Papers › PRover: Proof Generation for Interpretable Reasoning over Rules

PRover: Proof Generation for Interpretable Reasoning over Rules

6 Oct 2020EMNLP 2020 11arXiv:2010.02830archive 2025-07-28

Swarnadeep Saha, Sayan Ghosh, Shashank Srivastava, Mohit Bansal

Recent work by Clark et al. (2020) shows that transformers can act as 'soft theorem provers' by answering questions over explicitly provided knowledge in natural language. In our work, we take a step closer to emulating formal theorem provers, by proposing PROVER, an interpretable transformer-based model that jointly answers binary questions over rule-bases and generates the corresponding proofs. Our model learns to predict nodes and edges corresponding to proof graphs in an efficient constrained training paradigm. During inference, a valid proof, satisfying a set of global constraints is generated. We conduct experiments on synthetic, hand-authored, and human-paraphrased rule-bases to show promising results for QA and proof generation, with strong generalization performance. First, PROVER generates proofs with an accuracy of 87%, while retaining or improving performance on the QA task, compared to RuleTakers (up to 6% improvement on zero-shot evaluation). Second, when trained on questions requiring lower depths of reasoning, it generalizes significantly better to higher depths (up to 15% improvement). Third, PROVER obtains near perfect QA accuracy of 98% using only 40% of the training data. However, generating proofs for questions requiring higher depths of reasoning becomes challenging, and the accuracy drops to 65% for 'depth 5', indicating significant scope for future work. Our code and models are publicly available at https://github.com/swarnaHub/PRover

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2010.02830")

Code

Syntology Ran 2 of 12 code samples harvested from 1 repository linked to this paper; 10 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

swarnaHub/PRover officialmentioned in papermentioned on GitHubpytorchMIT report
swarnaHub/multiPRover mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 2 ran; 0 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran
10unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from swarnaHub/PRover. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

get_proof_graph swarnaHub/PRover/proof_utils.py official repository ran fingerprinted MIT (permissive) · c13d0749a5472646 · report
get_proof_graph_with_fail swarnaHub/PRover/proof_utils.py official repository ran MIT (permissive) · 5621c0d34ff2bff6 · report
compute_metrics swarnaHub/PRover/utils.py official repository unverified MIT (permissive) · edca3480666257aa · report
convert_examples_to_features_RR swarnaHub/PRover/utils.py official repository unverified MIT (permissive) · ecb790feacadaaad · report
convert_examples_to_features_RR swarnaHub/PRover/utils_natlang.py official repository unverified MIT (permissive) · 3f327d827ee113e3 · report
filter_context swarnaHub/PRover/evaluation/eval_natlang.py official repository unverified MIT (permissive) · abf6d8b134f4edd6 · report
get_fact_rule_identifiers swarnaHub/PRover/ilp_infer/inference.py official repository unverified MIT (permissive) · 555f983801abb905 · report
get_index_component_maps swarnaHub/PRover/evaluation/print_graphs.py official repository unverified MIT (permissive) · 89fc1d14be606f95 · report
get_natlang_mappings swarnaHub/PRover/evaluation/eval_natlang.py official repository unverified MIT (permissive) · 5fe3351fd927fc60 · report
simple_accuracy swarnaHub/PRover/utils.py official repository unverified MIT (permissive) · 3c241ecfe3749a6d · report
solve_LP swarnaHub/PRover/ilp_infer/inference.py official repository unverified MIT (permissive) · fcbaf738dc6fc42a · report
solve_LP_unconstrained swarnaHub/PRover/ilp_infer/inference.py official repository unverified MIT (permissive) · f7b1e7bc7db74fa7 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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