Home › Code › compute_baseline_loss

compute_baseline_loss

Syntologyentry name in harvested coderead from the graph 2026-09-24

compute_baseline_loss appears in the code Syntology harvested for 12 papers, as 5 distinct code bodies found in 13 places (a place is one code body under one paper). At least one of them ran in 8 of the papers; 2 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named compute_baseline_loss do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 2 of the 5 distinct code bodies named compute_baseline_loss; 3 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
2ran · our draft was wrong
0ran · fixture could not drive it
0ran
3unverified
2fingerprinted

Licence is a property of each copy, so it is counted per place: 10 of the 13 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

12 papers shown of 12, newest first; 13 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Dungeons and Data: A Large-Scale NetHack Dataset 1 Nov 2022 identical code first harvested elsewhere e624e7bc82f85ecd unverified licence of this copy not recorded
Improving Policy Learning via Language Dynamics Distillation 30 Sep 2022 identical code first harvested elsewhere e624e7bc82f85ecd unverified licence of this copy not recorded
The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models 10 Jan 2022 aypan17/reward-misspecification/atari/torchbeast/monobeast.py e9123707cba84b2c ran · our draft was wrong fingerprinted MIT (permissive)
Interesting Object, Curious Agent: Learning Task-Agnostic Exploration 25 Nov 2021 identical code first harvested elsewhere dde95c495d2752d6 ran · our draft was wrong fingerprinted licence of this copy not recorded
SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmark 20 Oct 2021 identical code first harvested elsewhere dde95c495d2752d6 ran · our draft was wrong fingerprinted licence of this copy not recorded
The NetHack Learning Environment 24 Jun 2020 facebookresearch/nle/nle/agent/agent.py e624e7bc82f85ecd unverified licence not identified · pointer only
Learning with AMIGo: Adversarially Motivated Intrinsic Goals 22 Jun 2020 facebookresearch/adversarially-motivated-intrinsic-goals/monobeast/minigrid/monobeast_amigo.py dde95c495d2752d6 ran · our draft was wrong fingerprinted licence not identified · pointer only
RTFM: Generalising to Novel Environment Dynamics via Reading 18 Oct 2019 identical code first harvested elsewhere dde95c495d2752d6 ran · our draft was wrong fingerprinted licence of this copy not recorded
TorchBeast: A PyTorch Platform for Distributed RL 8 Oct 2019 identical code first harvested elsewhere e9123707cba84b2c ran · our draft was wrong fingerprinted licence of this copy not recorded
TorchBeast: A PyTorch Platform for Distributed RL 8 Oct 2019 heiner/scalable_agent/experiment.py 777b5a676e76d593 unverified Apache-2.0 (permissive)
The StreetLearn Environment and Dataset 4 Mar 2019 deepmind/streetlearn/streetlearn/python/experiment.py c4621788cdb91119 unverified Apache-2.0 (permissive)
Multi-task Deep Reinforcement Learning with PopArt 12 Sep 2018 identical code first harvested elsewhere e9123707cba84b2c ran · our draft was wrong fingerprinted licence of this copy not recorded
StarCraft II: A New Challenge for Reinforcement Learning 16 Aug 2017 identical code first harvested elsewhere e9123707cba84b2c ran · our draft was wrong fingerprinted licence of this copy not recorded

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections