Papers › Differentiable Inductive Logic Programming for Structured Examples

Differentiable Inductive Logic Programming for Structured Examples

2 Mar 2021arXiv:2103.01719archive 2025-07-28

Hikaru Shindo, Masaaki Nishino, Akihiro Yamamoto

The differentiable implementation of logic yields a seamless combination of symbolic reasoning and deep neural networks. Recent research, which has developed a differentiable framework to learn logic programs from examples, can even acquire reasonable solutions from noisy datasets. However, this framework severely limits expressions for solutions, e.g., no function symbols are allowed, and the shapes of clauses are fixed. As a result, the framework cannot deal with structured examples. Therefore we propose a new framework to learn logic programs from noisy and structured examples, including the following contributions. First, we propose an adaptive clause search method by looking through structured space, which is defined by the generality of the clauses, to yield an efficient search space for differentiable solvers. Second, we propose for ground atoms an enumeration algorithm, which determines a necessary and sufficient set of ground atoms to perform differentiable inference functions. Finally, we propose a new method to compose logic programs softly, enabling the system to deal with complex programs consisting of several clauses. Our experiments show that our new framework can learn logic programs from noisy and structured examples, such as sequences or trees. Our framework can be scaled to deal with complex programs that consist of several clauses with function symbols.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 23 code samples harvested from 1 repository linked to this paper: 9 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 23 samples from 1 repository, 9 ran (7 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hkrsnd/dilp-st officialmentioned in paperSyntology: 23 samples, 9 ran (2 instrument-failed) · 14 unverified 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

23 samples harvested: 9 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 14 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
5ran
14unverified

Licence: 0 of the 23 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 hkrsnd/dilp-st. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

hkrsnd/dilp-st official repository 23 samples, 9 ran (2 instrument-failed) · 14 unverified
Atom src/clause_generator.py ran · metamorphic tier: deterministic MIT (permissive) · acd256902db3d7da · report fixture: returned Atom · level recorded 2026-09-22
Const src/clause_generator.py ran · metamorphic tier: deterministic MIT (permissive) · 79758a0df2fbb970 · report fixture: returned Const · level recorded 2026-09-22
Predicate src/clause_generator.py ran MIT (permissive) · 8e94a3fefda05ceb · report fixture: returned Predicate · level recorded 2026-09-22
Term src/clause_generator.py ran MIT (permissive) · 00a5b4ee11ed489c · report fixture: returned Term · level recorded 2026-09-22
Var src/clause_generator.py ran fingerprinted MIT (permissive) · db81a46d2b6706f8 · report fixture: signature level:int/0/int · returned str · level recorded 2026-09-24
flatten in 178 papers
census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
src/clause_generator.py ran · our draft was wrong fingerprinted MIT (permissive) · 1a922e4a8a94dba9 · report fixture: signature x:list/1/int · returned list · level recorded 2026-09-22
get_disagree_index src/clause_generator.py ran · honoured contract MIT (permissive) · 88d01be925b6598e · report fixture: signature terms:list/1/Term · returned tuple · level recorded 2026-09-22
get_disagreements src/clause_generator.py ran · our draft was wrong MIT (permissive) · 1307503a0ca46e08 · report fixture: signature terms:list/1/Term · returned tuple · level recorded 2026-09-22
is_singleton src/clause_generator.py ran · violated contract fingerprinted MIT (permissive) · 74560ac0380fb5b5 · report fixture: signature atoms:list/1/Atom · returned bool · level recorded 2026-09-22
Clause src/clause_generator.py unverified MIT (permissive) · 3613026564e05b5e · report
ClauseGenerator src/clause_generator.py unverified MIT (permissive) · 190a226af393125b · report
FuncTerm src/clause_generator.py unverified MIT (permissive) · d817dcd7835646fc · report
InferModule src/clause_generator.py unverified MIT (permissive) · ab2f061a519c64f0 · report
RefinementGenerator src/clause_generator.py unverified MIT (permissive) · fda81194aa3906d6 · report
convert in 76 papers src/clause_generator.py unverified MIT (permissive) · ece9dfa2bd12d452 · report
find_subs_term src/clause_generator.py unverified MIT (permissive) · e28c5695ccf75788 · report
is_entailed src/clause_generator.py unverified MIT (permissive) · dc2069a3e3e2350f · report
occur_check src/clause_generator.py unverified MIT (permissive) · 8434df103dd0829e · report
subs src/clause_generator.py unverified MIT (permissive) · 13939b1b9513f421 · report
subs_list src/clause_generator.py unverified MIT (permissive) · 8d19b6fe8156a952 · report
t_p src/clause_generator.py unverified MIT (permissive) · a48cee9bec30434c · report
t_p_n src/clause_generator.py unverified MIT (permissive) · 552c5aa6d7f3973d · report
unify src/clause_generator.py unverified MIT (permissive) · 221082e2e2fad2e6 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for adaptive clause search method (graph method: adaptive clause search method). 23 bricks; individually on a fixture: 9 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 14 unverified. The assembly has not been run end-to-end.

  1. ClauseGenerator entry · level 0 · unverified · 190a226af393125b
  2. InferModule helper · level 0 · unverified · ab2f061a519c64f0
  3. RefinementGenerator helper · level 0 · unverified · fda81194aa3906d6
  4. convert helper · level 0 · unverified · ece9dfa2bd12d452
  5. is_entailed helper · level 0 · unverified · dc2069a3e3e2350f
  6. Atom helper · level 1 · ran · acd256902db3d7da
  7. Clause helper · level 0 · unverified · 3613026564e05b5e
  8. FuncTerm helper · level 0 · unverified · d817dcd7835646fc
  9. subs helper · level 0 · unverified · 13939b1b9513f421
  10. t_p_n helper · level 0 · unverified · 552c5aa6d7f3973d
  11. unify helper · level 0 · unverified · 221082e2e2fad2e6
  12. Var helper · level 1 · ran · db81a46d2b6706f8
  13. flatten helper · level 1 · ran · our draft was wrong · 1a922e4a8a94dba9
  14. Term helper · level 1 · ran · 00a5b4ee11ed489c
  15. Const helper · level 1 · ran · 79758a0df2fbb970
  16. t_p helper · level 0 · unverified · a48cee9bec30434c
  17. find_subs_term helper · level 0 · unverified · e28c5695ccf75788
  18. get_disagreements helper · level 1 · ran · our draft was wrong · 1307503a0ca46e08
  19. is_singleton helper · level 1 · ran · violated contract · 74560ac0380fb5b5
  20. subs_list helper · level 0 · unverified · 8d19b6fe8156a952
  21. occur_check helper · level 0 · unverified · 8434df103dd0829e
  22. get_disagree_index helper · level 1 · ran · honoured contract · 88d01be925b6598e
  23. Predicate helper · level 1 · ran · 8e94a3fefda05ceb

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2103.01719") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Inductive logic programming

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