Chess as a Testbed for Language Model State Tracking Article Swipe
Shubham Toshniwal
,
Sam Wiseman
,
Karen Livescu
,
Kevin Gimpel
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v36i10.21390
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v36i10.21390
Transformer language models have made tremendous strides in natural language understanding tasks. However, the complexity of natural language makes it challenging to ascertain how accurately these models are tracking the world state underlying the text. Motivated by this issue, we consider the task of language modeling for the game of chess. Unlike natural language, chess notations describe a simple, constrained, and deterministic domain. Moreover, we observe that the appropriate choice of chess notation allows for directly probing the world state, without requiring any additional probing-related machinery. We find that: (a) With enough training data, transformer language models can learn to track pieces and predict legal moves with high accuracy when trained solely on move sequences. (b) For small training sets providing access to board state information during training can yield significant improvements. (c) The success of transformer language models is dependent on access to the entire game history i.e. “full attention”. Approximating this full attention results in a significant performance drop. We propose this testbed as a benchmark for future work on the development and analysis of transformer language models.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1609/aaai.v36i10.21390
- https://ojs.aaai.org/index.php/AAAI/article/download/21390/21139
- OA Status
- diamond
- Cited By
- 14
- References
- 49
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4283793451
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4283793451Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1609/aaai.v36i10.21390Digital Object Identifier
- Title
-
Chess as a Testbed for Language Model State TrackingWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-06-28Full publication date if available
- Authors
-
Shubham Toshniwal, Sam Wiseman, Karen Livescu, Kevin GimpelList of authors in order
- Landing page
-
https://doi.org/10.1609/aaai.v36i10.21390Publisher landing page
- PDF URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/21390/21139Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/21390/21139Direct OA link when available
- Concepts
-
Computer science, Testbed, Language model, Natural language, Transformer, Notation, Artificial intelligence, Natural language understanding, Natural language processing, Machine learning, Engineering, Linguistics, Computer network, Electrical engineering, Voltage, PhilosophyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
14Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 3, 2024: 5, 2023: 4, 2022: 2Per-year citation counts (last 5 years)
- References (count)
-
49Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4283793451 |
|---|---|
| doi | https://doi.org/10.1609/aaai.v36i10.21390 |
| ids.doi | https://doi.org/10.1609/aaai.v36i10.21390 |
| ids.openalex | https://openalex.org/W4283793451 |
| fwci | 1.64577056 |
| type | article |
| title | Chess as a Testbed for Language Model State Tracking |
| biblio.issue | 10 |
| biblio.volume | 36 |
| biblio.last_page | 11393 |
| biblio.first_page | 11385 |
| topics[0].id | https://openalex.org/T10028 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.991100013256073 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Topic Modeling |
| topics[1].id | https://openalex.org/T11674 |
| topics[1].field.id | https://openalex.org/fields/20 |
| topics[1].field.display_name | Economics, Econometrics and Finance |
| topics[1].score | 0.9909999966621399 |
| topics[1].domain.id | https://openalex.org/domains/2 |
| topics[1].domain.display_name | Social Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2002 |
| topics[1].subfield.display_name | Economics and Econometrics |
| topics[1].display_name | Sports Analytics and Performance |
| topics[2].id | https://openalex.org/T10181 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.973800003528595 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Natural Language Processing Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7724384665489197 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C31395832 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7595502138137817 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1318674 |
| concepts[1].display_name | Testbed |
| concepts[2].id | https://openalex.org/C137293760 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6908013224601746 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[2].display_name | Language model |
| concepts[3].id | https://openalex.org/C195324797 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6216021180152893 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q33742 |
| concepts[3].display_name | Natural language |
| concepts[4].id | https://openalex.org/C66322947 |
| concepts[4].level | 3 |
| concepts[4].score | 0.5820537805557251 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[4].display_name | Transformer |
| concepts[5].id | https://openalex.org/C45357846 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5279741883277893 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2001982 |
| concepts[5].display_name | Notation |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.5027084350585938 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C2779439875 |
| concepts[7].level | 3 |
| concepts[7].score | 0.43068578839302063 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1078276 |
| concepts[7].display_name | Natural language understanding |
| concepts[8].id | https://openalex.org/C204321447 |
| concepts[8].level | 1 |
| concepts[8].score | 0.4130479693412781 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[8].display_name | Natural language processing |
| concepts[9].id | https://openalex.org/C119857082 |
| concepts[9].level | 1 |
| concepts[9].score | 0.33445632457733154 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[9].display_name | Machine learning |
| concepts[10].id | https://openalex.org/C127413603 |
| concepts[10].level | 0 |
| concepts[10].score | 0.11877146363258362 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[10].display_name | Engineering |
| concepts[11].id | https://openalex.org/C41895202 |
| concepts[11].level | 1 |
| concepts[11].score | 0.08780255913734436 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[11].display_name | Linguistics |
| concepts[12].id | https://openalex.org/C31258907 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[12].display_name | Computer network |
| concepts[13].id | https://openalex.org/C119599485 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q43035 |
| concepts[13].display_name | Electrical engineering |
| concepts[14].id | https://openalex.org/C165801399 |
| concepts[14].level | 2 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[14].display_name | Voltage |
| concepts[15].id | https://openalex.org/C138885662 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[15].display_name | Philosophy |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7724384665489197 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/testbed |
| keywords[1].score | 0.7595502138137817 |
| keywords[1].display_name | Testbed |
| keywords[2].id | https://openalex.org/keywords/language-model |
| keywords[2].score | 0.6908013224601746 |
| keywords[2].display_name | Language model |
| keywords[3].id | https://openalex.org/keywords/natural-language |
| keywords[3].score | 0.6216021180152893 |
| keywords[3].display_name | Natural language |
| keywords[4].id | https://openalex.org/keywords/transformer |
| keywords[4].score | 0.5820537805557251 |
| keywords[4].display_name | Transformer |
| keywords[5].id | https://openalex.org/keywords/notation |
| keywords[5].score | 0.5279741883277893 |
| keywords[5].display_name | Notation |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.5027084350585938 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/natural-language-understanding |
| keywords[7].score | 0.43068578839302063 |
| keywords[7].display_name | Natural language understanding |
| keywords[8].id | https://openalex.org/keywords/natural-language-processing |
| keywords[8].score | 0.4130479693412781 |
| keywords[8].display_name | Natural language processing |
| keywords[9].id | https://openalex.org/keywords/machine-learning |
| keywords[9].score | 0.33445632457733154 |
| keywords[9].display_name | Machine learning |
| keywords[10].id | https://openalex.org/keywords/engineering |
| keywords[10].score | 0.11877146363258362 |
| keywords[10].display_name | Engineering |
| keywords[11].id | https://openalex.org/keywords/linguistics |
| keywords[11].score | 0.08780255913734436 |
| keywords[11].display_name | Linguistics |
| language | en |
| locations[0].id | doi:10.1609/aaai.v36i10.21390 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210191458 |
| locations[0].source.issn | 2159-5399, 2374-3468 |
| locations[0].source.type | conference |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2159-5399 |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].source.host_organization | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| locations[0].license | |
| locations[0].pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/21390/21139 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].landing_page_url | https://doi.org/10.1609/aaai.v36i10.21390 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5073890145 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Shubham Toshniwal |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I160992636 |
| authorships[0].affiliations[0].raw_affiliation_string | TTI Chicago |
| authorships[0].institutions[0].id | https://openalex.org/I160992636 |
| authorships[0].institutions[0].ror | https://ror.org/02sn5gb64 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I160992636 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | Toyota Technological Institute at Chicago |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Shubham Toshniwal |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | TTI Chicago |
| authorships[1].author.id | https://openalex.org/A5073227709 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-0923-1086 |
| authorships[1].author.display_name | Sam Wiseman |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I170897317 |
| authorships[1].affiliations[0].raw_affiliation_string | Duke University |
| authorships[1].institutions[0].id | https://openalex.org/I170897317 |
| authorships[1].institutions[0].ror | https://ror.org/00py81415 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I170897317 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | Duke University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Sam Wiseman |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Duke University |
| authorships[2].author.id | https://openalex.org/A5015602781 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-4962-946X |
| authorships[2].author.display_name | Karen Livescu |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I160992636 |
| authorships[2].affiliations[0].raw_affiliation_string | TTI Chicago |
| authorships[2].institutions[0].id | https://openalex.org/I160992636 |
| authorships[2].institutions[0].ror | https://ror.org/02sn5gb64 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I160992636 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | Toyota Technological Institute at Chicago |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Karen Livescu |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | TTI Chicago |
| authorships[3].author.id | https://openalex.org/A5081022650 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Kevin Gimpel |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I160992636 |
| authorships[3].affiliations[0].raw_affiliation_string | TTI Chicago |
| authorships[3].institutions[0].id | https://openalex.org/I160992636 |
| authorships[3].institutions[0].ror | https://ror.org/02sn5gb64 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I160992636 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | Toyota Technological Institute at Chicago |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Kevin Gimpel |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | TTI Chicago |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://ojs.aaai.org/index.php/AAAI/article/download/21390/21139 |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Chess as a Testbed for Language Model State Tracking |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10028 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.991100013256073 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Topic Modeling |
| related_works | https://openalex.org/W2367925007, https://openalex.org/W3015724364, https://openalex.org/W4288263119, https://openalex.org/W2967994095, https://openalex.org/W2900126711, https://openalex.org/W4285240985, https://openalex.org/W4225162083, https://openalex.org/W3202115945, https://openalex.org/W2542958340, https://openalex.org/W4286930972 |
| cited_by_count | 14 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 3 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 5 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 4 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 2 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1609/aaai.v36i10.21390 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210191458 |
| best_oa_location.source.issn | 2159-5399, 2374-3468 |
| best_oa_location.source.type | conference |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2159-5399 |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.source.host_organization | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/21390/21139 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.landing_page_url | https://doi.org/10.1609/aaai.v36i10.21390 |
| primary_location.id | doi:10.1609/aaai.v36i10.21390 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210191458 |
| primary_location.source.issn | 2159-5399, 2374-3468 |
| primary_location.source.type | conference |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2159-5399 |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.source.host_organization | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| primary_location.license | |
| primary_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/21390/21139 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.landing_page_url | https://doi.org/10.1609/aaai.v36i10.21390 |
| publication_date | 2022-06-28 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W2515741950, https://openalex.org/W2529194139, https://openalex.org/W6783944145, https://openalex.org/W2810346659, https://openalex.org/W6891798393, https://openalex.org/W2896457183, https://openalex.org/W2965647350, https://openalex.org/W2516090925, https://openalex.org/W6739847781, https://openalex.org/W6632455782, https://openalex.org/W2970862333, https://openalex.org/W2126209950, https://openalex.org/W6745610606, https://openalex.org/W6666761814, https://openalex.org/W3034573343, https://openalex.org/W6631190155, https://openalex.org/W6771626834, https://openalex.org/W6631834165, https://openalex.org/W6745245109, https://openalex.org/W2466175319, https://openalex.org/W6739518724, https://openalex.org/W2473344385, https://openalex.org/W2970971581, https://openalex.org/W3015449890, https://openalex.org/W2902907165, https://openalex.org/W2908854766, https://openalex.org/W2980282514, https://openalex.org/W3047988254, https://openalex.org/W4292779060, https://openalex.org/W2766569996, https://openalex.org/W1525961042, https://openalex.org/W1522301498, https://openalex.org/W4301785137, https://openalex.org/W3035305735, https://openalex.org/W3098637454, https://openalex.org/W4309793872, https://openalex.org/W2970476646, https://openalex.org/W4297798492, https://openalex.org/W2692059227, https://openalex.org/W3037798801, https://openalex.org/W2949615363, https://openalex.org/W2763421725, https://openalex.org/W3004346089, https://openalex.org/W4288351520, https://openalex.org/W4295838474, https://openalex.org/W4385245566, https://openalex.org/W2963015836, https://openalex.org/W4213009331, https://openalex.org/W4295312788 |
| referenced_works_count | 49 |
| abstract_inverted_index.a | 57, 157, 166 |
| abstract_inverted_index.We | 86, 161 |
| abstract_inverted_index.as | 165 |
| abstract_inverted_index.by | 36 |
| abstract_inverted_index.in | 7, 156 |
| abstract_inverted_index.is | 139 |
| abstract_inverted_index.it | 19 |
| abstract_inverted_index.of | 15, 43, 49, 70, 135, 176 |
| abstract_inverted_index.on | 112, 141, 171 |
| abstract_inverted_index.to | 21, 99, 122, 143 |
| abstract_inverted_index.we | 39, 64 |
| abstract_inverted_index.(a) | 89 |
| abstract_inverted_index.(b) | 115 |
| abstract_inverted_index.(c) | 132 |
| abstract_inverted_index.For | 116 |
| abstract_inverted_index.The | 133 |
| abstract_inverted_index.and | 60, 102, 174 |
| abstract_inverted_index.any | 82 |
| abstract_inverted_index.are | 27 |
| abstract_inverted_index.can | 97, 128 |
| abstract_inverted_index.for | 46, 74, 168 |
| abstract_inverted_index.how | 23 |
| abstract_inverted_index.the | 13, 29, 33, 41, 47, 67, 77, 144, 172 |
| abstract_inverted_index.With | 90 |
| abstract_inverted_index.find | 87 |
| abstract_inverted_index.full | 153 |
| abstract_inverted_index.game | 48, 146 |
| abstract_inverted_index.have | 3 |
| abstract_inverted_index.high | 107 |
| abstract_inverted_index.i.e. | 148 |
| abstract_inverted_index.made | 4 |
| abstract_inverted_index.move | 113 |
| abstract_inverted_index.sets | 119 |
| abstract_inverted_index.task | 42 |
| abstract_inverted_index.that | 66 |
| abstract_inverted_index.this | 37, 152, 163 |
| abstract_inverted_index.when | 109 |
| abstract_inverted_index.with | 106 |
| abstract_inverted_index.work | 170 |
| abstract_inverted_index.board | 123 |
| abstract_inverted_index.chess | 54, 71 |
| abstract_inverted_index.data, | 93 |
| abstract_inverted_index.drop. | 160 |
| abstract_inverted_index.learn | 98 |
| abstract_inverted_index.legal | 104 |
| abstract_inverted_index.makes | 18 |
| abstract_inverted_index.moves | 105 |
| abstract_inverted_index.small | 117 |
| abstract_inverted_index.state | 31, 124 |
| abstract_inverted_index.text. | 34 |
| abstract_inverted_index.that: | 88 |
| abstract_inverted_index.these | 25 |
| abstract_inverted_index.track | 100 |
| abstract_inverted_index.world | 30, 78 |
| abstract_inverted_index.yield | 129 |
| abstract_inverted_index.Unlike | 51 |
| abstract_inverted_index.access | 121, 142 |
| abstract_inverted_index.allows | 73 |
| abstract_inverted_index.chess. | 50 |
| abstract_inverted_index.choice | 69 |
| abstract_inverted_index.during | 126 |
| abstract_inverted_index.enough | 91 |
| abstract_inverted_index.entire | 145 |
| abstract_inverted_index.future | 169 |
| abstract_inverted_index.issue, | 38 |
| abstract_inverted_index.models | 2, 26, 96, 138 |
| abstract_inverted_index.pieces | 101 |
| abstract_inverted_index.solely | 111 |
| abstract_inverted_index.state, | 79 |
| abstract_inverted_index.tasks. | 11 |
| abstract_inverted_index.domain. | 62 |
| abstract_inverted_index.history | 147 |
| abstract_inverted_index.models. | 179 |
| abstract_inverted_index.natural | 8, 16, 52 |
| abstract_inverted_index.observe | 65 |
| abstract_inverted_index.predict | 103 |
| abstract_inverted_index.probing | 76 |
| abstract_inverted_index.propose | 162 |
| abstract_inverted_index.results | 155 |
| abstract_inverted_index.simple, | 58 |
| abstract_inverted_index.strides | 6 |
| abstract_inverted_index.success | 134 |
| abstract_inverted_index.testbed | 164 |
| abstract_inverted_index.trained | 110 |
| abstract_inverted_index.without | 80 |
| abstract_inverted_index.“full | 149 |
| abstract_inverted_index.However, | 12 |
| abstract_inverted_index.accuracy | 108 |
| abstract_inverted_index.analysis | 175 |
| abstract_inverted_index.consider | 40 |
| abstract_inverted_index.describe | 56 |
| abstract_inverted_index.directly | 75 |
| abstract_inverted_index.language | 1, 9, 17, 44, 95, 137, 178 |
| abstract_inverted_index.modeling | 45 |
| abstract_inverted_index.notation | 72 |
| abstract_inverted_index.tracking | 28 |
| abstract_inverted_index.training | 92, 118, 127 |
| abstract_inverted_index.Moreover, | 63 |
| abstract_inverted_index.Motivated | 35 |
| abstract_inverted_index.ascertain | 22 |
| abstract_inverted_index.attention | 154 |
| abstract_inverted_index.benchmark | 167 |
| abstract_inverted_index.dependent | 140 |
| abstract_inverted_index.language, | 53 |
| abstract_inverted_index.notations | 55 |
| abstract_inverted_index.providing | 120 |
| abstract_inverted_index.requiring | 81 |
| abstract_inverted_index.accurately | 24 |
| abstract_inverted_index.additional | 83 |
| abstract_inverted_index.complexity | 14 |
| abstract_inverted_index.machinery. | 85 |
| abstract_inverted_index.sequences. | 114 |
| abstract_inverted_index.tremendous | 5 |
| abstract_inverted_index.underlying | 32 |
| abstract_inverted_index.Transformer | 0 |
| abstract_inverted_index.appropriate | 68 |
| abstract_inverted_index.challenging | 20 |
| abstract_inverted_index.development | 173 |
| abstract_inverted_index.information | 125 |
| abstract_inverted_index.performance | 159 |
| abstract_inverted_index.significant | 130, 158 |
| abstract_inverted_index.transformer | 94, 136, 177 |
| abstract_inverted_index.constrained, | 59 |
| abstract_inverted_index.Approximating | 151 |
| abstract_inverted_index.attention”. | 150 |
| abstract_inverted_index.deterministic | 61 |
| abstract_inverted_index.improvements. | 131 |
| abstract_inverted_index.understanding | 10 |
| abstract_inverted_index.probing-related | 84 |
| cited_by_percentile_year.max | 98 |
| cited_by_percentile_year.min | 94 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.5699999928474426 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.84423844 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |