Pith. sign in

Paper Citation Record · LEDGER

Unsupervised Discovery of Failure Taxonomies from Deployment Logs

As of 8 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2506.06570.

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

pith.paper-citation-record.v1
2506.06570 v4

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T06:00:06.425719Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

49 of 49 outbound references displayed

  • verified exact2
  • verified fuzzy36
  • unresolved11
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9b01ae53-4cd7-4d6b-8443-50acc24c33d6 · outbound

This paper cites Wod-e2e: Waymo open dataset for end-to-end driving in challenging long-tail scenarios,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Wod-e2e: Waymo open dataset for end-to-end driving in challenging long-tail scenarios,

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T06:00:06.312293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T06:00:06.312293Z digest=sha256:74088f5d29a790e2d4d82bf1ca5e3dbc81269f5fd97fc6d290c07b10b617af32

Observation 51fd2eb9-9155-49b5-a431-296371adb40f · outbound

This paper cites REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T06:00:06.315414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T06:00:06.315414Z digest=sha256:9da6887fd921f98634493c622f5005ff0d1ded62341d90d6fa2d7d7ec9777562

Observation 68d689ad-07fa-4e28-a035-36e81a2aa6b9 · outbound

This paper cites AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T06:00:06.318287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T06:00:06.318287Z digest=sha256:7d3f88a379a9d7a14562079968d036311d2fcc7ed33848317fef554c8c6fc2fe

Observation 2a6e4f38-f211-4265-aac4-86bce238a22e · outbound

This paper cites Robofac: A comprehensive framework for robotic failure analysis and correc- tion,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Robofac: A comprehensive framework for robotic failure analysis and correc- tion,

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:11.086652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.320962Z digest=sha256:bb3e7cd186df1470c31b0c2286edbb4bcece44868a72e6b40c38c73490d8d4c3

Observation 9c0d5737-0051-4540-810c-01683666afce · outbound

This paper cites Self-refining vision language model for robotic failure detection and reasoning,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Self-refining vision language model for robotic failure detection and reasoning,

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:10.918240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.323744Z digest=sha256:d9b6cc92de29ef34874c1f09b3c06675575014f6283db679bec8b25f53e426a2

Observation 069f23be-ff71-49e0-a2fb-e7ba930d9495 · outbound

This paper cites Guardian: Detecting robotic planning and execution errors with vision-language models,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Guardian: Detecting robotic planning and execution errors with vision-language models,

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T06:00:06.326210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T06:00:06.326210Z digest=sha256:3f95be45a24d8be647e5567f5648a96e1a9c172fa06e97ab83d1b82833ca6529

Observation 660d140d-99e9-44b4-a1e7-ac4f54692b27 · outbound

This paper cites Image Clustering Conditioned on Text Criteria.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Image Clustering Conditioned on Text Criteria

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T06:00:06.328808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T06:00:06.328808Z digest=sha256:42978e674108eb67b5f04c258c65ac800aeafda2faa1ee3aa5a6fdd2fcb9d63e

Observation d5675d9e-7b73-49c3-8186-c013ea585661 · outbound

This paper cites Organizing Unstructured Image Collections using Natural Language.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Organizing Unstructured Image Collections using Natural Language

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T06:00:06.331317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T06:00:06.331317Z digest=sha256:5df1a51f1825e1fb4af95ec6aed37e344193ae741cef3463420ea3dac3ae49f0

Observation 9a1f8aa4-9d77-41d1-8da9-7f3a8de84855 · outbound

This paper cites Describing differences in image sets with natural language,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Describing differences in image sets with natural language,

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:10.757969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.333790Z digest=sha256:c5b51a053189608337104df878ad7b96675ab50168eff9314e083271c9777b14

Observation f45f562b-dff1-4238-96eb-f4f1aac15b55 · outbound

This paper cites Llm as dataset analyst: Subpopulation structure discovery with large language model,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Llm as dataset analyst: Subpopulation structure discovery with large language model,

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:10.550363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.335905Z digest=sha256:4be62fe48fd098ee341f13dfb077e37c987ad9ca6802273f1b58a3efdedfd02e

Observation 329e046e-81b6-466d-a771-077316ffc122 · outbound

This paper cites SSE: Multimodal Semantic Data Selection and Enrichment for Industrial-scale Data Assimilation.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs SSE: Multimodal Semantic Data Selection and Enrichment for Industrial-scale Data Assimilation

Reference 11

Resolution
verified exact
local_arxiv, observed 2026-08-07T06:00:06.562872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.337944Z digest=sha256:763cdf78352a1d4004f98edd271066d932a82f3afb072387c4f0d7495d70c58f

Observation 0157a3d4-1623-4f26-adf7-948ed8c32df5 · outbound

This paper cites Octis: Comparing and optimizing topic models is simple!.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Octis: Comparing and optimizing topic models is simple!

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:10.425865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.340405Z digest=sha256:a6204c5519958f2cfe620721fefe716b72d79fea7388ff46f9b5cd4ca7d13e1b

Observation f3c0e99b-1640-465e-8b34-07cc2c39ea4e · outbound

This paper cites Topic modelling meets deep neural networks: A survey,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Topic modelling meets deep neural networks: A survey,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:10.268770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.342835Z digest=sha256:e8207cf748326cb9c7369eb9fc567fc9cd09f91e13d4431b7f7ab950898c2018

Observation cc9322f6-223b-465e-9e29-d3ecafc64df7 · outbound

This paper cites A neural autoregressive topic model,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs A neural autoregressive topic model,

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:10.119216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.345131Z digest=sha256:1d3ca939a4b1a2f3b54b5dc10cb1900475a7229cd6c6b7668866d3335e28eb41

Observation 9867d4fd-2ea9-4205-96d0-d6759114a4d5 · outbound

This paper cites A novel neural topic model and its supervised extension,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs A novel neural topic model and its supervised extension,

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:10.011960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.347309Z digest=sha256:18a4cd67f983676c02ecf8b26557a1dfa7e0f7089c05ea6cf3d42544a9f6dda3

Observation 6deed8c6-6fc8-4ffa-9ee4-b7465c5b1b6c · outbound

This paper cites Topic modeling over short texts by incorporating word embeddings,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Topic modeling over short texts by incorporating word embeddings,

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:09.913422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.349513Z digest=sha256:a55ffd843b4b80206f27563879fbdf6fb2e915cb548da140865bb6340b8ba552

Observation 3d14aec8-e8be-4287-9b86-1b9b21c2934e · outbound

This paper cites We-lda: A word embeddings augmented lda model for web services clustering,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs We-lda: A word embeddings augmented lda model for web services clustering,

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:09.812464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.351679Z digest=sha256:3005e52bf1bcf13df9cdef91c5b6404e87e72ba43796ecab2a3018339cff9080

Observation 5a261537-9733-429b-bff3-3ecf505d8b5d · outbound

This paper cites Improving topic models with latent feature word representations,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Improving topic models with latent feature word representations,

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:09.692570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.354139Z digest=sha256:ef2a025323ee57a8c8a2948b00465aaf53bd711b4aaad5d60b324a883309d930

Observation 10dfd29f-ee23-4685-aa34-030c7b762a18 · outbound

This paper cites Topical word embeddings,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Topical word embeddings,

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:09.540352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.356384Z digest=sha256:2b70aba49e6a8adfb90395c24242affa1d63cba1b298d7334f4d4fbacfa51bc4

Observation 4eb8d20a-fc72-4c43-bf11-477dbcfdc3ca · outbound

This paper cites Cross- lingual contextualized topic models with zero-shot learning,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Cross- lingual contextualized topic models with zero-shot learning,

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:09.410865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.358478Z digest=sha256:f0283da3858534f2821ed7712de055592ffcba548fd613c7f4c37e79c4358580

Observation 041f770f-7e25-4099-9a4c-e149020272e6 · outbound

This paper cites Topic modeling in embedding spaces,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Topic modeling in embedding spaces,

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:09.238606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.360925Z digest=sha256:33e4025f53388c645ec3edffc5cc42f4fa35c0c3aa81bc2a6368de03a926f07f

Observation 27f91cf8-f7ef-4d9c-9076-84d4ec21a16e · outbound

This paper cites Topic modeling with contextualized word representation clusters,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Topic modeling with contextualized word representation clusters,

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:09.134348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.363098Z digest=sha256:e5cd25de5a6947b9d4521259e7f549f10969fab09e80e798084a31a27700fa1a

Observation 95ec21c5-4f78-428b-b9ef-ccd041c8b059 · outbound

This paper cites Pre-training is a hot topic: Contextualized document embeddings improve topic coherence,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Pre-training is a hot topic: Contextualized document embeddings improve topic coherence,

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:08.976450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.365338Z digest=sha256:ed57df8a316f12c7fb1b0da2958e076bcb98858d50280ecd53305c241b9f8687

Observation a17c2cd0-8fa5-4d82-89bd-34713f7c37fb · outbound

This paper cites Tired of topic models? clusters of pretrained word embeddings make for fast and good topics too!.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Tired of topic models? clusters of pretrained word embeddings make for fast and good topics too!

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:08.845981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.367626Z digest=sha256:8831e7643516f31e86ffcc1c3020a2052e80963f1c46fc54018ca8e61d57fd6e

Observation 200de2df-c9d1-49b2-953b-a3405d6a0bce · outbound

This paper cites Top2vec: Distributed representations of topics,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Top2vec: Distributed representations of topics,

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:08.699557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.369691Z digest=sha256:670970ffd24186e90a314c7e7047df2db4f415bcccbf25d2179e4b21b7a19282

Observation 395429fc-edb0-41d5-84b0-63a20c4d082e · outbound

This paper cites Bertopic: Neural topic modeling with a class- based tf-idf procedure,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Bertopic: Neural topic modeling with a class- based tf-idf procedure,

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:08.529871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.371830Z digest=sha256:568628866c1ff3ba7d37531e007c38c75131146709ed6f546cabf12326057be0

Observation a23571f0-49f1-4308-ab57-43ecd2c9ac5b · outbound

This paper cites A Scenario-Based Platform for Testing Autonomous Vehicle Behavior Prediction Models in Simulation.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs A Scenario-Based Platform for Testing Autonomous Vehicle Behavior Prediction Models in Simulation

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T06:00:06.374321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T06:00:06.374321Z digest=sha256:43ed9cf58b9ec3ed35769ed4a6ed35241ade14699526e22b06e0957526e7bc3b

Observation 004e9c0e-93d6-4ef0-934c-930d89c2155b · outbound

This paper cites Formal scenario-based testing of autonomous vehicles: From simulation to the real world,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Formal scenario-based testing of autonomous vehicles: From simulation to the real world,

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:08.370083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.377091Z digest=sha256:cd4bdbf40543d81fe2ba19bee2fe124ff3c2e8a34ebef16ce818bc5ce2f91953

Observation 07e1edc0-23e4-4f68-b3e9-cd40ffe04ab2 · outbound

This paper cites Systematic Testing of Convolutional Neural Networks for Autonomous Driving.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Systematic Testing of Convolutional Neural Networks for Autonomous Driving

Reference 29

Resolution
verified exact
local_arxiv, observed 2026-08-07T06:00:06.544781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.379453Z digest=sha256:ed41c7cbd2e5afbdfe2dad4520abf684fbdd057f3907473c3c7fd6b0120e483f

Observation 8fd0dd93-13da-4f7f-bbe4-889746d7fcda · outbound

This paper cites Safety-Aware Imitation Learning via MPC-Guided Disturbance Injection.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Safety-Aware Imitation Learning via MPC-Guided Disturbance Injection

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T06:00:06.381907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T06:00:06.381907Z digest=sha256:5158a578ca0c1f1459b4c49976c4c860fce3dfcb2b76ade2db606deccf93c528

Observation 8114a0d2-a562-4374-90e6-959b044071da · outbound

This paper cites Verifai: A toolkit for the formal design and analysis of artificial intelligence-based systems,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Verifai: A toolkit for the formal design and analysis of artificial intelligence-based systems,

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:08.216596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.384380Z digest=sha256:ac8c69bd373da63536503e07b5d3862c759dfaa8e47a82f38a110343d3efdef0

Observation 894cb62f-11ea-4c01-96e2-90f5faa8acb1 · outbound

This paper cites Formal certification methods for automated vehicle safety assessment,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Formal certification methods for automated vehicle safety assessment,

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:08.015483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.386555Z digest=sha256:01c19fee230285fa961f56358ad729e2b2116a5b8f76b54e157bc1afada2c7c3

Observation 7e913168-48f4-449e-896f-f4711a1c3fb3 · outbound

This paper cites Counterexample- guided synthesis of perception models and control,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Counterexample- guided synthesis of perception models and control,

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:07.761516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.388721Z digest=sha256:d85497465232e09fe11d1a5e1345d5302676eabb3d2c22a2bce479847bc45fb2

Observation 6e73cd73-e5eb-45fe-8d5c-d9d879a5db77 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Chain-of-thought prompting elicits reasoning in large language models,

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:07.520888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.390796Z digest=sha256:c4f9186aa4ef6962c55ce0253beaf331b92e156da2e78cbde637fb1eabd075e6

Observation fca59e73-25d5-4ad3-9c19-63f8f7555021 · outbound

This paper cites Large Language Models as Optimizers.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Large Language Models as Optimizers

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T06:00:06.393043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T06:00:06.393043Z digest=sha256:95b068e9bc9d90b691a1b4abfb6e23c67d9ab5af412ca9fe7dc5c6879d9f9890

Observation 9475b8d0-c9fa-49d4-b9d0-85db95bf8dee · outbound

This paper cites Calibrate before use: Improving few-shot performance of language models,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Calibrate before use: Improving few-shot performance of language models,

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:07.287538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.395399Z digest=sha256:3e9d4deb18bccc8564b76e140ce81682f21eb7cad8a9854105cafeb7173029dc

Observation 811413aa-0659-42a1-b869-6ec4c01dd311 · outbound

This paper cites Self-refine: Iterative refinement with self- feedback,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Self-refine: Iterative refinement with self- feedback,

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:07.057626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.397734Z digest=sha256:54aeee2dea0358362a554a7c57a94dfac1d7a408f5e58fb89a07967c041571a2

Observation 8034ecc4-13eb-40e5-9ed2-b6a63e80d4ec · outbound

This paper cites Test-time recursive thinking: Self-improvement without external feedback,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Test-time recursive thinking: Self-improvement without external feedback,

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-07T06:00:06.399749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T06:00:06.399749Z digest=sha256:7b57ca32d0b833ffa726cf29fa22ac6f24deed2b0bec9d6c09721289fc3d34cc

Observation 4f31a243-d984-40c1-8b90-ae62e40b1a26 · outbound

This paper cites Nexar dashcam collision predic- tion dataset and challenge,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Nexar dashcam collision predic- tion dataset and challenge,

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:06.965272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.401861Z digest=sha256:b5945a6024dc3c758d7fd26f7bc23fe18026159767ade34d2a15d6b8b0da87f9

Observation 87fa23da-b11c-4f18-b55e-ff0c850bd945 · outbound

This paper cites Pre-crash scenario typology for crash avoidance research,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Pre-crash scenario typology for crash avoidance research,

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:06.917314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.403991Z digest=sha256:4111f0021f3b5cdbb3eda170c9cc6b1894b45174e670d465cba22127f3dcf259

Observation 3459eb67-686f-4056-adbe-3fe8798e2d54 · outbound

This paper cites Com- bining optimal control and learning for visual navigation in novel environments,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Com- bining optimal control and learning for visual navigation in novel environments,

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:06.865730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.406416Z digest=sha256:132f7523194ce8401b79eac5e59537b0305d295deba8d4b8f23029bf5bcd1e18

Observation 180815c8-7b19-4f81-b073-2b13c1979ee2 · outbound

This paper cites 3d semantic parsing of large-scale indoor spaces,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs 3d semantic parsing of large-scale indoor spaces,

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:06.826709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.408798Z digest=sha256:a755e80a31134530bb91bf78dda3fdb6119d32d48b586a727c2c532ac855ec90

Observation a6ac769e-b021-4d49-8824-31733bb22e0e · outbound

This paper cites Discovering closed-loop failures of vision-based controllers via reachability analysis,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Discovering closed-loop failures of vision-based controllers via reachability analysis,

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:06.788979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.410942Z digest=sha256:c0dba79bb91578f726175a27f0f8bcf55d6b6a591c6c6765dcc890027526be87

Observation 9b23b7db-12e9-40c7-a774-55d021fc2b6c · outbound

This paper cites Semantic anomaly detection with large language models,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Semantic anomaly detection with large language models,

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:06.753719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.413120Z digest=sha256:d964ab94de0bc1065804f7a9d5b2867b26d44f18db312c25e83a73b7201e86e4

Observation df7dddd1-a797-4da3-bf1d-632b3d4d150e · outbound

This paper cites Videomae v2: Scaling video masked autoencoders with dual masking,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Videomae v2: Scaling video masked autoencoders with dual masking,

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:06.743279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.415380Z digest=sha256:69c3dc63a854b1da5968ae2773de074a5f0c59f90cf7ede3d4d9b66d754a7f3c

Observation 39a9147f-6fe5-4590-8131-40447a44d8f0 · outbound

This paper cites Enhancing Safety and Robustness of Vision-Based Controllers via Reachability Analysis.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Enhancing Safety and Robustness of Vision-Based Controllers via Reachability Analysis

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-07T06:00:06.417708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T06:00:06.417708Z digest=sha256:dc866e01d11cc66c08ddcc6db293dc1575118a32c95c54209b246a923c6ca77e

Observation c5977642-5835-4177-a291-518969d576cd · outbound

This paper cites Detecting and mitigat- ing system-level anomalies of vision-based controllers,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Detecting and mitigat- ing system-level anomalies of vision-based controllers,

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:06.735401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.420057Z digest=sha256:2747d5754ece6cf36e44455cb73754fcc83eb43bc3106904fcb7f703173f78cf

Observation 3ddadca1-037b-4120-a8ad-20dbbbf8a050 · outbound

This paper cites Counterexample-guided data aug- mentation,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Counterexample-guided data aug- mentation,

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:06.728089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.422252Z digest=sha256:ea3126dfaaef1bc3f7015ac7cd3ff410580b1197adcc9f80b9c093b5f5a7bc5f

Observation 552c4c7e-2dd8-4b6b-8336-e8704ac90b28 · outbound

This paper cites Specification-guided data aggregation for semantically aware imitation learning,.

Unsupervised Discovery of Failure Taxonomies from Deployment Logs Specification-guided data aggregation for semantically aware imitation learning,

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T06:00:06.719196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T06:00:06.425719Z digest=sha256:70800621f19bf6e830bf97b399b642b4b0d970a52774807a3ee4230542e7d0a9

Pith citing papers

No inbound Pith citation observations are available.