-9f38-4717-9a98-fdfbf0156b57 · outbound

This paper cites URL https://doi.org/ 10.1145/1458082.1458092.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization URL https://doi.org/ 10.1145/1458082.1458092

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.288735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.288735Z digest=sha256:1fe32bfba6ac681e77ea249bc4f5ca197100455fd33ff9524780d253b1beeed8

Observation ee393e61-5e80-4b21-953c-dfb618f2eb58 · outbound

This paper cites Training language models to follow instructions with human feedback.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Training language models to follow instructions with human feedback

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.284859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.284859Z digest=sha256:5859d927cc8331cb75f1565a62ee639bc38cf03bbac6d0a30d881e4c4640e3a1

Observation 2b07a200-e6c2-4c57-900f-c0d537021bc3 · outbound

This paper cites an unresolved cited work.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Unresolved cited work

Reference 12

Resolution
unresolved
raw_fallback, observed 2026-08-16T10:32:52.782584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-16T10:32:52.346773Z digest=sha256:84f159f8eb14b5f201ac85b28442f8bce4522b5ca21671b70493052b485f2705

Observation efe3ef62-1572-45f8-bf43-43bc708bd7f7 · outbound

This paper cites cc/paper_files/paper/2021/file/ 60ce36723c17bbac504f2ef4c8a46995-Paper.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization cc/paper_files/paper/2021/file/ 60ce36723c17bbac504f2ef4c8a46995-Paper

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:32:52.862230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-16T10:32:52.292370Z digest=sha256:a8c49527b56cfe7af110876cf47a1b0793974e5ac22967141249e76d1da36092

Observation fe5d3e13-c2b2-455b-a517-76497bae9968 · outbound

This paper cites ImageNet Large Scale Visual Recognition Challenge.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization ImageNet Large Scale Visual Recognition Challenge

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.296272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.296272Z digest=sha256:120860662d23ebb2187b4be218a62e8381c05997790fa5faebcafa2b294c1e58

Observation 11cb7afb-1aba-48ee-be2c-69e299fccee0 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Proximal Policy Optimization Algorithms

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.300358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.300358Z digest=sha256:6a0873cd9672c640cb3bcf9700be55d2f4cea4fcb0ebb2b4b66e32b0f320d55c

Observation 5542aaeb-df2e-4f1c-a4dd-d153db6287f6 · outbound

This paper cites A Closer Look at the Intervention Procedure of Concept Bottleneck Models.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization A Closer Look at the Intervention Procedure of Concept Bottleneck Models

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.303892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.303892Z digest=sha256:4893b052ceefcf7e946da69200c203d72f4402e9b2a28b9ea0de2d26015a3613

Observation 74640d21-9075-4e93-b6ef-6314bbfe80a5 · outbound

This paper cites RLVF: Learning from Verbal Feedback without Overgeneralization.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization RLVF: Learning from Verbal Feedback without Overgeneralization

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.312439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.312439Z digest=sha256:2165d34510c720a2ad63d5557d92fb361bc1684b167ad4a7d65e9e9f3ea8f52c

Observation 4d7189d2-9f9c-4e51-891b-68ff8fdeb268 · outbound

This paper cites The Llama 3 Herd of Models.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization The Llama 3 Herd of Models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.316262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.316262Z digest=sha256:d16825feb09c2e6f3b5274396ccbe675c052fa08fa0c2b309e6de52ae9a988d8

Observation e6228eb6-13ea-452b-a3a9-e82d2979bdcd · outbound

This paper cites Caltech ucsd birds.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Caltech ucsd birds

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:32:52.849871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-16T10:32:52.320218Z digest=sha256:9f9f9d60b05ead081fc60ec5634834dd807527bca7c5aa825777d0516febf1ed

Observation 583e9e21-e880-4e5b-afb1-cc8d533c00d9 · outbound

This paper cites URL https://doi.org/ 10.1145/1553374.1553527.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization URL https://doi.org/ 10.1145/1553374.1553527

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.327684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.327684Z digest=sha256:5b8e518aa474d25431ba4bfc9ee8680a43fed0916e859768fc7a58fcf745c171

Observation 3d64827e-00c7-414c-a0d4-c3fd3b899460 · outbound

This paper cites Following standard procedures, we apply random cropping and flipping to a portion of the images during training.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Following standard procedures, we apply random cropping and flipping to a portion of the images during training

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:32:52.835723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-16T10:32:52.331185Z digest=sha256:5bdf7d4635c1cf85678e9c9ab42f59fd047dd807ca04b714a9819fe54888227a

Observation 71588e0d-3676-4dda-95f2-5a1872cbc69c · outbound

This paper cites The final dataset is composed of∼ 6,000 RGB images of dimension (3,299,299) , and split into a standard 70%-10%-20% train-validation-test split.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization The final dataset is composed of∼ 6,000 RGB images of dimension (3,299,299) , and split into a standard 70%-10%-20% train-validation-test split

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:32:52.809928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-16T10:32:52.339038Z digest=sha256:95dfe8f737124be31af798151953e26d6b0485745ac5a2aa862f9bfc5336c1a8

Observation a9c9f8f1-eae8-40c6-9d6d-824d3087514b · outbound

This paper cites RL with KL penalties is better viewed as Bayesian inference.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization RL with KL penalties is better viewed as Bayesian inference

Reference 2009

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.272951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.272951Z digest=sha256:a63ba9df505533c683d0657a898c3d0ebcc4f2f359f6d3250e1aebe15ed6993a

Observation 447a422c-0d7e-467d-8493-e4e132d9be26 · outbound

This paper cites Online Structured Prediction via Coactive Learning.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Online Structured Prediction via Coactive Learning

Reference 2012

Resolution
verified exact
local_arxiv, observed 2026-08-16T10:32:52.545904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-16T10:32:52.308339Z digest=sha256:e4ba8560f1908264790b4c395c52236336f8cf92b3fdbdf1752adf41ff5a7519

Observation 01fdffbb-3a4a-4617-ba2d-766710aebe74 · outbound

This paper cites Deep Residual Learning for Image Recognition.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Deep Residual Learning for Image Recognition

Reference 2015

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.254225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.254225Z digest=sha256:6d03bde06693d617e9410faf78e61ba1c7c298ea5d1f81a2915f6b25e2baa792

Observation c86d2940-0100-476f-abf1-8c6039b2021e · outbound

This paper cites Reinforcement Learning with Deep Energy-Based Policies.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Reinforcement Learning with Deep Energy-Based Policies

Reference 2017

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.249373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.249373Z digest=sha256:7103224bf8ee48015689ad2499dfd1e455c63d1d8c5eb7fcc80f71e1f26ea7b3

Observation ea44e460-195f-44b3-9bda-f4057bbfa9da · outbound

This paper cites Xu, X., Qin, Y ., Mi, L., Wang, H., and Li, X.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Xu, X., Qin, Y ., Mi, L., Wang, H., and Li, X

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.323963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.323963Z digest=sha256:7997ea051b29d47d61a67292541dab5965daebd6aa4456705cf2fce899620e69

Observation a9e89d1a-899c-4e2a-8f3d-e4455909203a · outbound

This paper cites Our only departure from Koh et al.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Our only departure from Koh et al

Reference 2020

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T10:32:52.821555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-16T10:32:52.334906Z digest=sha256:4bc4b9fe0018ac3d1cf8249d9997023986a76876fdd954d171ad638c7dced057

Observation 40f78c91-8426-4ac3-a6c4-2bd1e8205445 · outbound

This paper cites Preference-based Online Learning with Dueling Bandits: A Survey.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Preference-based Online Learning with Dueling Bandits: A Survey

Reference 2021

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.240130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.240130Z digest=sha256:00f8598995db1fde2b943c9ff2de55a34709561a58842864814839db130a6224

Observation 88e3552b-827e-436c-ba33-3c9292b68169 · outbound

This paper cites Maximum Entropy RL (Provably) Solves Some Robust RL Problems.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Maximum Entropy RL (Provably) Solves Some Robust RL Problems

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.245136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.245136Z digest=sha256:9975c1d3190700068afb42de22076b7ef3a80166dd4ab22e28304625ea146bc8

Observation e8819980-8916-42af-ba7d-4d476fea7345 · outbound

This paper cites Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-16T10:32:52.280893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T10:32:52.280893Z digest=sha256:4b8a67559ca8261651f8e305dfd7f2b6bfe3509a1facd4354576ba76f75bc03e

Observation a88833a5-17aa-4ae7-8096-72210ec94c51 · outbound

This paper cites EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors

Reference 2024

Resolution
verified exact
local_arxiv, observed 2026-08-16T10:32:52.715378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-16T10:32:52.263860Z digest=sha256:80613652f5f617cd061d6c6645e1c9c41b761176aafa7ca136a8e0a1ab411de6

Pith citing papers

Observation 239ce291-df99-474e-b2cc-3f8b55d94226 · inbound

SynCB: A Synergy Concept-Based Model with Dynamic Routing Between Concepts and Complementary Neural Branches cites this paper.

SynCB: A Synergy Concept-Based Model with Dynamic Routing Between Concepts and Complementary Neural Branches Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization

Reference 18

Resolution
verified exact
arxiv_id, observed 2026-05-21T05:49:41.005748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-05-21T05:46:42.018851Z digest=sha256:71852fd6acf2dc420c4b0c96c2258e73e78c342dc30a0974dcbacca89d42522b