Pith. sign in

Paper Citation Record · LEDGER

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories

As of 23 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 4 inbound Pith citation observations for arXiv:2606.05414.

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

pith.paper-citation-record.v1
2606.05414 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T06:02:44.836106Z

measured 32 of 32 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 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T23:23:54.624347Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-08T04:04:29.269379Z

Reference resolution

28 of 28 outbound references displayed

  • verified exact1
  • verified fuzzy0
  • unresolved22
  • parse uncertain0
  • malformed identifier2
  • metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9d24d62d-6b0e-4b38-aefc-4093c9f8710e · outbound

This paper cites Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks

Reference 1

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T08:26:48.334470Z

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=2026-06-28T06:02:44.836106Z digest=sha256:18bb1701985c26c39c7b9fa47632740b7954d0e4c744c7861148091a92a6b9ed

Observation a869f422-7020-4255-8148-c5e6d65657b8 · outbound

This paper cites InProceedings of the 35th International Confer- ence on Machine Learning (ICML), volume 80, pages 2127–2136.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories InProceedings of the 35th International Confer- ence on Machine Learning (ICML), volume 80, pages 2127–2136

Reference 2

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:cf27b5ac80425b09fa9ee6b266dac747a3688f7eec5b9d5b219e8d9891b3cc04

Observation e982bd6d-6a67-4c37-9715-185b4eabd0a0 · outbound

This paper cites Aviral Kumar, Xue Bin Peng, and Sergey Levine.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Aviral Kumar, Xue Bin Peng, and Sergey Levine

Reference 3

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:6f9a7773f9c284b5806c16880384dd1100a1cddf21b5cf7a45e29f4b7776c343

Observation 206569dd-0496-457f-a49c-c357571fcf4e · outbound

This paper cites Reward-Conditioned Policies.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Reward-Conditioned Policies

Reference 4

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T08:26:48.331761Z

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=2026-06-28T06:02:44.836106Z digest=sha256:37bbbb465cf81951e10e45ee456027d2e774be1b2d27328132e462d5e67d3728

Observation 8f8bc008-57c1-4dac-8895-73f83e101939 · outbound

This paper cites Multi-Step Dialogue Workflow Action Prediction.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Multi-Step Dialogue Workflow Action Prediction

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-07-02T08:26:48.333439Z

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=2026-06-28T06:02:44.836106Z digest=sha256:e47a325bb61e08c3ff54b6e27acb95b1235682b49b4cb1eebecc138057243df6

Observation 9bbb31e7-7f51-4ffd-a558-659d819ee564 · outbound

This paper cites InProceedings of the Second Workshop on When Creative AI Meets Conversational AI, pages 23–34.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories InProceedings of the Second Workshop on When Creative AI Meets Conversational AI, pages 23–34

Reference 6

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:850a8617d232b223989796d6addf10fa78b321d9fa074707e34ca4b153ffab5c

Observation a6b07d79-ef8a-4925-8388-d68204abfe76 · outbound

This paper cites AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents

Reference 7

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T08:26:48.325783Z

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=2026-06-28T06:02:44.836106Z digest=sha256:c763e596f5d42210870e8fc727f53a313a9e9a48de427396a32ec51e5246908c

Observation 376922f3-e369-4b52-8bd0-171b241b465a · outbound

This paper cites Figure 3: Accuracy-earliness curve for failure predictors under the same Plug-in Threshold rule.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Figure 3: Accuracy-earliness curve for failure predictors under the same Plug-in Threshold rule

Reference 8

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:e289cea932566ef6385ba2ffbd8ec35983886f461091d3be6946c499635aef5f

Observation 49bf6a16-8788-48e5-83bd-390fad2175ba · outbound

This paper cites an unresolved cited work.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Unresolved cited work

Reference 9

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:5bcd74d4c66b1b7b4c2a963869a0fb9f065236cec10ffec22217f91e9450eb03

Observation 5d20b538-8d47-4d29-a3d7-6e848054c8cb · outbound

This paper cites an unresolved cited work.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:8d622849f914f1a6212aa9e3d15568d7a349abc88cd0cb38da8ba761e87d6080

Observation 779a63c1-6cbb-4a71-8eb6-087083a4896e · outbound

This paper cites not LUHF.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories not LUHF

Reference 11

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:9eb2b755adf6c7a74cfceae2a1b8c4ea2168c369b408d3d65ea995ce43923902

Observation 72092410-20f1-47b5-9df6-767af5b689be · outbound

This paper cites an unresolved cited work.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Unresolved cited work

Reference 12

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:a640181c444b85c0be5cecfd3512f5626cbd4d39409643429f33815705234082

Observation b2275aef-d135-4aeb-a0fa-aaa971c45782 · outbound

This paper cites system" represents the dialog system/assistant -.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories system" represents the dialog system/assistant -

Reference 14

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:3218e9a0e63d104d3dea42efa9741a7a7cfea66c64c129a7d7c49a8f5aab6a16

Observation d14ea9a1-eb25-4669-87a3-3d607808d303 · outbound

This paper cites an unresolved cited work.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Unresolved cited work

Reference 15

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:830b8a2558ab7b129f8baa288ad8ad088ed7bbae507a3a6a59160b8824b8b03d

Observation 35ca8d17-2b4e-42f9-8573-66c0de9943fc · outbound

This paper cites persuader.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories persuader

Reference 17

Resolution
malformed identifier
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:fc88d60b77f21321e9035e26fb0cb87dead45d01fe11db706bb1a2dcad22dd58

Observation 1798940d-b00c-46a4-9545-9f59a44ffaaa · outbound

This paper cites an unresolved cited work.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Unresolved cited work

Reference 18

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:7d04aa2131d24dbe41eef0d51fc5ee0c9638707882539bc4a12502266770cb70

Observation eadec750-99a9-4484-876f-52f46a91d7bc · outbound

This paper cites agent" represents the AI agent's reasoning and actions -.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories agent" represents the AI agent's reasoning and actions -

Reference 20

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:aa0ab044313d79868b52465b120f11c4af6e1fcfe9a0ffce5a588153350ef086

Observation aa451a7c-4db4-4f67-84f5-5194562edd62 · outbound

This paper cites an unresolved cited work.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Unresolved cited work

Reference 21

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:9978fefbfde608ef1d9b914798e658a4629b2797f571a0e728831839c5f58e4c

Observation ce9cd0e7-2de7-41b5-9e91-46072f270735 · outbound

This paper cites think" represents the agent's reasoning and planning -.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories think" represents the agent's reasoning and planning -

Reference 23

Resolution
malformed identifier
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:70cd344c512723a04aac0b2356907f143d936a65bed6b716e1036076e6b49028

Observation 8a3251aa-569e-4c25-8c13-842a72d74a85 · outbound

This paper cites an unresolved cited work.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Unresolved cited work

Reference 24

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:4ab741746aa7759d67ed161db15937538de38671560fb82d6f2fd28bca4e93d4

Observation 9ffbd2ae-70ad-43db-a652-12805cc17184 · outbound

This paper cites an unresolved cited work.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Unresolved cited work

Reference 25

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:5a01d37aba37b47d9cd68d07c39586baf9a0b1f47ba8621623db88bb09bb0e6b

Observation 1de55f83-e06f-4ddc-ab8b-086c49904e06 · outbound

This paper cites system" represents the customer support agent -.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories system" represents the customer support agent -

Reference 26

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:6b2857bf49658bbd30a6fabed295838e48e6d998a4ffa50338d5765417f5c665

Observation cb77adc6-afa6-4965-811a-64944407e4b7 · outbound

This paper cites an unresolved cited work.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Unresolved cited work

Reference 27

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:d482eca3f4ab1f4b796420e6d1f68741499a957a92b9a62de7eb6aa4dac26ad3

Observation ac090345-8215-402e-bf9e-78c8deaa157f · outbound

This paper cites an unresolved cited work.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Unresolved cited work

Reference 28

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:adb5a005a502a249cedb6d391348543c1ebff9ef63d6ce818c580e0cbf4a6b58

Observation c6680507-db9a-4144-98ff-e4cf6d1f5322 · outbound

This paper cites an unresolved cited work.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Unresolved cited work

Reference 29

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:699506c71c251d1be38b919730f731ef5b7c6774e404d6653f0fc04f71f271b9

Observation a6dce941-b1cc-4da9-8e17-5461768dd4b8 · outbound

This paper cites an unresolved cited work.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Unresolved cited work

Reference 30

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:5ca2a111b6ee0d73f089d4cd7e3f152c64b9aa27ad1e8fa27589c53e4808ffeb

Observation a276ab45-30da-4cc6-bb02-335208c8590d · outbound

This paper cites an unresolved cited work.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Unresolved cited work

Reference 31

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:f65db053c638a2d4c5478494a3d5ad0c35cf261b112d0d3ae5b833dfea6c6823

Observation 223940b8-570d-47fa-b90e-4c775621de00 · outbound

This paper cites • While |A|< K and candidates remain, add the point p⋆ that maximizes the hypervolume gainHV(A ∪ {p}).

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories • While |A|< K and candidates remain, add the point p⋆ that maximizes the hypervolume gainHV(A ∪ {p})

Reference 32

Resolution
unresolved
no resolver link, observed 2026-06-28T06:02:44.836106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T06:02:44.836106Z digest=sha256:be327df6360cfd0b3148f2974f045406ecd67f26b8b19aedb52a7076bb06717c

Pith citing papers

Observation 044ea9ce-4b99-4815-a590-4b0503804555 · inbound

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade cites this paper.

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories

Reference 3

Resolution
metadata mismatch
local_arxiv, observed 2026-07-08T04:04:29.270533Z

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=2026-07-08T03:54:37.954084Z digest=sha256:7e1bfe1438a11d37bd8189c3b1f14679f1b10ea4297cf1603f37b59ba20c00d1

Observation 8abe831e-7351-4b92-b93d-1abd1b30ed6a · inbound

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade cites this paper.

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories

Reference 2026

Resolution
unresolved
no resolver link, observed 2026-08-02T08:18:03.582277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:18:03.582277Z digest=sha256:8dabcd4ce876ccc64ccf7f5e92ba1b65556bbe08a90fef6a4222c3ab6883b762

Observation ade27ff5-89e4-4248-bff5-9c59b72de0a6 · inbound

Real-Time Detection and Repair of LLM Agent Failures cites this paper.

Real-Time Detection and Repair of LLM Agent Failures When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-04T06:54:58.997189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T06:54:58.997189Z digest=sha256:c38f8caf94eab351c50cd11796733da30cf8b58dd8099e9dea47c135fde9f497

Observation 767eb2be-8301-4f98-bf6c-69214c4c02e2 · inbound

Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks cites this paper.

Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-05T23:23:54.624347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T23:23:54.624347Z digest=sha256:c7df57ae11cc5d3a6de6058a99320f7078315db5046dff9ffd9169e9d23a774a