Browse State-of-the-Art › Semantic Textual Similarity
Semantic Textual Similarity
693 papers with code · 13 benchmarks · 19 datasets archive 2025-07-28
Semantic textual similarity deals with determining how similar two pieces of texts are. This can take the form of assigning a score from 1 to 5. Related tasks are paraphrase or duplicate identification.
Image source: Learning Semantic Textual Similarity from Conversations
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
13 leaderboard tables shown for this task, 13 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 13 until expanded.
Syntology 16 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): STS Benchmark (10 judged, 0 placed), MRPC (9 judged, 0 placed), STS13 (1 judged, 0 placed), STS14 (1 judged, 0 placed), STS12 (1 judged, 0 placed), STS15 (1 judged, 0 placed), STS16 (1 judged, 0 placed), MRPC Dev (1 judged, 0 placed), SICK-R (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
19 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
2 subtasks in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 2,381 · with a code link: 693 · where Syntology ran a sample: 144 (114 with a run with no instrument failure, 30 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (144 of 2,381 tagged: 114 with a run with no instrument failure, 30 where every run was a failure of Syntology's instrument)
Page 1 of 24: papers 1 to 100 of 2,381, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
11 Oct 2018 534 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified (of 659 harvested samples) · 164 pointer-only (licence)We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers.
-
26 Jul 2019 67 repositories listed Syntology community repositories only · 37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified (of 48 harvested samples) · 24 pointer-only (licence)Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging.
-
27 Aug 2019 64 repositories listed Syntology community repositories only · 33 ran (of which 9 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 3 where Syntology's instrument failed) · 25 unverified (of 58 harvested samples) · 11 pointer-only (licence)However, it requires that both sentences are fed into the network, which causes a massive computational overhead: Finding the most similar pair in a collection of 10, 000 sentences requires about 50 million inference…
-
23 Oct 2019 57 repositories listed Syntology 21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified (of 31 harvested samples)Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP).
-
26 Sep 2019 48 repositories listed Syntology official (archive's flag): 6 ran · 81 ran (of which 17 constructed an object rather than computing a result; 56 with no instrument failure: 4 honoured, 0 violated, 52 with no contract checked; 25 where Syntology's instrument failed) · 45 unverified (of 126 harvested samples) · 28 pointer-only (licence)Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks.
-
2 Oct 2019 37 repositories listed Syntology official (archive's flag): 1 ran · 21 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified (of 27 harvested samples) · 2 pointer-only (licence)As Transfer Learning from large-scale pre-trained models becomes more prevalent in Natural Language Processing (NLP), operating these large models in on-the-edge and/or under constrained computational training or…
-
19 Jun 2019 27 repositories listed Syntology official (archive's flag): 1 ran · 15 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified (of 24 harvested samples) · 4 pointer-only (licence)With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling.
-
29 Mar 2018 24 repositories listed Syntology 18 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 22 harvested samples) · 1 pointer-only (licence)For both variants, we investigate and report the relationship between model complexity, resource consumption, the availability of transfer task training data, and task performance.
-
18 Apr 2021 23 repositories listed Syntology community repositories only · 17 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified (of 30 harvested samples) · 19 pointer-only (licence)This paper presents SimCSE, a simple contrastive learning framework that greatly advances state-of-the-art sentence embeddings.
-
5 May 2017 23 repositories listed Syntology official (archive's flag): 3 ran · 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features.
-
19 Apr 2019 19 repositories listed Syntology community repositories only · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples)We present a novel language representation model enhanced by knowledge called ERNIE (Enhanced Representation through kNowledge IntEgration).
-
28 Jul 2020 14 repositories listed Syntology official (archive's flag): 1 ran · 10 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified (of 15 harvested samples) · 11 pointer-only (licence)To remedy this, we propose, BigBird, a sparse attention mechanism that reduces this quadratic dependency to linear.
-
5 Jun 2020 14 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified (of 13 harvested samples) · 3 pointer-only (licence)Recent progress in pre-trained neural language models has significantly improved the performance of many natural language processing (NLP) tasks.
-
11 Jun 2018 13 repositories listedWe demonstrate that large gains on these tasks can be realized by generative pre-training of a language model on a diverse corpus of unlabeled text, followed by discriminative fine-tuning on each specific task.
-
9 May 2021 12 repositories listed Syntology community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 1 pointer-only (licence)At longer input lengths, our FNet model is significantly faster: when compared to the "efficient" Transformers on the Long Range Arena benchmark, FNet matches the accuracy of the most accurate models, while outpacing…
-
7 Feb 2021 10 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 1 pointer-only (licence)The scalability of Nyströmformer enables application to longer sequences with thousands of tokens.
-
23 Sep 2019 10 repositories listed Syntology official: harvested, nothing ran · 0 ran · 4 unverified (of 4 harvested samples) · 4 pointer-only (licence)To accelerate inference and reduce model size while maintaining accuracy, we first propose a novel Transformer distillation method that is specially designed for knowledge distillation (KD) of the Transformer-based…
-
6 Apr 2020 7 repositories listedThen, we conduct knowledge transfer from this teacher to MobileBERT.
-
14 Apr 2021 6 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)Learning sentence embeddings often requires a large amount of labeled data.
-
3 Jul 2020 6 repositories listedWhile BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning (Reimers and Gurevych, 2019), BERT based cross-lingual sentence embeddings…
-
19 Jun 2020 6 repositories listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)Humans read and write hundreds of billions of messages every day.
-
8 Nov 2019 6 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples) · 1 pointer-only (licence)However, due to limited data resources from downstream tasks and the extremely large capacity of pre-trained models, aggressive fine-tuning often causes the adapted model to overfit the data of downstream tasks and…
-
24 Jul 2019 6 repositories listed Syntology official (archive's flag): 2 ran · 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified (of 15 harvested samples) · 6 pointer-only (licence)We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text.
-
13 Oct 2022 5 repositories listed Syntology community repositories only · 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 13 harvested samples)MTEB spans 8 embedding tasks covering a total of 58 datasets and 112 languages.
-
21 Dec 2020 5 repositories listedTransformer is the backbone of modern NLP models.
-
14 Oct 2019 5 repositories listed Syntology official (archive's flag): 5 ran · 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 11 harvested samples) · 3 pointer-only (licence)Recently, pre-trained Transformer based language models such as BERT and GPT, have shown great improvement in many Natural Language Processing (NLP) tasks.
-
28 Aug 2018 5 repositories listedA subset of MedSTS (MedSTS_ann) containing 1, 068 sentence pairs was annotated by two medical experts with semantic similarity scores of 0-5 (low to high similarity).
-
19 Dec 2022 4 repositories listed Syntology official (archive's flag): 15 ran · 17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 3 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 20 harvested samples) · 2 pointer-only (licence)Our analysis suggests that INSTRUCTOR is robust to changes in instructions, and that instruction finetuning mitigates the challenge of training a single model on diverse datasets.
-
15 Aug 2022 4 repositories listed Syntology official: harvested, nothing ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 2 pointer-only (licence)We develop a procedure for Int8 matrix multiplication for feed-forward and attention projection layers in transformers, which cut the memory needed for inference by half while retaining full precision performance.
-
20 May 2021 4 repositories listedWe introduce Korean Language Understanding Evaluation (KLUE) benchmark.
-
15 Apr 2021 4 repositories listed
-
30 Mar 2018 4 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
15 Feb 2018 4 repositories listed
-
2 Sep 2024 3 repositories listed
-
18 Mar 2021 3 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
29 Dec 2020 3 repositories listed Syntology official (archive's flag): 4 ran · 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples) · 6 pointer-only (licence)
-
2 Nov 2020 3 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
7 Apr 2020 3 repositories listed
-
16 Feb 2020 3 repositories listed
-
17 Sep 2019 3 repositories listed
-
29 Jul 2019 3 repositories listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
27 Jul 2019 3 repositories listed Syntology official: harvested for another paper · 0 ran · 1 unverified (of 1 harvested sample)
-
20 Apr 2019 3 repositories listed
-
4 Nov 2018 3 repositories listed
-
1 May 2018 3 repositories listed
-
20 Aug 2017 3 repositories listed
-
SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation31 Jul 2017 3 repositories listed
-
17 Feb 2016 3 repositories listed
-
20 Sep 2024 2 repositories listed
-
19 Sep 2024 2 repositories listed
-
14 Jun 2024 2 repositories listed
-
8 Jun 2024 2 repositories listed
-
2 Apr 2024 2 repositories listed Syntology official (archive's flag): 12 ran · 12 ran (of which 7 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified (of 18 harvested samples) · 2 pointer-only (licence)
-
13 Feb 2024 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
13 Feb 2024 2 repositories listed Syntology 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
16 Dec 2023 2 repositories listed
-
9 Nov 2023 2 repositories listed Syntology community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)
-
20 Oct 2023 2 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
22 Sep 2023 2 repositories listed
-
24 Aug 2023 2 repositories listed
-
18 Jul 2023 2 repositories listed Syntology official: harvested, nothing ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 1 pointer-only (licence)
-
30 May 2023 2 repositories listed Syntology official (archive's flag): 4 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 1 pointer-only (licence)
-
26 May 2023 2 repositories listed
-
23 May 2023 2 repositories listed
-
19 May 2023 2 repositories listed
-
21 Dec 2022 2 repositories listed
-
29 Nov 2022 2 repositories listed
-
26 Sep 2022 2 repositories listed
-
29 Jun 2022 2 repositories listed
-
5 Mar 2022 2 repositories listed
-
9 Dec 2021 2 repositories listed
-
29 Nov 2021 2 repositories listed
-
25 Oct 2021 2 repositories listed Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
10 Oct 2021 2 repositories listed Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)
-
23 Aug 2021 2 repositories listed
-
19 Aug 2021 2 repositories listed
-
23 Jun 2021 2 repositories listed Syntology community repositories only · 7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples)
-
20 Apr 2021 2 repositories listed
-
15 Apr 2021 2 repositories listed Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
11 Apr 2021 2 repositories listed
-
22 Mar 2021 2 repositories listed
-
22 Dec 2020 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
13 Dec 2020 2 repositories listed
-
3 Dec 2020 2 repositories listed
-
27 Nov 2020 2 repositories listed
-
27 Oct 2020 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 4 harvested samples) · 1 pointer-only (licence)
-
19 Aug 2020 2 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
4 May 2020 2 repositories listed Syntology official (archive's flag): 1 ran · 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
30 Apr 2020 2 repositories listed
-
27 Mar 2020 2 repositories listed
-
26 Feb 2020 2 repositories listed
-
17 Jan 2020 2 repositories listed
-
25 Dec 2019 2 repositories listed
-
10 Nov 2019 2 repositories listed
-
9 Jul 2019 2 repositories listed
-
17 May 2019 2 repositories listed Syntology official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 1 pointer-only (licence)
-
30 Apr 2019 2 repositories listed
-
8 Mar 2019 2 repositories listed Syntology community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 12 harvested samples) · 1 pointer-only (licence)
Syntology lines on 49 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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