Jianfeng Gao, Jiawei Han, Minjia Zhang, Liyuan Liu, Suyu Ge, Yunan Zhang
5 of 9 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; 4 failures of our instrument; 4 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/2310.01801.json · badge: /api/ran/2310.01801.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 |
|---|---|---|
| answerdotai/cold-compress | community Papers with Code archive |
4 ran · 4 no recorded run |
| copy not recorded | community not in the paper's declared repositories |
1 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| create_window_attention_mask | Ran ran, violated the contract we drafted |
this paper's copy was not recorded; identical code first harvested from answerdotai/cold-compress pointer only · get_code("472d821ef38be37d") How it ranThe body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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. |
| dequantize_tensor | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
answerdotai/cold-compress/cache.py code served (permissive licence) · get_code("5564321cfa1d2c94") 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 Tensor, ndim 2, dtype family float, shape (2, 4) 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.
|
| pack_low_bit_tensor | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
answerdotai/cold-compress/cache.py code served (permissive licence) · get_code("f7e4d6a116aaae11") 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 Tensor, ndim 1, dtype family int, shape (4,) 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.
|
| quantize_tensor | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
answerdotai/cold-compress/cache.py code served (permissive licence) · get_code("8d5153e794aa8b15") 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. 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.
|
| unpack_low_bit_tensor | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
answerdotai/cold-compress/cache.py code served (permissive licence) · get_code("910108db225dd9fe") 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 Tensor, ndim 1, dtype family int, shape (4,) 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.
|
| KVCache | Not yet run unverified (harvested, no recorded run) |
answerdotai/cold-compress/cache.py code served (permissive licence) · get_code("77d2d58362eb96eb") How it ranno invocation recorded. |
| KVCacheHeadSpecific | Not yet run unverified (harvested, no recorded run) |
answerdotai/cold-compress/cache.py code served (permissive licence) · get_code("8e720cf08e93134e") How it ranno invocation recorded. |
| KVCacheHeavyHitter | Not yet run unverified (harvested, no recorded run) |
answerdotai/cold-compress/cache.py code served (permissive licence) · get_code("b74628786f18097a") How it ranno invocation recorded. |
| KVCacheHybrid | Not yet run unverified (harvested, no recorded run) |
answerdotai/cold-compress/cache.py code served (permissive licence) · get_code("bc3c2262d92a1205") How it ranno invocation recorded. |
Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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 |
|---|---|---|---|
| create_window_attention_mask brick of this paper's assembly: helper |
3 other papers 2 dated earlier, 1 later |
2305.17118 (2023-05) Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time |
2306.14048 (2023-06) H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models 2406.02069 (2024-06) PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling |
| KVCache brick of this paper's assembly: model |
1 other paper 1 dated earlier · 1 only as an assembly brick |
2309.17453 (2023-09) Efficient Streaming Language Models with Attention Sinks |
|
| dequantize_tensor brick of this paper's assembly: helper |
1 other paper 1 dated earlier · 1 only as an assembly brick |
2309.17453 (2023-09) Efficient Streaming Language Models with Attention Sinks |
|
| pack_low_bit_tensor brick of this paper's assembly: helper |
1 other paper 1 dated earlier · 1 only as an assembly brick |
2309.17453 (2023-09) Efficient Streaming Language Models with Attention Sinks |
|
| quantize_tensor brick of this paper's assembly: helper |
1 other paper 1 dated earlier · 1 only as an assembly brick |
2309.17453 (2023-09) Efficient Streaming Language Models with Attention Sinks |
|
| unpack_low_bit_tensor brick of this paper's assembly: helper |
1 other paper 1 dated earlier · 1 only as an assembly brick |
2309.17453 (2023-09) Efficient Streaming Language Models with Attention Sinks |
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.
In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and value vectors for all context tokens, we conduct targeted profiling to discern the intrinsic structure of attention modules. Based on the recognized structure, we propose FastGen, which constructs the KV cache in an adaptive manner: evicting long-range contexts on attention heads emphasizing local contexts, discarding non-special tokens on attention heads centered on special tokens, and only employing the standard KV cache for attention heads that broadly attend to all tokens. Moreover, with the lightweight attention profiling used to guide the construction of the adaptive KV cache, FastGen can be deployed without resource-intensive fine-tuning or re-training. In our experiments across various asks, FastGen demonstrates substantial reduction on GPU memory consumption with negligible generation quality loss.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2310.01801")
get_code_for_paper("2310.01801")
have("2310.01801")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2310.01801.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2310.01801)
Connect an agent — have() is free.