Papers › Holophrasm: a neural Automated Theorem Prover for higher-order logic

Holophrasm: a neural Automated Theorem Prover for higher-order logic

8 Aug 2016arXiv:1608.02644archive 2025-07-28

Daniel Whalen

I propose a system for Automated Theorem Proving in higher order logic using deep learning and eschewing hand-constructed features. Holophrasm exploits the formalism of the Metamath language and explores partial proof trees using a neural-network-augmented bandit algorithm and a sequence-to-sequence model for action enumeration. The system proves 14% of its test theorems from Metamath's set.mm module.

PaperPDFCodeCode 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="1608.02644")

Code

Syntology Ran 0 of 14 code samples harvested from 1 repository linked to this paper; 14 have no recorded run.

By repository: official repository: 14 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

dwhalen/holophrasm officialmentioned on GitHubMIT report
giomasce/mmpp mentioned on GitHub report
jinpz/refactor mentioned on GitHubpytorch report
justin941208/SPIA-Project mentioned on GitHub 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

14 samples harvested; 0 ran; 0 honoured the contract we drafted; 14 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.

14unverified

Licence: 0 of the 14 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 dwhalen/holophrasm. “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.

dictionary_merge dwhalen/holophrasm/data_utils5.py official repository unverified MIT (permissive) · 7d0b96fa6f5331d0 · report
get_wrong dwhalen/holophrasm/build_payout_data_set.py official repository unverified MIT (permissive) · 83f3b97d976fb076 · report
list_to_data dwhalen/holophrasm/payout_model_5_train.py official repository unverified MIT (permissive) · e4f3ecb14bd415e0 · report
merge_graph_structures dwhalen/holophrasm/models.py official repository unverified MIT (permissive) · 53bedbded781bd89 · report
prop_applies_to_statement dwhalen/holophrasm/data_utils5.py official repository unverified MIT (permissive) · ad8fc7eac91efe6f · report
slow_delete_duplicates dwhalen/holophrasm/build_payout_data_set.py official repository unverified MIT (permissive) · 7f6b640ff2600f3b · report
test_data_set dwhalen/holophrasm/gen_model_train.py official repository unverified MIT (permissive) · 3ec00b3b7aa08090 · report
test_data_set dwhalen/holophrasm/payout_model_5_train.py official repository unverified MIT (permissive) · 6518d7d784e7aaa9 · report
test_data_set dwhalen/holophrasm/pred_model.py official repository unverified MIT (permissive) · 9ee1ed4c5a709c17 · report
training_data_set dwhalen/holophrasm/gen_model_train.py official repository unverified MIT (permissive) · 3781549407b86440 · report
training_data_set dwhalen/holophrasm/pred_model.py official repository unverified MIT (permissive) · 9f0d681dfe32d4c8 · report
validation_data_set dwhalen/holophrasm/gen_model_train.py official repository unverified MIT (permissive) · 7f3e5f63ef491e6d · report
validation_data_set dwhalen/holophrasm/payout_model_5_train.py official repository unverified MIT (permissive) · bdf57915ccc9a068 · report
validation_data_set dwhalen/holophrasm/pred_model.py official repository unverified MIT (permissive) · d68d4b10e52cc4fd · report

Tasks

Automated Theorem Proving

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Automated Theorem Proving Metamath set.mm Holophrasm Percentage correct 14.3 #3 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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