Databases · arXiv:2611.17044 v1 · submitted 12 Nov 2026 · 36 references
[Experiment, Analysis, and Benchmark] How well do LLMs comprehend and design relational database schemata?
The paper says
“Large Language Models (LLMs) are increasingly used for database tasks, yet most work, such as Text2SQL, assumes that the relational schema already exists.”
more of the abstract
We ask whether LLMs can design a schema from natural language requirements (Text2Schema), verbalize an existing schema (Schema2Text), and preserve its structure through a Schema-to-Text-to-Schema round trip. We present SchemaBridge, a benchmark of 902 schemata from three collections, stratified by size and constraint complexity, that scores fidelity separately for tables, attributes, domain (data types and nullability), entity, and referential integrity. Evaluating six open-weight and proprietary LLMs, we find that: (i) human-written requirements under-specify schemata, with no model exceeding 0.27 referential integrity F1; (ii) LLM-generated descriptions carry far more structure when explicitly asked to be complete, raising GPT-5.4-mini's referential F1 on SchemaBench from 0.228 to 0.909, even as BLEU, ROUGE-L, and BERTScore decrease; (iii) controlled experiments show that both constructor and describer choices influence round-trip fidelity under fixed settings; and (iv) masked schema experiments show that structural cues support recovery of keys and relationships, while joint data-type and nullability information is poorly retained through verbalization. Code and data are available at https://github.com/iamsriom/SchemaBridge
from the abstract
Pith says
Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded · not checked by a person
It can be wrong. Challenge this review or reply to it.
Holds up, with conditions. SchemaBridge is a careful, reusable benchmark for LLM schema reasoning, but its headline claim about human-written requirements is weaker than advertised because the data provenance is unverified. This line is wrong
3 major objections · 8 minor
How often objections from reviews like this one are right: not yet measured
Not checked: figures, code, what the 36 references say.
The paper says, at Abstract, §V-B, §IV-A
The review did not quote this passage.
A classifier read this sentence of the paper as acknowledging the concern (probability 0.60):
“The dataset documentation states that the examples were manually curated and semi-automatically validated, but it does not describe the validation procedure or indicate whether the specifications were written entirely by humans or with LLM assistance.”
Pith says: Objection 1 of 3 · major
The claim that 'human-written requirements under-specify schemata' (abstract, b4; §V-B) is load-bearing but rests on unverified premises about the datasets. As the paper itself discloses (§IV-A, b147), RSchema requirements were partially LLM-generated, and SchemaBench's documentation does not confirm human authorship.
more of objection 1
The abstract and conclusion assert the claim unhedged. The paper should either (a) provide evidence that the requirements are representative of human-authored specifications, or (b) soften the claim to 'the evaluated requirements (which may include LLM-generated content) under-specify schemata relative to the gold references.' Without this, finding (i) is ambiguous.
The paper says, at §V-B, Table V, §III-E
The review did not quote this passage.
A classifier read this sentence of the paper as acknowledging the concern (probability 0.75):
“Note that EASYdoes not imply easier reconstruction: constraint-sparse schemata leave an LLM more room to add structure that the gold design omits, which exact matching counts as errors (§V-B and V-F).”
Pith says: Objection 2 of 3 · major
The low referential F1 (≤0.27) is interpreted as requirements under-specifying schemata, but the paper does not control for the strictness of exact-match scoring. Referential integrity requires an exact 4-tuple match (§III-E), which is the harshest criterion. The paper concedes that exact matching counts valid alternative designs as errors (b173).
more of objection 2
Without a human baseline or an alternative scoring that rewards partial matches, the extent to which the low F1 reflects missing information vs. scoring strictness is unknown. The authors should discuss this limitation explicitly and consider reporting a relaxed metric (e.g., allowing equivalent foreign keys with different column orderings or naming).
The paper says, at §V-B, Table VI
The review did not quote this passage.
Pith says: Objection 3 of 3 · major
The baseline comparison (Table VI) shows that few-shot prompting improves referential F1 from 0.004–0.146 to 0.118–0.188, a 3–4x swing. This indicates that the scores are sensitive to extraction behavior (prompting strategy) rather than purely to information content. The paper acknowledges this indirectly but does not reconcile it with the 'under-specify' interpretation.
more of objection 3
If a simple few-shot prompt can triple referential F1, the ceiling may be higher than 0.27 under optimal prompting, undermining the claim that requirements inherently lack information. The authors should discuss this.
8 minor objections
The paper says, at §III-B
Pith says: minor objection 1 of 8
The normalization of identifiers (lowercasing, removing underscores, etc.) is reasonable but may conflate distinct identifiers (e.g., 'order_id' vs 'orderid'). The authors should note this limitation.
The paper says, at §IV-B, Table III
Pith says: minor objection 2 of 8
The stratification thresholds (5/15 tables, 50/150 columns, s=4/10) are described as heuristic. The paper should justify these thresholds more concretely or show that results are robust to small variations.
show 6 more
The paper says, at §V-C, Table VII
Pith says: minor objection 3 of 8
SCR is reported as macro-average, but the paper does not specify whether it is macro- or micro-averaged. Clarify.
The paper says, at §V-D, Table VIII
Pith says: minor objection 4 of 8
The round-trip results for RSchema show very high F1 (e.g., 0.994 for tables under detailed prompting). This is surprising given the low Text2Schema scores. The authors should comment on why round-trip preservation is so high for RSchema despite its requirements being underspecified.
The paper says, at §V-F, Table X
Pith says: minor objection 5 of 8
The heuristic inferability labels are described as reflecting structural clues rather than logical entailment. The paper should provide examples of what makes an element 'inferable' vs 'non-inferable' to aid reproducibility.
The paper says, at §V-G, Table XII
Pith says: minor objection 6 of 8
The cost analysis uses only 30 schemas per dataset. The authors should note that these estimates may not generalize to the full dataset.
The paper says, at §VI
Pith says: minor objection 7 of 8
The recommendations are sensible but some are generic (e.g., 'Specify structural requirements explicitly'). The authors could tie them more directly to specific findings.
The paper says, at General
Pith says: minor objection 8 of 8
The paper uses 'human-written requirements' in the abstract and conclusion but the datasets include LLM-generated content. This should be corrected for accuracy.
What would settle it
Run a human-expert baseline on the same requirements with the identical SchemaBridge scoring (§III-E): recruit 3–5 independent database designers to produce DDL for a stratified sample (≥30 per dataset) of RSchema and SchemaBench requirements, given only the requirement text and the constructor prompt's output specification. Compare their micro-averaged referential-integrity F1 with the 0.27 LLM ceiling. If expert human F1 stays near or below 0.27, the requirements genuinely under-specify and finding (i) survives (modulo authorship).
from the skeptic's reading
How the review went
4 readings by deepseek-v4-flash · 13 Nov 2026
- Reader holds up, with conditions
- Skeptic partly agrees
- Editor wrote the verdict above
- Referee major revision: 3 major objections, 8 minor
Not run on this paper: the simulated authors' defence.
Pith did not check this review's objections against the paper.
The review in full
The review in brief, machine-written
The paper builds SchemaBridge, a benchmark that jointly evaluates Text2Schema, Schema2Text, and Schema→Text→Schema round-trip preservation across 902 schemata, with per-dimension structural fidelity scoring (tables, attributes, domain, entity, referential integrity). This unified treatment is genuinely new relative to SchemaAgent, SchemaBench, and Avignone et al., which each cover only part of the space. The methodology is careful: identifier and type normalization, micro-averaging, failures treated as empty predictions, and disclosed restrictions on domain evaluation. The round-trip and masking protocols are well-designed and yield internally consistent measurements. The finding that detailed prompting dramatically improves round-trip referential F1 (0.228→0.909 for GPT-5.4-mini on SchemaBench) while text-similarity metrics decrease is a useful empirical result. The paper also ships code and data, which is real evidence.
The soft spot is the headline claim that "human-written requirements under-specify schemata" (abstract, b4). The paper itself discloses (b147) that RSchema requirements were partially LLM-generated and SchemaBench's documentation does not indicate whether specifications were written entirely by humans or with LLM assistance. So the qualifier "human-written" is unverified for both datasets used in the Text2Schema evaluation. The stress-test note is correct on this point. The paper also concedes that exact matching counts valid alternative designs as errors (b173), and the referential dimension requires an exact 4-tuple match, which is the harshest criterion. No human control establishes how much of the 0.27 ceiling is mechanical. The paper's own baselines (Table VI) show few-shot prompting moving referential F1 on RSchema from 0.004–0.146 to 0.118–0.188, a 3–4x swing, indicating the scores are sensitive to extraction behavior rather than purely to information content. So finding (i) is unsupported as stated. Findings (ii)–(iv) are paired comparisons against the same gold DDL and survive this concern.
Who this is for: researchers working on LLM-based schema generation, schema verbalization, and benchmark design. The benchmark itself is reusable and the per-dimension scoring is a methodological contribution. The paper deserves a serious referee, but the authors should be asked to either verify the provenance of the requirement texts or soften the claim about human-written requirements. I would cite the benchmark methodology but not the headline claim without verification.
Recommendation: Accept for peer review with a request to address the data provenance issue for the Text2Schema findings.
The strongest objection
The load-bearing premise for finding (i) — 'human-written requirements under-specify schemata, with no model exceeding 0.27 referential-integrity F1' (abstract, b4) — is threefold: (a) the RSchema and SchemaBench requirement texts are genuinely human-authored and typical; (b) the gold schemata are correct; (c) the low F1 reflects missing information in the requirements rather than the strictness of exact-match scoring or constructor failure. Premise (a) is contradicted for RSchema, whose requirements the paper says were partially LLM-generated (Section IV-A), and unverified for SchemaBench, whose documentation 'does not... indicate whether the specifications were written entirely by humans or with LLM assistance' (b147); the abstract and conclusion (b285) assert the claim unhedged. Premise (c) is untested: matching is strict reference-based set matching (§III-E), the referential dimension requires an exact 4-tuple match (the harshest criterion), and the paper itself concedes that exact matching counts valid alternative designs as errors (b173; Introduction). No human control establishes how much of the 0.27 ceiling is mechanical. The paper's own baselines (Table VI) show few-shot prompting moving referential F1 on RSchema from 0.004–0.146 to 0.118–0.188, a 3–4x swing, indicating the scores are sensitive to extraction behavior rather than purely to information content. Findings (ii)–(iv) are paired comparisons against the same gold DDL and survive this concern; finding (i), the abstract's first headline, is unsupported as stated.
I confirm the reader's CONDITIONAL verdict. The most load-bearing concern is the interpretation attached to finding (i), not the measurements themselves. The abstract asserts 'human-written requirements under-specify schemata' (b4), while Section IV-A discloses that RSchema requirements were partially LLM-generated and that SchemaBench's documentation does not establish human authorship (b147); the paper's own text thus undermines the 'human-written' qualifier of its headline claim, and the conclusion (b285) repeats the claim unhedged. This is an internal tension, not a disagreement with external consensus. Second, even granting authorship, the inference from 'no model exceeds 0.27 referential F1' to 'requirements under-specify' presupposes that a human designer given the same requirements would match the gold schema; that premise is untested. Because matching is strict reference-based set matching (§III-E) and referential integrity requires exact 4-tuple agreement, valid alternative designs are penalized — a confound the paper itself acknowledges (b173; Introduction). The Table VI baselines, where few-shot prompting raises referential F1 3–4x, show the scores are sensitive to extraction behavior, complicating the under-specification reading. Credit where due: the round-trip finding (ii) is a paired comparison against the same gold DDL and survives these concerns, as do the masking retention results (iv); the disclosures at b147, b173, and b255–257 are honest and specific. The proposed human-expert baseline plus authorship verification would settle whether finding (i) describes requirement content or LLM performance under strict scoring. Since the framework, round-trip diagnosis, and masking findings retain value either way, CONDITIONAL remains the right verdict; at stake is the wording and interpretation of finding (i), not the benchmark itself.
The referee's report
If the findings hold, SchemaBridge provides a much-needed unified evaluation framework for schema-level reasoning, moving beyond Text2SQL. The per-dimension fidelity metrics and round-trip diagnosis are methodologically sound and practically useful. The finding that text-similarity metrics do not reflect structural preservation is important for the field. The benchmark and code are released, supporting reproducibility.
Pith's reading of the paper (a machine's summary, not the authors')
This paper argues that large language models are poor at constructing a relational database schema from a natural-language requirement (Text2Schema), with no tested model exceeding 0.27 F1 for referential integrity. However, when an existing schema is described in natural language with an explicit instruction to be exhaustive, a later reconstruction from that description can recover most of the original structure: GPT-5.4-mini's referential F1 on SchemaBench rises from 0.228 to 0.909. The authors introduce SchemaBridge, a benchmark of 902 schemata from three collections, and measure fidelity separately for tables, attributes, domain (data types and nullability), entity integrity, and referential integrity. They also show that text-similarity metrics like BLEU and ROUGE-L do not track structural preservation, that the choice of describer and constructor both matter independently, and that data-type and nullability information is especially fragile through verbalization.
What carries the argument. SchemaBridge is the central object: a unified benchmark of 902 relational schemata from Enterprise-145, RSchema, and SchemaBench, stratified by size and constraint complexity. It defines structural fidelity as exact set matching after normalization across five dimensions: tables, attributes, domain integrity (data type + nullability), entity integrity (primary keys and unique constraints), and referential integrity (foreign keys). The round-trip protocol (Schema→Text→Schema) with controlled describer and constructor isolation is the mechanism that separates verbalization loss from reconstruction loss.
Core claim. The paper establishes that LLMs can preserve relational schema structure through a Schema→Text→Schema round trip when the describer is prompted to be exhaustive, even though they cannot reliably construct a schema from typical human-authored requirements. The key empirical finding is that GPT-5.4-mini's referential integrity F1 on SchemaBench jumps from 0.228 (direct Text2Schema) to 0.909 (round trip with detailed description), while BLEU-4, ROUGE-L, and BERTScore all decrease. This reveals that standard text-similarity metrics are misleading for evaluating schema comprehension, and that the bottleneck is not the LLM's ability to reason about relational structure but the underspecification of natural-language requirements.
The premise it rests on. The claim that human-written requirements under-specify schemata depends on the premise that the requirements in RSchema and SchemaBench are genuinely human-authored and that their gold schemata are correct references, but the paper discloses that RSchema requirements were partially LLM-generated and SchemaBench's validation procedure is undocumented.
If the paper is right (Pith's inferences, not the authors')
Schema design from natural language should not be trusted without manual validation; current LLMs miss most referential constraints even with prompting.
For schema documentation or interchange, a detailed prompting strategy that explicitly requests tables, columns, types, keys, and foreign keys can yield descriptions from which the original schema is largely recoverable.
Text-similarity metrics (BLEU, ROUGE-L, BERTScore) are inadequate for evaluating schema descriptions; structural reconstruction metrics should replace them in any serious evaluation.
Data types and nullability are the most fragile schema dimension through verbalization, with only 7.8% retention from direct to round-trip recall, suggesting that domain information needs special handling.
The describer model and the constructor model should be selected independently; a model that describes well is not necessarily a good reconstructor.
The paper's results imply that a practical schema-documentation pipeline could use an LLM describer with a detailed prompt followed by automated validation of types and nullability, rather than trying to improve Text2Schema directly.
The finding that few-shot prompting improves Text2Schema over direct prompting (Table VI) while one-shot CoT hurts it suggests that the models rely on surface pattern matching from examples rather than genuine reasoning about relational design.
The poor retention of domain information (7.8%) combined with the strong recovery of keys and foreign keys when structural cues are present suggests that LLMs treat data types as arbitrary labels rather than semantically meaningful constraints.
If the RSchema requirements are partially LLM-generated (as the paper notes is unverified), then the "human-written requirements under-specify schemata" conclusion may be an artifact of the dataset rather than a property of human requirements.
Check this review
Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.
How often reviews like this one are right
Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.
How often objections from reviews like this one are right: not yet measured
Reviews by people
This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.
The paper
Abstract
Large Language Models (LLMs) are increasingly used for database tasks, yet most work, such as Text2SQL, assumes that the relational schema already exists. We ask whether LLMs can design a schema from natural language requirements (Text2Schema), verbalize an existing schema (Schema2Text), and preserve its structure through a Schema-to-Text-to-Schema round trip. We present SchemaBridge, a benchmark of 902 schemata from three collections, stratified by size and constraint complexity, that scores fidelity separately for tables, attributes, domain (data types and nullability), entity, and referential integrity. Evaluating six open-weight and proprietary LLMs, we find that: (i) human-written requirements under-specify schemata, with no model exceeding 0.27 referential integrity F1; (ii) LLM-generated descriptions carry far more structure when explicitly asked to be complete, raising GPT-5.4-mini's referential F1 on SchemaBench from 0.228 to 0.909, even as BLEU, ROUGE-L, and BERTScore decrease; (iii) controlled experiments show that both constructor and describer choices influence round-trip fidelity under fixed settings; and (iv) masked schema experiments show that structural cues support recovery of keys and relationships, while joint data-type and nullability information is poorly retained through verbalization. Code and data are available at https://github.com/iamsriom/SchemaBridge
The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.
abstract compiled · 2026-11-13
The authors' main claim, as the classifier picked it out 1.00
“Evaluating six open-weight and proprietary LLMs, we find that: (i) human-written requirements under-specify schemata, with no model exceeding 0.27 referential integrity F1; (ii) LLM-generated descriptions carry far more structure when explicitly asked to be complete, raising GPT-5.4-mini's referential F1 on SchemaBench from 0.228 to 0.909, even as BLEU, ROUGE-L, and BERTScore decrease; (iii) controlled experiments show that both constructor and describer choices influence round-trip fidelity under fixed settings; and (iv) masked schema experiments show that structural cues support recovery of keys and relationships, while joint data-type and nullability information is poorly retained through verbalization.”
How the main claim is stated: asserted 1.00
What the abstract itself states, as probabilities: claims first 0.08 · states limitation 0.85 · human participants 0.11 · controlled comparison 0.54 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.57 · mentions code or data availability 0.99
The abstract, sentence by sentence
This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| Large Language Models (LLMs) are increasingly used for database tasks, yet most work, such as Text2SQL, assumes that the relational schema already exists. | background 0.83 | 0.06 | 0.02 | asserted 1.00 |
| We ask whether LLMs can design a schema from natural language requirements (Text2Schema), verbalize an existing schema (Schema2Text), and preserve its structure through a Schema-to-Text-to-Schema round trip. | contribution 0.75 | 0.29 | 0.03 | unclear 0.55 |
| We present SchemaBridge, a benchmark of 902 schemata from three collections, stratified by size and constraint complexity, that scores fidelity separately for tables, attributes, domain (data types and nullability), entity, and referential integrity. | method 0.57 | 0.95 | 0.04 | asserted 0.99 |
| Evaluating six open-weight and proprietary LLMs, we find that: (i) human-written requirements under-specify schemata, with no model exceeding 0.27 referential integrity F1; (ii) LLM-generated descriptions carry far more structure when explicitly asked to be complete, raising GPT-5.4-mini's referential F1 on SchemaBench from 0.228 to 0.909, even as BLEU, ROUGE-L, and BERTScore decrease; (iii) controlled experiments show that both constructor and describer choices influence round-trip fidelity under fixed settings; and (iv) masked schema experiments show that structural cues support recovery of keys and relationships, while joint data-type and nullability information is poorly retained through verbalization. | result 1.00 | 0.98 | 0.83 | asserted 1.00 |
| Code and data are available at https://github.com/iamsriom/SchemaBridge | contribution 0.85 | 0.30 | 0.02 | asserted 0.83 |
What kind of paper the classifier reports this is: dataset or benchmark 0.99 · evidence from observation or experiment 1.00
What was examined, and what was not
Sources read
- arXiv listing abstract v1
Not examined
- full text
- figures and tables
- references and citing sentences
- relations to other papers
Levels run
- P abstract
Not run
- S sections
- T body sentences
- C citations
- R cross-paper relations
How the labels were made
Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-13: 1 request, 4,592 input tokens.
Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON
Figures (6)
Showing 5 of the paper's 6 figures. Figures are the authors', reproduced from the paper.
References (36)
- [1] D. Gao, H. Wang, Y . Li, X. Sun, Y . Qian, B. Ding, and J. Zhou, “Text-to- SQL empowered by large language models: A benchmark evaluation,” Proceedings of the VLDB Endowment, vol. 17, no. 5, pp. 1132–1145, 2024 on Pith
- [2] M. Pourreza, H. Li, R. Sun, Y . Chung, S. Talaei, G. T. Kakkar, Y . Gan, A. Saberi, F. Ozcan, and S. ¨O. Arik, “CHASE-SQL: multi-path reasoning and preference optimized candidate selection in text-to-sql,” inThe Thirteenth International Conference on Learning Representations, 2025 on Pith
- [3] A. Koukouvinis, G. Katsogiannis-Meimarakis, and G. Koutrika, “Com- parison and analysis of value linking in text-to-sql systems: [experiments & analysis],”Proc. ACM Manag. Data, vol. 4, no. 3, pp. 152:1–152:26, 2026 on Pith
- [4] V . Zhong, C. Xiong, and R. Socher, “Seq2sql: Generating structured queries from natural language using reinforcement learning,”arXiv preprint arXiv:1709.00103, 2017 on PithPith's reviewarXiv
- [5] T. Yu, R. Zhang, K. Yang, M. Yasunaga, D. Wang, Z. Li, J. Ma, I. Li, Q. Yao, S. Roman, Z. Zhang, and D. R. Radev, “Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task,” inConference on Empirical Methods in Natural Lang... on Pith
- [6] J. Li, B. Hui, G. Qu, J. Yang, B. Li, B. Li, B. Wang, B. Qin, R. Geng, N. Huoet al., “Can LLM already serve as a database interface? a big bench for large-scale database grounded text-to-SQLs,”Advances in Neural Information Processing Systems, vol. 36, pp. 42 330–42 357, 2023 on Pith
- [7] K. Xu, L. Wu, Z. Wang, Y . Feng, and V . Sheinin, “SQL-to-text generation with graph-to-sequence model,” inConference on Empirical Methods in Natural Language Processing, 2018, pp. 931–936 on Pith
- [8] V . Cˆamara, R. Mendonca-Neto, A. Silva, and L. Cordovil, “A large lan- guage model approach to SQL-to-text generation,” inIEEE International Conference on Consumer Electronics, 2024, pp. 1–4 on Pith
- [9] A. Al-Lawati, J. Lucas, and P. Mitra, “Semantic captioning: Benchmark dataset and graph-aware few-shot in-context learning for SQL2Text,” inInternational Conference on Computational Linguistics, 2025, pp. 8026–8042 on Pith
- [10] S. Chakrabarti, C. Ma, A. Khan, and S. Link, “SQL-to-text generation with weighted-AST few-shot prompting,” inDatabases Theory and Applications: 36th Australasian Database Conference (ADC 2025), ser. Lecture Notes in Computer Science, vol. 16391. Springer, 2026, pp. 365–379 on Pith
- [11] Q. Wang, Y . Li, Y . Feng, S. Chen, Z. Li, P. Zhang, Z. Shi, Y . Dou, Z. Huang, Z. Siet al., “SchemaAgent: A multi-agent framework for generating relational database schemas,”arXiv e-prints, pp. arXiv–2503, 2025 on Pith
- [12] E. F. Codd, “A relational model of data for large shared data banks,” Communications of the ACM, vol. 13, no. 6, pp. 377–387, 1970 on Pith
- [13] P. P.-S. Chen, “The entity-relationship model—toward a unified view of data,”ACM Transactions on Database Systems, vol. 1, no. 1, pp. 9–36, 1976 on Pith
- [14] P. A. Bernstein, “Synthesizing third normal form relations from func- tional dependencies,”ACM Transactions on Database Systems (TODS), vol. 1, no. 4, pp. 277–298, 1976 on Pith
- [15] T. Papenbrock, J. Ehrlich, J. Marten, T. Neubert, J.-P. Rudolph, M. Sch ¨onberg, J. Zwiener, and F. Naumann, “Functional dependency discovery: An experimental evaluation of seven algorithms,”Proceed- ings of the VLDB Endowment, vol. 8, no. 10, pp. 1082–1093, 2015 on Pith
- [16] T. Papenbrock and F. Naumann, “Data-driven schema normalization,” inInternational Conference on Extending Database Technology, 2017, pp. 342–353 on Pith
- [17] D. K. Deeptimahanti and R. Sanyal, “Semi-automatic generation of UML models from natural language requirements,” inIndia Software Engineering Conference, 2011, pp. 165–174 on Pith
- [18] G. Lucassen, M. Robeer, F. Dalpiaz, J. M. E. Van Der Werf, and S. Brinkkemper, “Extracting conceptual models from user stories with visual narrator,”Requirements Engineering, vol. 22, no. 3, pp. 339–358, 2017 on Pith
- [19] M. Pourreza and D. Rafiei, “DIN-SQL: Decomposed in-context learning of text-to-SQL with self-correction,” inAdvances in Neural Information Processing Systems, vol. 36, 2023, pp. 36 339–36 348 on Pith
- [20] A. Avignone, A. Tierno, A. Fiori, and S. Chiusano, “Exploring large language models’ ability to describe entity-relationship schema-based conceptual data models,”Information, vol. 16, no. 5, p. 368, 2025 on Pith
show 16 more
- [21] S. Chafik, “SchemaBench,” 2026. [Online]. Available: https://doi.org/ 10.5281/zenodo.20151089 on Pithdoi:10.5281/zenodo.20151089
- [22] H. Kalumin and A. Deshpande, “When the application layer is dispos- able: Putting integrity constraints back in the database,”arXiv preprint arXiv:2610.36418, 2026 on PithPith's reviewarXiv
- [23] C. Cleverdon, “The cranfield tests on index language devices,” inAslib proceedings, vol. 19, no. 6, 1967, pp. 173–194 on Pith
- [24] C. v. Rijsbergen,Information retrieval. Butterworth-heinemann, 1979 on Pith
- [25] K. Riesen and H. Bunke, “Approximate graph edit distance computation by means of bipartite graph matching,”Image and Vision Computing, vol. 27, no. 7, pp. 950–959, 2009 on Pith
- [26] K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu, “Bleu: a method for automatic evaluation of machine translation,” inAnnual Meeting of the Association for Computational Linguistics, 2002, pp. 311–318 on Pith
- [27] C.-Y . Lin, “ROUGE: A package for automatic evaluation of summaries,” inText Summarization Branches Out. Association for Computational Linguistics, 2004, pp. 74–81 on Pith
- [28] T. Zhang, V . Kishore, F. Wu, K. Q. Weinberger, and Y . Artzi, “BERTScore: Evaluating text generation with BERT,” inInternational Conference on Learning Representations, 2020 on Pith
- [29] J. Motl and O. Schulte, “The ctu prague relational learning repository,” on Pith
- [30] B. Roziere, J. Gehring, F. Gloeckle, S. Sootla, I. Gat, X. E. Tan, Y . Adi, J. Liu, R. Sauvestre, T. Remezet al., “Code Llama: Open foundation models for code,”arXiv preprint arXiv:2308.12950, 2023 on PithPith's reviewarXiv
- [31] D. Guo, Q. Zhu, D. Yang, Z. Xie, K. Dong, W. Zhang, G. Chen, X. Bi, Y . Wu, Y . K. Li, F. Luo, Y . Xiong, and W. Liang, “DeepSeek-Coder: When the large language model meets programming—the rise of code intelligence,”arXiv preprint arXiv:2401.14196, 2024 on PithPith's reviewarXiv
- [32] A. Grattafiori, A. Dubey, A. Jauhri, A. Pandey, A. Kadian, A. Al-Dahle et al., “The Llama 3 herd of models,”arXiv preprint arXiv:2407.21783, 2024 on PithPith's reviewarXiv
- [33] Anthropic, “Introducing claude sonnet 4.6,” Anthropic, Feb. 2026. [Online]. Available: https://www.anthropic.com/news/claude-sonnet-4-6 on Pith
- [34] OpenAI , “Introducing GPT-5.4 mini and nano,” Ope- nAI, Mar. 2026. [Online]. Available: https://openai.com/index/ introducing-gpt-5-4-mini-and-nano/ on Pith
- [35] OpenAI, “GPT-4o mini: Advancing cost-efficient intelligence,” OpenAI, Jul. 2024. [Online]. Available: https://openai.com/index/ gpt-4o-mini-advancing-cost-efficient-intelligence/ 13 on Pith
- [2015] [Online]. Available: https://arxiv.org/abs/1511.03086 on PithPith's reviewarXiv
Challenges and discussion
Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.
No comments yet.
Sign in to comment