Yoav Artzi, Mustafa Gul
2 of 6 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 4 no recorded run), measured 2026-11-22; 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/2408.15992.json · badge: /api/ran/2408.15992.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 |
|---|---|---|
| lil-lab/cogen | marked official in Papers with Code Papers with Code archive |
2 ran · 4 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| filter_targets | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
lil-lab/cogen/models/joint_inference.py pointer only (licence: NONE) · get_code("3391626ba57002a1") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lil-lab/cogen 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. |
| process_images | Ran ran, honoured the contract we drafted |
lil-lab/cogen/models/joint_inference.py pointer only (licence: NONE) · get_code("5f621459c8e0f985") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lil-lab/cogen 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. |
| IdeficsJointInferenceModel | Not yet run unverified (harvested, no recorded run) |
lil-lab/cogen/models/joint_inference.py pointer only (licence: NONE) · get_code("b6243816583a3cac") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lil-lab/cogen 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. |
| construct_listener_full_prompt | Not yet run unverified (harvested, no recorded run) |
lil-lab/cogen/models/joint_inference.py pointer only (licence: NONE) · get_code("85f44b9c0224bae7") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lil-lab/cogen 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. |
| get_listener_generation_prompts | Not yet run unverified (harvested, no recorded run) |
lil-lab/cogen/models/joint_inference.py pointer only (licence: NONE) · get_code("fc616f122d15486d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lil-lab/cogen 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. |
| process_idefics_listener_generation_input | Not yet run unverified (harvested, no recorded run) |
lil-lab/cogen/models/joint_inference.py pointer only (licence: NONE) · get_code("d1b01eb9e322a6d5") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, lil-lab/cogen 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. |
Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.
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.
Systems with both language comprehension and generation capabilities can benefit from the tight connection between the two. This work studies coupling comprehension and generation with focus on continually learning from interaction with users. We propose techniques to tightly integrate the two capabilities for both learning and inference. We situate our studies in two-player reference games, and deploy various models for thousands of interactions with human users, while learning from interaction feedback signals. We show dramatic improvements in performance over time, with comprehension-generation coupling leading to performance improvements up to 26% in absolute terms and up to 17% higher accuracies compared to a non-coupled system. Our analysis also shows coupling has substantial qualitative impact on the system's language, making it significantly more human-like.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2408.15992")
get_code_for_paper("2408.15992")
have("2408.15992")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2408.15992.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2408.15992)
Connect an agent — have() is free.