Published May 28, 2026 | Version 1.0.0
Software Open

Scinobo Research Artifact Analysis (RAA) tool

  • 1. ROR icon Athena Research and Innovation Center In Information Communication & Knowledge Technologies
  • 2. ROR icon Institute for Language and Speech Processing
  • 3. ROR icon OpenAIRE Non-Profit Civil Partnership
  • 4. OPIX

Description

This tool performs RAA on scientific texts to extract mentions of research artifacts (RAs) (e.g. datasets, software) along with their metadata and then deduplicates these mentions to find the unique RAs that were referenced, (re)used or created in the text. It is based on finetuned LLMs and depends on a list of keywords/keyphrases/gazetteers to detect candidate mentions to RAs in the texts (source: default list of keywords for Computer Science and a default list of gazetteers from PapersWithCode).

For more information:

Files

adapter_config.json

Files (21.7 MB)

Name Size Download all
md5:07d4dd16c81f1d52893d68cbe2e2f548
333 Bytes Preview Download
md5:f8b99f0ab4a106a35bdc47dafd1da4bc
7.1 MB Download
md5:6401aee245fee679f67359873a1714d8
3.2 kB Download
md5:be0be2ff19986528f2d05839cf66c70e
1.5 MB Preview Download
md5:95f440a13c4f86b5aa45b974c1a116ca
428.9 kB Preview Download
md5:eb460070aa3114a98fc73b94e8c63d13
770.7 kB Preview Download
md5:48e6de75de9c9a9f730de806981a6605
2.7 MB Preview Download
md5:30aadb2c0cfd18cba5e1a2cc84b4858e
451.5 kB Preview Download
md5:92c301c3424686d64ae3a154501d27c5
143.9 kB Preview Download
md5:451d7b89662fd5f34e8f30186733ac69
44.5 kB Download
md5:b879815dd24addebcc3a6af4e6796898
21.6 kB Download
md5:0439cf8b3fbbbf57179607d9d0d0bdb5
2.7 kB Preview Download
md5:e3fb48d9cf418d74432427dbc79f7536
2.5 MB Download
md5:24e399dcb333f80d8dda9f1179488552
918 Bytes Download
md5:38d9e8e7774a50b2556d334ab3f6dbb4
1.3 kB Download
md5:b95fb8cfd3aba001d658334a62cc18ce
918 Bytes Download
md5:9e422555508a43b0bb4c8a500ab8b7c9
265 Bytes Download
md5:a1f674c4293fe7825e4f75d8ac46f9ef
10.5 kB Download
md5:090671b63ca55212c381706f62fea6b5
50.5 kB Preview Download
md5:052dfc4405e55091f3a256d922d280df
168.0 kB Download
md5:47fc1141ec89f16607084b3eb7926109
11.2 kB Download
md5:9c56c1ea8bc93fd5a88cf2b09067dbe3
196.5 kB Download
md5:b45b0f5df96b7e976f17b8e76a5804a2
155.9 kB Download
md5:808dc498ad6b63450b08828b8a30211d
1.1 kB Download
md5:88d83d91cf60599cef72b860dd077ea9
1.7 kB Download
md5:734224946001900bd57abec0d780fba9
1.2 kB Download
md5:dcc0f134f46da27c43153e8d1edbf310
1.2 kB Download
md5:fd3e7c84b06b5998ff2d60cd8ec2c1af
713.7 kB Download
md5:10a94ca707c4435fe83329cdb0926130
4.6 kB Download
md5:2a174fc2d61ae7a61c12eb415e147412
72.7 kB Preview Download
md5:5cb29b9b65a4362c5106cd62b4548417
108.8 kB Preview Download
md5:f3697a8d345609d7bbd6ca0b558b6446
60.8 kB Preview Download
md5:13a0b8740f77865de91dca7fce0db782
1.4 kB Preview Download
md5:eb8c07529ed827676e3b019e454844a5
14.9 kB Preview Download
md5:6d952c9e0ae02ad5e43ea65486a4aab1
1.0 kB Preview Download
md5:0fd8af615791f867d77d8974d6e5e152
125.8 kB Preview Download
md5:9efef828170455341dc32c6b688a0ed2
6.6 kB Preview Download
md5:d4ae36d87428a5b035e1d6fc62b28f8a
475 Bytes Preview Download
md5:c6c382ffe56e7055d44bdfadb17d6993
4.3 MB Download
md5:f62694e9b586fd99463e2a4e06f6505d
561 Bytes Preview Download
md5:68dea84b8b1eda59cc7cf139cd25bd99
8.0 kB Download
md5:9787c441b2763289bbb89731c6e7b425
6.0 kB Download

Additional details

Funding

European Commission
SciLake - Democratising and making sense out of heterogeneous scholarly content 101058573
European Commission
PathOS - Open Science Impact Pathways 101058728
European Commission
TIER2 - TIER2: ENHANCING TRUST, INTEGRITY AND EFFICIENCY IN RESEARCH THROUGH NEXT-LEVEL REPRODUCIBILITY IMPACT PATHWAYS 101094817

Software

Repository URL
https://github.com/iNoBo/scinobo-raa
Programming language
Python
Development Status
Active

References

  • Petros Stavropoulos, Ioannis Lyris, Natalia Manola, Ioanna Grypari, and Haris Papageorgiou. 2023. Empowering Knowledge Discovery from Scientific Literature: A novel approach to Research Artifact Analysis. In Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023), pages 37–53, Singapore. Association for Computational Linguistics.