Pith. sign in

Paper Citation Record · LEDGER

CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 24 inbound Pith citation observations for arXiv:2305.02309.

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

pith.paper-citation-record.v1
2305.02309 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 24 of 24 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-09T11:01:27.910143Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T15:18:32.748914Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 9bd0ffbe-6601-4db9-8dd5-70d3e4f11f37 · inbound

A Survey of Large Language Models cites this paper.

A Survey of Large Language Models CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 99

Resolution
metadata mismatch
arxiv_id, observed 2026-05-10T22:46:39.843832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-05-10T22:46:39.268353Z digest=sha256:daec5657116f88bdd00f5c33582fce126ed3e1230a27e6a5d4382e3cfec16682

Observation 2f69b74c-aa70-4417-922e-22635470c073 · inbound

Gorilla: Large Language Model Connected with Massive APIs cites this paper.

Gorilla: Large Language Model Connected with Massive APIs CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 27

Resolution
verified exact
arxiv_id, observed 2026-05-11T23:22:17.389671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-05-11T23:22:16.879418Z digest=sha256:76c0b0d742e28d16346f478267db6fd76ab2033d4e1207bb141fef63957e9d51

Observation 2a99496b-1333-4284-a029-e38eaa8a958e · inbound

Textbooks Are All You Need cites this paper.

Textbooks Are All You Need CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 24

Resolution
metadata mismatch
arxiv_id, observed 2026-05-13T04:44:03.252112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-05-13T04:44:03.148223Z digest=sha256:a4241515221449af9a44ba89b97e13310a92af0637f855039f0f392d4d2b1a16

Observation 3dd1a7a0-c80d-4e6b-82ea-4f8eb51f2d7d · inbound

Large Language Models: A Survey cites this paper.

Large Language Models: A Survey CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 113

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T15:22:55.476246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-05-11T15:22:54.023279Z digest=sha256:e3e551f2d3747d99edddfd8860182c167f84cfe76b72a7c3a05fa39cb661cc7e

Observation 913a1198-1681-400f-a12d-5fc341c19804 · inbound

A Survey on Large Language Models for Code Generation cites this paper.

A Survey on Large Language Models for Code Generation CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 196

Resolution
verified exact
arxiv_id, observed 2026-05-13T20:18:06.517384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-05-13T20:18:06.304134Z digest=sha256:656f4985a37e587b414928c74efac0ed2670e63aedb4edbe4097f9848c08fbd0

Observation 31ba6f2e-7ea5-4953-bdea-244441ce724b · inbound

COFFE: A Code Efficiency Benchmark for Code Generation cites this paper.

COFFE: A Code Efficiency Benchmark for Code Generation CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-09T11:01:27.910143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T11:01:27.910143Z digest=sha256:c85b97abeffdc6a9ace06b717e77dced57ffd71ef65c6eb624bad3e89278d368

Observation 8b545787-6f47-4bfa-be6b-caaa1734e58b · inbound

LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks cites this paper.

LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-08T16:26:32.308142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T16:26:32.308142Z digest=sha256:e706c59fa3b7625ad8515b441be20ab139d50da5f46bcb3366bda272341644e2

Observation f006770e-c09a-462f-8dac-c82957f11475 · inbound

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse cites this paper.

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T13:27:55.849826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:27:55.849826Z digest=sha256:f2ab75cdad5365527cb177bce498d68d68cb9601057acfe45d9c22767f1634fa

Observation 2aa6af1f-2dd8-4a58-85e3-8c28c2de61bb · inbound

Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning cites this paper.

Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-07T10:58:19.992128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:58:19.992128Z digest=sha256:d7f6ec2ff73a0790d4d484372b412880894e0ec0b73ce3f557b93282916ac98a

Observation 9b434580-6308-4ca2-bfce-caa12580aa8b · inbound

LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation cites this paper.

LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T04:37:15.092070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:37:15.092070Z digest=sha256:e3b3f29fa40e9c8cd7aecb7c0c0fa03ef4a55db19c6a6b14a6455b6e0a73df3b

Observation a4c3e5f5-a8c7-4a92-91d8-7bae60c8462d · inbound

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones cites this paper.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T21:23:38.275531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:23:38.275531Z digest=sha256:69601a245a1e5b8cd2fb48885fcd7219ae1b3f7e952bcde3e0c74680225abdc3

Observation 08823728-284e-40bd-876d-df429088531d · inbound

ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis cites this paper.

ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 7

Resolution
verified exact
arxiv_id, observed 2026-05-19T07:02:07.836532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-05-19T06:58:27.279482Z digest=sha256:d1c2ebbf912bf8bfa0facdb2847f5ed82b0febfd0656bc4cac2b1abd891f95f5

Observation db4aa14f-a804-4390-b5cb-a432b82360ed · inbound

Semantic Source Code Segmentation using Small and Large Language Models cites this paper.

Semantic Source Code Segmentation using Small and Large Language Models CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T18:14:06.296411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:14:06.296411Z digest=sha256:9ec19c5c1cc17b317509e7f8ee189bc8791aca52963c4abd6ad7eac9681eac21

Observation 02f4f2a9-0598-4365-a407-c056fdb14f1a · inbound

Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing cites this paper.

Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T15:52:20.410994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T15:52:20.410994Z digest=sha256:72c98a6cce24de656b4bafdb4c289c133b9413cda6e451acb9a622d63f406cf0

Observation 9bd108fc-062d-4b2f-8c4d-837df0ee4e3a · inbound

GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion cites this paper.

GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-05T04:48:37.109377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T04:48:37.109377Z digest=sha256:250b295aa507d3ee496e1aa2a732101a4284bd1b4e5aed3197442cd77d0aa708

Observation b18a651e-8e80-4c51-8f7f-54cd1b9f41f2 · inbound

AutoVeriFix: Automatically Correcting Errors and Enhancing Functional Correctness in LLM-Generated Verilog Code cites this paper.

AutoVeriFix: Automatically Correcting Errors and Enhancing Functional Correctness in LLM-Generated Verilog Code CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-04T20:43:12.940366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T20:43:12.940366Z digest=sha256:0fe48d79c94ba61d7ceae253f48919f325fc558d23ef96140d5890b8a82dd500

Observation 3d2af7c1-a9dc-47cc-a8d7-86e0da150a52 · inbound

Context-Guided Decompilation: A Step Towards Re-executability cites this paper.

Context-Guided Decompilation: A Step Towards Re-executability CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 43

Resolution
verified exact
arxiv_id, observed 2026-05-18T01:35:36.489477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-05-18T01:33:54.870931Z digest=sha256:4cf67310390080f84a16ed8ec244e17284ad150bdce8eeb62428afe536c9fc19

Observation b7645c0a-aeed-4e09-8c65-fb27fe2c08ab · inbound

A Taxonomy of Programming Languages for Code Generation cites this paper.

A Taxonomy of Programming Languages for Code Generation CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 15

Resolution
verified exact
arxiv_id, observed 2026-05-11T22:56:14.117278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-05-08T02:17:18.127674Z digest=sha256:fd9ae7d9359d83aa739eb3566ee87944779f3bf93af29bae7377970693bb8c4f

Observation 1ab005d5-bbe6-4c9d-b066-0b799af0bd8f · inbound

SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair cites this paper.

SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 23

Resolution
metadata mismatch
arxiv_id, observed 2026-05-10T06:41:36.540576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-05-10T06:39:29.822371Z digest=sha256:c0c8775124a037ee7fc17cb999c0a4e0141db990b280480fcd9569e7c5f0abe2

Observation 5af8be4b-b77b-48db-87de-2f088f3dda35 · inbound

VerilogCL: A Contrastive Learning Framework for Robust LLM-Based Verilog Generation cites this paper.

VerilogCL: A Contrastive Learning Framework for Robust LLM-Based Verilog Generation CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 5

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T12:11:07.027347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-05-10T04:04:47.376762Z digest=sha256:e5f597d58df4883c250a7ec3b4f215d8d2f9ae295af282535a83cd847ca2cd84

Observation f9f8759e-10fc-491e-a37f-2c1e940c6cfe · inbound

Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs cites this paper.

Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 227

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T07:45:59.859808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-05-10T16:58:10.013475Z digest=sha256:ac8c82f2f8484a690ae89c0698e7444a241c6ae090b5a60fec5a134011ca2ace

Observation 02c59a68-a014-463e-a169-79b2685111a9 · inbound

Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning cites this paper.

Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 212

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T08:01:00.441049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-05-10T16:51:19.555272Z digest=sha256:483737c92fd483b9f6feeee40e0aefa53e32242d0b316d7829d268fae6ea5436

Observation bb634b73-9f92-4508-90d5-63ee309e1646 · inbound

Towards Knowledge Alignment in Code LLMs: Contrastive Unlearning for Evolving APIs cites this paper.

Towards Knowledge Alignment in Code LLMs: Contrastive Unlearning for Evolving APIs CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 21

Resolution
metadata mismatch
arxiv_id, observed 2026-07-01T12:35:44.433390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-07-01T01:54:14.176526Z digest=sha256:fd4650bd48356847a41a35dfad88c5a569202913ba0abed38e746a8d901c267e

Observation 683b3d28-3db5-4606-85a5-cf7ef49a2bb9 · inbound

PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation cites this paper.

PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

Reference 22

Resolution
metadata mismatch
arxiv_id, observed 2026-07-03T15:18:32.750897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-07-03T15:15:14.024594Z digest=sha256:1726e8aa71fde4f6d4d339f7f7ee6ac782ac0a38e1da0b77d36f1cd3b999e97a