Pith. sign in

Paper Citation Record · LEDGER

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports

As of 7 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 0 inbound Pith citation observations for arXiv:2608.04682.

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

pith.paper-citation-record.v1
2608.04682 v1

Coverage vector

measured 66 of 66 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:02:40.696853Z

measured 66 of 66 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

66 of 66 outbound references displayed

  • verified exact1
  • verified fuzzy44
  • unresolved20
  • parse uncertain1
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0565f63a-f9be-4791-8c58-d2f804216905 · outbound

This paper cites ICLR , year=.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports ICLR , year=

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:42.033982Z

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=arxiv_source observed=2026-08-06T19:02:40.290931Z digest=sha256:114c9c0e2ff9c405e2b716d9e89b2eb92dfe5e4f711070f85036f283bf00808a

Observation 49516cd8-6ba3-43f7-b0fa-143c03450ce4 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports LLaMA: Open and Efficient Foundation Language Models

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.308496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.308496Z digest=sha256:545142876123c52a9796f7ed7974e4befd6ef69b1b4ab24e607a8415d400bd6d

Observation b9a61cc0-4534-45ca-80c1-abe1104f57b9 · outbound

This paper cites ACM transactions on intelligent systems and technology , year=.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports ACM transactions on intelligent systems and technology , year=

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:42.015769Z

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=arxiv_source observed=2026-08-06T19:02:40.313909Z digest=sha256:b92d7f4947d9d60c83efa297fee9f46db38f1d04634546a5d4ea4d7abe393edb

Observation dadae06c-eb74-4022-a9c4-f036a2014744 · outbound

This paper cites Frontiers of Computer Science , year=.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Frontiers of Computer Science , year=

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.994927Z

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=arxiv_source observed=2026-08-06T19:02:40.319687Z digest=sha256:42f4e44f77956ed5310b4d521559f29de6610dcd2b13f0ca7f0b9bed69d10c29

Observation e81df24c-c8ba-4769-a303-c616ca9b4ce5 · outbound

This paper cites ICSE-FoSE , year=.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports ICSE-FoSE , year=

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.325309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.325309Z digest=sha256:75a9205ff37d0ec91103cfe9b62c3a09a6d347293e232b0bdb72788c1473a3d2

Observation 8d662c10-40b9-4050-970d-2e35e528b05c · outbound

This paper cites 2024 , howpublished =.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports 2024 , howpublished =

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.964031Z

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=arxiv_source observed=2026-08-06T19:02:40.336945Z digest=sha256:bfd55fd61690a2f64b4ea2dccbfd70c3afbdcd3b05b356439ba9a52a457426fc

Observation 9115f5ca-b6f8-4f03-b6f3-a2b45d3ebe7d · outbound

This paper cites 2024 , howpublished =.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports 2024 , howpublished =

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.943464Z

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=arxiv_source observed=2026-08-06T19:02:40.342006Z digest=sha256:768db2aa7ef59dfbbb7333a15e949c1c7bf417ce37b8b32931edc51c026f5175

Observation 891edd44-be57-4a68-8a60-b294434e3997 · outbound

This paper cites 2024 , howpublished =.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports 2024 , howpublished =

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.927060Z

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=arxiv_source observed=2026-08-06T19:02:40.346986Z digest=sha256:5113c4d3acce8353fda5473d48d92447bde185c96721109a2849f7c9d945c6b3

Observation c9d8cead-7ff6-4820-b947-b63811c2c720 · outbound

This paper cites 2026 , howpublished =.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports 2026 , howpublished =

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.908802Z

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=arxiv_source observed=2026-08-06T19:02:40.351934Z digest=sha256:6bb1a7f86b0736f64be57ea01fc44b3d485ec1e8482e200e0425c7d1df87d225

Observation b30d7ecf-2130-4d80-9f68-d40884c106d2 · outbound

This paper cites 2026 , howpublished =.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports 2026 , howpublished =

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.890389Z

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=arxiv_source observed=2026-08-06T19:02:40.356669Z digest=sha256:eef9297acb6793bfad64c6bc045cacf416a1871d4ee63fa4c45a268da045554e

Observation 85e92ddc-fa13-435f-915e-714e05b68d1c · outbound

This paper cites NeurIPS , year=.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports NeurIPS , year=

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.870937Z

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=arxiv_source observed=2026-08-06T19:02:40.361764Z digest=sha256:cab6867728872d080423a21eda69f2919b49e846788f5c025b00f2ea2d971ec5

Observation 0a0e2002-0825-4760-9fee-7dac66b10620 · outbound

This paper cites NeurIPS , year=.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports NeurIPS , year=

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.852951Z

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=arxiv_source observed=2026-08-06T19:02:40.372026Z digest=sha256:005fd47ea9102ea96c59f9fecde1cd2a5798ad8a3f7ec64927b92a7fe8f86fb7

Observation 64ba4e39-b21a-4b0a-9c41-5cddd61a9a18 · outbound

This paper cites SWE-Bench+: Enhanced Coding Benchmark for LLMs.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports SWE-Bench+: Enhanced Coding Benchmark for LLMs

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.376652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.376652Z digest=sha256:17d5df8e018ff0ac01d3c12951bdbe5f70b69acd77679e811f3b31a3a1fccdff

Observation 6a627b34-1f43-409d-81a5-4827a2338a3c · outbound

This paper cites ACL , year=.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports ACL , year=

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.835097Z

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=arxiv_source observed=2026-08-06T19:02:40.382378Z digest=sha256:f4a8fccf73c8626bf2b20d50187677c2fb7550ccafea35cdab0ccb5514584c5a

Observation 9a0930f9-0958-4d81-a76d-bd09a0406e57 · outbound

This paper cites NeurIPS , year=.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports NeurIPS , year=

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.818320Z

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=arxiv_source observed=2026-08-06T19:02:40.403082Z digest=sha256:39915ca022037b205058c3696cf6f826f2aba9f5a5efe5b7b25469853d841011

Observation 83bd7b1c-0ffa-42f8-85af-8929782a01e3 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Advances in Neural Information Processing Systems , volume=

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.413636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.413636Z digest=sha256:a9a4b697f3bef81141fd257bef3dde9385209068dcb37a16a47644010ae5ee1d

Observation 1cfb059a-d1d4-4f63-bb5a-695d361d32a7 · outbound

This paper cites ACL , year=.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports ACL , year=

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.790730Z

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=arxiv_source observed=2026-08-06T19:02:40.418361Z digest=sha256:512e06a42372d340c93903a5167c0c4be60d93c082d361eff65044274b1ce4b7

Observation 0619187b-1846-4afe-9b3b-eaa0d2de5f5a · outbound

This paper cites ICLR , year=.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports ICLR , year=

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.771010Z

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=arxiv_source observed=2026-08-06T19:02:40.423733Z digest=sha256:d086dca39dcc5a7d54e4f53e69234c6cdf73680a2b32ea4b6de372604538bb9c

Observation 9a479890-d1b4-42f0-a840-d4b7fd6359c7 · outbound

This paper cites ACL , year=.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports ACL , year=

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.754414Z

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=arxiv_source observed=2026-08-06T19:02:40.428427Z digest=sha256:c6868841698ebf6bf72b67902baeb39e55b0fd56c43c2b97f1309b32f075616d

Observation d098cacf-1a18-4d77-99eb-6662078e2e95 · outbound

This paper cites NeurIPS , year=.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports NeurIPS , year=

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.737619Z

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=arxiv_source observed=2026-08-06T19:02:40.433649Z digest=sha256:0ca8a83952bd82825360c7f2c2545ef552ce9493f1c56d15a04075ada00e3444

Observation 6742c5c2-6174-4d6b-9714-f98aa2d79b7b · outbound

This paper cites 2026 , howpublished =.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports 2026 , howpublished =

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.714824Z

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=arxiv_source observed=2026-08-06T19:02:40.448812Z digest=sha256:d01a0a0a313e4ccdb6acd815b2c8021044df8dcb9c077a082cf432c6e8f2db51

Observation 517c0c83-b80f-41fe-aaa4-0e8cc3177cfe · outbound

This paper cites 2026 , howpublished =.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports 2026 , howpublished =

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.696949Z

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=arxiv_source observed=2026-08-06T19:02:40.459486Z digest=sha256:f0b05dc22908b97c71aa3633c0a3be26add7eb728a758bf44b7da7798adc678f

Observation 7fda5a46-3f01-4293-bf9e-341e083e61f5 · outbound

This paper cites Qwen3.5: Accelerating Productivity with Native Multimodal Agents , howpublished =.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Qwen3.5: Accelerating Productivity with Native Multimodal Agents , howpublished =

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.678185Z

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=arxiv_source observed=2026-08-06T19:02:40.474687Z digest=sha256:18af9fa6a211555567b1890d74dff5723a749b52e30e8b0089322abe57000002

Observation d437dc11-78b9-4574-80e2-b06b942efee2 · outbound

This paper cites 2026 , howpublished =.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports 2026 , howpublished =

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.479235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.479235Z digest=sha256:20bbabaef0226f890a2edd77da821f924c1aafd5932a45f68e9caf5f49b09694

Observation ba7c3479-1fa3-49a1-a12a-6b79a7f87839 · outbound

This paper cites 2026 , howpublished =.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports 2026 , howpublished =

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.645910Z

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=arxiv_source observed=2026-08-06T19:02:40.484085Z digest=sha256:8e777848c9988d14c990b7ed7f6cd8cd3cdd17ca4dde7d83569fab09de2fdb96

Observation dd58faa9-7394-48e2-81ce-f65cf8b8bdf0 · outbound

This paper cites 2026 , howpublished =.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports 2026 , howpublished =

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.629172Z

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=arxiv_source observed=2026-08-06T19:02:40.489325Z digest=sha256:7313ddd4f356e1048c240e36d6fdbe3ebd8e2910f657fd18f5962d81c99cf40e

Observation b0c83089-c242-4d7b-bfbd-0785c326eb3b · outbound

This paper cites an unresolved cited work.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Unresolved cited work

Reference 42

Resolution
parse uncertain
no resolver link, observed 2026-08-06T19:02:40.509167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.509167Z digest=sha256:cb7d327bc90e8ed3384b4277c678682e6a35649f1c474b9ff3f0f2b75d02b3ed

Observation 89c6e5dd-035d-4ee2-a1ce-842f3486327d · outbound

This paper cites System card: Claude sonnet 4.6.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports System card: Claude sonnet 4.6

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.601259Z

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=arxiv_source observed=2026-08-06T19:02:40.513795Z digest=sha256:19feeee9c66ede4c7e28a0bfcd74c6ae72b5809f732e8d56da1f31b2d82e5cea

Observation 06eb38fb-7222-444f-b0d7-7abd67c27903 · outbound

This paper cites System card: Claude opus 4.8.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports System card: Claude opus 4.8

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.585132Z

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=arxiv_source observed=2026-08-06T19:02:40.518702Z digest=sha256:34ab76ec1aa8845a1c6870125c0d1474906865598523ec57b1969a59f8ff3c0f

Observation d0187244-64c2-4c7c-9476-308866a0ec00 · outbound

This paper cites A survey on evaluation of large language models.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports A survey on evaluation of large language models

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.568599Z

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=arxiv_source observed=2026-08-06T19:02:40.523406Z digest=sha256:424e4e23b35e1cd01c785fa02c66c66c7349e4458424e47b0d37ad9c9c695e2d

Observation 72be4632-bdf0-49e8-82ed-74b805e6b46b · outbound

This paper cites The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.528271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.528271Z digest=sha256:b657a0d5735404ec8db55c9a90b7f7dc96cce6dd149e7a0e5fe5b58340517145

Observation 6e8b870a-04a4-444f-b81c-ebaca12c6134 · outbound

This paper cites External technical root cause analysis — channel file 291.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports External technical root cause analysis — channel file 291

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.552095Z

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=arxiv_source observed=2026-08-06T19:02:40.532761Z digest=sha256:c003f0424497feddbbb6811c00ad31527b1974f75a6acd34b98622053dc91488

Observation beb6dfa7-3e20-4817-85df-dfa4e8d756d7 · outbound

This paper cites Deepseek-v4: Towards highly efficient million-token context intelligence.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Deepseek-v4: Towards highly efficient million-token context intelligence

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.535235Z

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=arxiv_source observed=2026-08-06T19:02:40.537453Z digest=sha256:5e9cbaa7022a2ce7ecb1008c22f950974e423870821af3ac35e89625e54d3370

Observation 49bd99bc-1278-4d1d-ae47-14d10ac73729 · outbound

This paper cites SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.542646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.542646Z digest=sha256:f574da9a0ad759f76d1a668906ea60a95b52ad3ad1be5e2b9dcb385dcaec086d

Observation 128b5bd0-da9f-491c-bb5a-2f80a28b5e2e · outbound

This paper cites Large language models for software engineering: Survey and open problems.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Large language models for software engineering: Survey and open problems

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.518388Z

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=arxiv_source observed=2026-08-06T19:02:40.547534Z digest=sha256:2d08985151b079da40e5acc1a02196b448d16e86dee6e227dbc9dc4e15adfed3

Observation d4703c88-aaa4-4104-9a54-5d37d6225d5c · outbound

This paper cites Gemini 3.1 pro model card.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Gemini 3.1 pro model card

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.502015Z

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=arxiv_source observed=2026-08-06T19:02:40.552364Z digest=sha256:bfdb0c091f0055f5366ff57cf9081bd61e77bf1a536131b89b22bb8e0d7294be

Observation 904c9bb4-aaa4-46e1-9782-cd4833834b9d · outbound

This paper cites AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.557097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.557097Z digest=sha256:8d794e6c0227dbdf7ab1e0edd5576e6a3fd4414b1229f20a8563c504b9af4a64

Observation bfed2013-810d-438f-979a-4fccabf85356 · outbound

This paper cites Mapcoder: Multi-agent code generation for competitive problem solving.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Mapcoder: Multi-agent code generation for competitive problem solving

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.486321Z

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=arxiv_source observed=2026-08-06T19:02:40.561483Z digest=sha256:06f9136cfe1266eefab67e5fb42e54667c682555067f4aee281e9264344c5577

Observation 753f1b08-6ee4-468e-8039-99aa741f11c0 · outbound

This paper cites Swe-bench: Can language models resolve real-world github issues? In ICLR, 2024.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Swe-bench: Can language models resolve real-world github issues? In ICLR, 2024

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.468934Z

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=arxiv_source observed=2026-08-06T19:02:40.566348Z digest=sha256:861596f531883c50eb8b8cd6e75d851092b6c2dd4eb4df70b466ecb043dc527b

Observation 1b1f2c14-9151-43ab-bbf6-bc47a76ad8bf · outbound

This paper cites From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.571286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.571286Z digest=sha256:2677885877decfc31983dcfce42aa1c73bae261424e503c50e69b7a314959bad

Observation 764ae076-5e9f-4c84-a758-364f9bfbb011 · outbound

This paper cites Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.575847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.575847Z digest=sha256:c3cef6a560b9b1b5733d2a35030a9d5147660f803c30d74ea5ae182e12d1f32b

Observation f5745e75-a471-43d7-ba00-7f27b1a049dc · outbound

This paper cites Testexplora: Benchmarking llms for proactive bug discovery via repository-level test generation.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Testexplora: Benchmarking llms for proactive bug discovery via repository-level test generation

Reference 57

Resolution
verified exact
raw_fallback, observed 2026-08-06T19:02:41.009629Z

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=arxiv_source observed=2026-08-06T19:02:40.580855Z digest=sha256:f8ce6e2b614e2e40b9e289e6eb4aef7c002dd5a557838a5692a5f369ffcf28b1

Observation 60060c8c-6308-4b6d-abe2-43168cc9d958 · outbound

This paper cites Helping our customers through the crowdstrike outage.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Helping our customers through the crowdstrike outage

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.451448Z

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=arxiv_source observed=2026-08-06T19:02:40.585756Z digest=sha256:595d59f7cc42114c21030ff3bda8bc7256fc8ee816e6414e27b99c5d9601da88

Observation 24b7c483-1b3f-4c62-a17b-e3ea15790a6d · outbound

This paper cites u ndler, Mark N M \.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports u ndler, Mark N M \

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.435745Z

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=arxiv_source observed=2026-08-06T19:02:40.591162Z digest=sha256:86be248069ea29df14efc426ab61c0b44f4a224e1f4bdc6beaae2bcac4cc4da2

Observation fac8908f-b69b-4567-8be1-3f35844fff57 · outbound

This paper cites Why swe-bench verified no longer measures frontier coding capabilities.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Why swe-bench verified no longer measures frontier coding capabilities

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.418435Z

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=arxiv_source observed=2026-08-06T19:02:40.595627Z digest=sha256:ad0bdd0187232f3b473dfeafc5a0b3d40723cfeb626ed77e989f9f5281741659

Observation 06da3624-803e-471c-8eb2-b598b707635a · outbound

This paper cites Separating signal from noise in coding evaluations.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Separating signal from noise in coding evaluations

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.402190Z

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=arxiv_source observed=2026-08-06T19:02:40.600347Z digest=sha256:a1bececac8815e901f07b3ada4ac62648d1e4626a6283ca016e7897b23d4cec0

Observation d813e5dd-8a68-49dd-abdd-1a9943392915 · outbound

This paper cites Crowdstrike to cost fortune 500 \ 5.4b; insured loss range of \ 0.54b - \ 1.08b.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Crowdstrike to cost fortune 500 \ 5.4b; insured loss range of \ 0.54b - \ 1.08b

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.383196Z

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=arxiv_source observed=2026-08-06T19:02:40.605278Z digest=sha256:591eddd899fb927c8cefbda34cf5853b64b3c78bb715794af281500481a5afa2

Observation 25ba78ca-7e44-4a4c-a537-292814a882fc · outbound

This paper cites Qwen3.7 : The agent frontier, May 2026.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Qwen3.7 : The agent frontier, May 2026

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.365835Z

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=arxiv_source observed=2026-08-06T19:02:40.609842Z digest=sha256:77d1016827bf8910798194f8c42ce2475d8824ab64ae354691acbf11bc6ed6fe

Observation 36983989-f6c6-44e7-9295-216d3effa092 · outbound

This paper cites SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.614800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.614800Z digest=sha256:f439695a7ce2ca3692862b737987b55651c26ac42bd7917e3c0243f330959c11

Observation 7e520ca1-e326-40d5-9a5d-33f4815a7fba · outbound

This paper cites Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.619737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.619737Z digest=sha256:878e5f3f75e38727de874feb9185279ffdda52d2b4633ea48f26cbb23caafd36

Observation 6bff20fc-1e23-499d-aef2-306784211d9f · outbound

This paper cites OpenAI GPT-5 System Card.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports OpenAI GPT-5 System Card

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.624433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.624433Z digest=sha256:af5f2e0d4daa412956d293c5a338bff39eeabf26a8303201c0ebed641e4efbf9

Observation 4166d0b0-61c3-460c-9d67-305dae3fa442 · outbound

This paper cites Kimi K2.5: Visual Agentic Intelligence.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Kimi K2.5: Visual Agentic Intelligence

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.629242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.629242Z digest=sha256:a0d0057460901810c9354c9b98380929309170527899302796ae73208e71c74b

Observation 888e5023-ee2f-4712-9181-fc809203c592 · outbound

This paper cites Qwen3.5: Accelerating productivity with native multimodal agents.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Qwen3.5: Accelerating productivity with native multimodal agents

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.349448Z

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=arxiv_source observed=2026-08-06T19:02:40.633864Z digest=sha256:01a2d610a03564d53b6d973523086e764fa64f1b642ec12d7e6a0f4891b66375

Observation 8d751679-314d-461e-9cb2-18c912352ff8 · outbound

This paper cites an unresolved cited work.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Unresolved cited work

Reference 69

Resolution
unresolved
raw_fallback, observed 2026-08-06T19:02:41.332028Z

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=arxiv_source observed=2026-08-06T19:02:40.638972Z digest=sha256:e195a816f893b4ba9670057b832ebbc06cd38ea51d4540245a23758eef5e54d8

Observation 4913b48a-561f-4138-9269-3c513df3004f · outbound

This paper cites Openhands: An open platform for ai software developers as generalist agents.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Openhands: An open platform for ai software developers as generalist agents

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.315666Z

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=arxiv_source observed=2026-08-06T19:02:40.643906Z digest=sha256:e02fc2f7cbccd514abe33afd1472f64de0ede405a507f8fb05c7f906609a5ca7

Observation c95108be-bc6a-4c3f-9943-0e1ad7feaf8f · outbound

This paper cites Live-swe-agent: Can software engineering agents self-evolve on the fly? arXiv preprint arXiv:2511.13646, 2025.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Live-swe-agent: Can software engineering agents self-evolve on the fly? arXiv preprint arXiv:2511.13646, 2025

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.648923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.648923Z digest=sha256:bb2ef92706d4f6f7b14e4797fdcf50789a56492357c0a7096f173320a0676dcd

Observation 70896e99-4ea8-4a36-aaed-baf635d8ea05 · outbound

This paper cites Swe-agent: Agent-computer interfaces enable automated software engineering.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Swe-agent: Agent-computer interfaces enable automated software engineering

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.298970Z

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=arxiv_source observed=2026-08-06T19:02:40.653538Z digest=sha256:03a5dd55b4dd040729b16664ddffa622a083a0c5c22f69a3a724137bdc3a6a0b

Observation 474521f1-6871-4316-9674-9fed3c956337 · outbound

This paper cites SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.658366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.658366Z digest=sha256:5ef05d179808dafca70b280b58a42df5431be2dfea128ec2a4dbf04d256abad5

Observation b3543968-4e74-4956-8813-d4946b3df476 · outbound

This paper cites Swe-smith: Scaling data for software engineering agents.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Swe-smith: Scaling data for software engineering agents

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.280645Z

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=arxiv_source observed=2026-08-06T19:02:40.662708Z digest=sha256:51b2eae97e9acb739f432ac4fcfcb8b6fc2b0b7b43371d9a52ad154af3d22dea

Observation f28180df-8257-44fc-aa16-5f74e3e2d7fe · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports ReAct: Synergizing Reasoning and Acting in Language Models

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.667485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.667485Z digest=sha256:549a20c7ee03f231658da96ab4976469b6fe1c12c0197d556f98f9c94d56f501

Observation 1d73afb6-5baf-41b4-8e2e-f8662083c1a6 · outbound

This paper cites Multi-swe-bench: A multilingual benchmark for issue resolving.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Multi-swe-bench: A multilingual benchmark for issue resolving

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.264160Z

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=arxiv_source observed=2026-08-06T19:02:40.672186Z digest=sha256:1ec69a64330f53fc50fc5ff03dd818052544517cf33b6c001721fddc69a46f09

Observation 9b55618c-b92d-4c42-a61b-1751e94b601e · outbound

This paper cites GLM-5: from Vibe Coding to Agentic Engineering.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports GLM-5: from Vibe Coding to Agentic Engineering

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.677154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.677154Z digest=sha256:092471da45beaacbbd612ea5eb80d696f5617731fcb61a005046d6cb0a1ad7ca

Observation 37d59c2f-702c-447e-a703-8d4c3d9a7959 · outbound

This paper cites Codeagent: Enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Codeagent: Enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges

Reference 78

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.247502Z

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=arxiv_source observed=2026-08-06T19:02:40.681643Z digest=sha256:81fc60b12ae510f0be9878aa0e9b5f2cf8444172e5f7502d590be85de3325509

Observation 772dcec3-c004-4870-91db-1d8927a27f78 · outbound

This paper cites Swe-bench goes live! In NeurIPS, 2026.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Swe-bench goes live! In NeurIPS, 2026

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.229614Z

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=arxiv_source observed=2026-08-06T19:02:40.686763Z digest=sha256:322419317cb1eea4d53f4a97e81cc7d253ea28fc55e25a2ca8cb23bcffaa1f9b

Observation 8eebe9aa-1454-4e4b-b045-82b5beb7fa9f · outbound

This paper cites A survey of large language models.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports A survey of large language models

Reference 80

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T19:02:41.212617Z

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=arxiv_source observed=2026-08-06T19:02:40.691634Z digest=sha256:ca57ba7924831682bda4d8de9118138ea6ebfb8fa0be3f4539317affa6443e3b

Observation 8e9f7764-9d6f-4452-9c46-28fe032d255a · outbound

This paper cites Featurebench: Benchmarking agentic coding for complex feature development.

Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports Featurebench: Benchmarking agentic coding for complex feature development

Reference 81

Resolution
unresolved
no resolver link, observed 2026-08-06T19:02:40.696853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T19:02:40.696853Z digest=sha256:7f94179874588f10e8cae35fe538fe2c5f9cd0f5b53284049e452eef3b39e74b

Pith citing papers

No inbound Pith citation observations are available.