10 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 9 failures of our instrument; 6 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2409.19256.json · badge: /api/ran/2409.19256.svg
Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.
| Repository | Role | Ran |
|---|---|---|
| du-nlp-lab/lengthreward | community (classifier label) classifier basis not recorded on the link |
10 ran · 6 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| compute_ce_dpo_loss_rm | Ran ran; our contract draft was wrong, not the code |
du-nlp-lab/lengthreward/recipe/prime/prime_core_algos.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("f220595adfc5e83c") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| compute_detach_dpo_loss_rm | Ran ran; our contract draft was wrong, not the code |
du-nlp-lab/lengthreward/recipe/prime/prime_core_algos.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("4d91e4383716e42c") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| compute_online_dpo_loss | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
du-nlp-lab/lengthreward/recipe/spin/core_algos.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("f19825983a523003") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| compute_onlinedpo_pref | Ran ran; our contract draft was wrong, not the code |
du-nlp-lab/lengthreward/recipe/spin/core_algos.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("41b6e81dc3ecba79") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| create_prompt_response | Ran ran; our contract draft was wrong, not the code |
du-nlp-lab/lengthreward/recipe/char_count/create_dataset.py code served (permissive licence) · get_code("e685ec4d0fa29f37") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| get_kl_controller | Ran ran; our contract draft was wrong, not the code |
du-nlp-lab/lengthreward/recipe/spin/core_algos.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("757d109d90121142") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| is_ipv4 | Ran ran, violated the contract we drafted |
du-nlp-lab/lengthreward/verl/utils/net_utils.py code served (permissive licence) · get_code("735e93af30b15fa9") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| reward_func | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
du-nlp-lab/lengthreward/recipe/r1/reward_score.py code served (permissive licence) · get_code("c30b2a96103abd2c") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned MagicMock. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| union_tensor_dict | Ran ran; our contract draft was wrong, not the code |
du-nlp-lab/lengthreward/verl/protocol.py code served (permissive licence) · get_code("21331a58f93375e4") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned TensorDict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| unpad_dataproto | Ran ran; our contract draft was wrong, not the code |
du-nlp-lab/lengthreward/verl/protocol.py code served (permissive licence) · get_code("83b1686d7ac03c21") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned DataProto. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| get_generation_config | Not yet run unverified (harvested, no recorded run) |
du-nlp-lab/lengthreward/verl/utils/model.py code served (permissive licence) · get_code("c9d58036da0286f2") How it ranno invocation recorded. |
| get_huggingface_actor_config | Not yet run unverified (harvested, no recorded run) |
du-nlp-lab/lengthreward/verl/utils/model.py code served (permissive licence) · get_code("59904a8955b34252") How it ranno invocation recorded. |
| get_weight_loader | Not yet run unverified (harvested, no recorded run) |
du-nlp-lab/lengthreward/verl/models/weight_loader_registry.py code served (permissive licence) · get_code("acf240079d434746") How it ranno invocation recorded. |
| get_weight_saver | Not yet run unverified (harvested, no recorded run) |
du-nlp-lab/lengthreward/verl/models/weight_loader_registry.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from Hesse73/ARMOR, is pointer only (licence: NONE) · get_code("cd6b1e0d6afb2762") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Hesse73/ARMOR, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded. |
| is_ipv6 | Not yet run unverified (harvested, no recorded run) |
du-nlp-lab/lengthreward/verl/utils/net_utils.py code served (permissive licence) · get_code("705afe175ad8e404") How it ranno invocation recorded. |
| squeeze | Not yet run unverified (harvested, no recorded run) |
du-nlp-lab/lengthreward/verl/utils/model.py code served (permissive licence) · get_code("3b15e2ac7497c441") How it ranno invocation recorded. |
Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 16 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 16 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).
Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| unpad_dataproto | 89 other papers 86 later, 3 undated |
2410.21236 (2024-10) Flaming-hot Initiation with Regular Execution Sampling for Large Language Models |
2025.findings-emnlp.1015 (2025 (year only)) MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning 2502.14382 (2025-02) S*: Test Time Scaling for Code Generation and 86 more not named here |
| squeeze | 82 other papers 79 later, 3 undated |
2410.21236 (2024-10) Flaming-hot Initiation with Regular Execution Sampling for Large Language Models |
2025.findings-emnlp.1015 (2025 (year only)) MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning 2502.14768 (2025-02) Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning and 79 more not named here |
| union_tensor_dict | 64 other papers 61 later, 3 undated · 4 only as an assembly brick |
2410.21236 (2024-10) Flaming-hot Initiation with Regular Execution Sampling for Large Language Models |
2025.findings-emnlp.1015 (2025 (year only)) MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning 2502.14768 (2025-02) Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning and 61 more not named here |
| get_generation_config | 63 other papers 61 later, 2 undated |
2410.21236 (2024-10) Flaming-hot Initiation with Regular Execution Sampling for Large Language Models |
2502.19613 (2025-02) Self-rewarding correction for mathematical reasoning 2503.06580 (2025-03) Agent models: Internalizing Chain-of-Action Generation into Reasoning models and 60 more not named here |
| get_weight_loader | 58 other papers 56 later, 2 undated |
2505.14362 (2025-05) DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning |
2505.20046 (2025-05) REARANK: Reasoning Re-ranking Agent via Reinforcement Learning 2506.08672 (2025-06) RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling and 55 more not named here |
| get_huggingface_actor_config | 53 other papers 51 later, 2 undated |
2410.21236 (2024-10) Flaming-hot Initiation with Regular Execution Sampling for Large Language Models |
2025.findings-emnlp.1015 (2025 (year only)) MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning 2502.14768 (2025-02) Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning and 50 more not named here |
| compute_ce_dpo_loss_rm | 46 other papers 43 later, 3 undated |
2410.02992 (2024-10) Learning to Better Search with Language Models via Guided Reinforced Self-Training |
2504.16084 (2025-04) TTRL: Test-Time Reinforcement Learning 2505.14362 (2025-05) DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning and 43 more not named here |
| compute_detach_dpo_loss_rm | 44 other papers 41 later, 3 undated |
2410.02992 (2024-10) Learning to Better Search with Language Models via Guided Reinforced Self-Training |
2504.16084 (2025-04) TTRL: Test-Time Reinforcement Learning 2505.14362 (2025-05) DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning and 41 more not named here |
| is_ipv4 | 41 other papers 39 later, 2 undated |
2506.08672 (2025-06) RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling |
2506.12935 (2025-06) SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models 2510.04678 (2025-10) Multi-Agent Tool-Integrated Policy Optimization and 38 more not named here |
| is_ipv6 | 41 other papers 39 later, 2 undated |
2506.08672 (2025-06) RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling |
2506.12935 (2025-06) SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models 2510.04678 (2025-10) Multi-Agent Tool-Integrated Policy Optimization and 38 more not named here |
| compute_online_dpo_loss | 38 other papers 35 later, 3 undated |
2410.02992 (2024-10) Learning to Better Search with Language Models via Guided Reinforced Self-Training |
2504.16084 (2025-04) TTRL: Test-Time Reinforcement Learning 2506.12935 (2025-06) SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models and 35 more not named here |
| get_kl_controller | 38 other papers 35 later, 3 undated |
2410.02992 (2024-10) Learning to Better Search with Language Models via Guided Reinforced Self-Training |
2504.16084 (2025-04) TTRL: Test-Time Reinforcement Learning 2506.12935 (2025-06) SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models and 35 more not named here |
| compute_onlinedpo_pref | 30 other papers 27 later, 3 undated |
2410.02992 (2024-10) Learning to Better Search with Language Models via Guided Reinforced Self-Training |
2504.16084 (2025-04) TTRL: Test-Time Reinforcement Learning 2512.11391 (2025-12) Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization and 27 more not named here |
| reward_func | 28 other papers 26 later, 2 undated |
2504.16084 (2025-04) TTRL: Test-Time Reinforcement Learning |
2505.14362 (2025-05) DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning 2505.20046 (2025-05) REARANK: Reasoning Re-ranking Agent via Reinforcement Learning and 25 more not named here |
| get_weight_saver | 12 other papers 12 later |
2510.04678 (2025-10) Multi-Agent Tool-Integrated Policy Optimization |
2602.12036 (2026-02) Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models 2603.12109 (2026-03) On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents and 9 more not named here |
| create_prompt_response | 1 other paper 1 later |
2510.04678 (2025-10) Multi-Agent Tool-Integrated Policy Optimization |
Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Reinforcement Learning from Human Feedback (RLHF) is widely used in Large Language Model (LLM) alignment. Traditional RL can be modeled as a dataflow, where each node represents computation of a neural network (NN) and each edge denotes data dependencies between the NNs. RLHF complicates the dataflow by expanding each node into a distributed LLM training or generation program, and each edge into a many-to-many multicast. Traditional RL frameworks execute the dataflow using a single controller to instruct both intra-node computation and inter-node communication, which can be inefficient in RLHF due to large control dispatch overhead for distributed intra-node computation. Existing RLHF systems adopt a multi-controller paradigm, which can be inflexible due to nesting distributed computation and data communication. We propose HybridFlow, which combines single-controller and multi-controller paradigms in a hybrid manner to enable flexible representation and efficient execution of the RLHF dataflow. We carefully design a set of hierarchical APIs that decouple and encapsulate computation and data dependencies in the complex RLHF dataflow, allowing efficient operation orchestration to implement RLHF algorithms and flexible mapping of the computation onto various devices. We further design a 3D-HybridEngine for efficient actor model resharding between training and generation phases, with zero memory redundancy and significantly reduced communication overhead. Our experimental results demonstrate 1.53$\times$~20.57$\times$ throughput improvement when running various RLHF algorithms using HybridFlow, as compared with state-of-the-art baselines. HybridFlow source code will be available at https://github.com/volcengine/verl.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2409.19256")
get_code_for_paper("2409.19256")
have("2409.19256")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2409.19256.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2409.19256)
Connect an agent — have() is free.