{"id":"fd2fda65-53dc-4026-8f64-66266e158a9d","arxiv_id":"1907.11112","paper_version":1,"verdict":"UNVERDICTED","confidence":"LOW","novelty_score":6.0,"correctness_risk":"unknown","formal_verification":"none","parameter_count":0,"one_line_summary":"Graph-based encoding of Winograd schemas solved via Answer Set Programming with added commonsense constraints achieves 240/291 accuracy.","lead":"The paper represents Winograd Schema Challenge problems as graphs and uses Answer Set Programming to perform subgraph isomorphism checks augmented with extra commonsense knowledge, correctly handling 240 of 291 instances. A generalist reader might examine it to understand how declarative logic programming can inject background knowledge into pronoun resolution tasks.","discovery_kind":"new_application","skeptic_critique":{"model":"grok-4.3","headline":"Success rate depends on manually supplied commonsense knowledge being accurate, sufficient, and non-spurious per schema","rationale":"The reader's weakest_assumption directly names the load-bearing dependency. Because the full text is now referenced but the knowledge details remain the unverified element, the UNVERDICTED verdict is unchanged; the concern is internal to the argument rather than external consensus.","tokens_in":1611,"tokens_out":332,"duration_ms":19228,"concrete_test":"From the full paper, extract the knowledge-base construction procedure and the ASP facts/rules used for a random sample of 20 solved schemas (from the experimental section or appendix). For each, determine whether the facts are derivable from an external resource such as ConceptNet or WordNet without reference to the schema's correct answer; if >30% appear tailored to the gold referent, the 240/291 figure does not support a general method.","verdict_should_be":"UNCHANGED","load_bearing_attack":"The central claim is that graph-subgraph isomorphism encoded in ASP, augmented with additional constraints, solves 240/291 WSC instances. This requires that the supplied knowledge (1) distinguishes the correct referent via the isomorphism check and (2) does not introduce extraneous solutions or rely on instance-specific facts reverse-engineered from the gold answers. The abstract states the knowledge is added in an elaboration-tolerant manner, but provides no description of its source, generality, or construction procedure. If the knowledge base is a collection of per-schema facts rather than a fixed, reusable commonsense theory, the result demonstrates knowledge engineering rather than automated reasoning.","agreement_with_reader":"agree"},"referee_report":{"model":"grok-4.3","summary":"The paper proposes solving Winograd Schema Challenge (WSC) instances via Answer Set Programming (ASP) encodings of graph-subgraph isomorphism augmented with additional commonsense knowledge constraints. It reports a success rate of 240 out of 291 problems and introduces a graph-based representation of the schemas and knowledge, highlighting the elaboration-tolerant addition of constraints in ASP.","tokens_in":1715,"tokens_out":283,"duration_ms":13541,"significance":"If the approach can be shown to rely on a reusable, general commonsense theory rather than per-instance encodings, the result would illustrate a concrete application of ASP to commonsense reasoning in NLU. The reported count is an empirical demonstration on hand-crafted encodings; its significance hinges on whether the supplied knowledge is accurate, sufficient, and non-spurious without reverse-engineering from gold answers.","major_comments":[{"comment":"Abstract: The claim that the method handles 240/291 WSC problems supplies no error analysis, no description of the source or construction procedure for the commonsense knowledge base, and no verification that the ASP models select the intended referent rather than any consistent model. This is load-bearing for the central claim because the success rate depends on the additional knowledge distinguishing the correct referent without introducing extraneous solutions.","section":"Abstract"}],"minor_comments":[],"recommendation":"major_revision","confidential_remarks":null},"author_rebuttal":{"model":"grok-4.3","summary":"We thank the referee for their detailed feedback. We address the concerns about the abstract's claims and supporting evidence below, and we will revise the manuscript accordingly to strengthen the presentation of our results.","responses":[{"response":"We agree that the abstract is brief and omits these supporting details, which are important for evaluating the central empirical claim. The full manuscript presents the graph-based representation of WSC instances and the ASP encoding of graph-subgraph isomorphism, along with the elaboration-tolerant addition of commonsense constraints. However, we will revise to include: (1) an error analysis section categorizing solved and unsolved instances; (2) a description of the commonsense knowledge base, including its source in general commonsense principles (drawn from broad axioms rather than instance-specific reverse-engineering from gold labels) and the construction procedure; and (3) verification that the ASP stable models select the intended referent, by showing that the added constraints eliminate the incorrect candidate without permitting extraneous consistent models. These additions will be made in a revised version of the paper.","revision_made":"partial","referee_comment":"[Abstract] Abstract: The claim that the method handles 240/291 WSC problems supplies no error analysis, no description of the source or construction procedure for the commonsense knowledge base, and no verification that the ASP models select the intended referent rather than any consistent model. This is load-bearing for the central claim because the success rate depends on the additional knowledge distinguishing the correct referent without introducing extraneous solutions."}],"tokens_in":1159,"tokens_out":327,"duration_ms":17245,"standing_objections":[]},"desk_editor":{"model":"grok-4.3","letter":"The core contribution is a graph representation of Winograd schemas together with an ASP program that reduces pronoun resolution to subgraph isomorphism plus extra constraints. They report handling 240 out of 291 cases this way and note that ASP supports elaboration-tolerant addition of rules. That encoding is the concrete piece that is new relative to the cited prior work on the benchmark. The declarative style is a strength; it makes the added knowledge explicit and lets the solver handle consistency checking in a standard way. The result shows that a symbolic pipeline can clear a large fraction of the test set once the right facts are present. The stress-test concern about per-schema knowledge engineering is reasonable on the evidence given. The abstract supplies the success count but no description of how the commonsense facts were gathered, whether they form a reusable theory or a collection of instance-specific assertions, and no breakdown of the 51 failures or confirmation that the chosen models match the gold answers for the intended reasons rather than some other consistent assignment. If the knowledge base turns out to be largely hand-crafted per schema, the work demonstrates knowledge engineering more than general automated reasoning. A referee could reasonably ask for the KB construction procedure and some per-instance analysis. This is useful reading for anyone interested in applying answer-set programming or graph-based methods to NLU benchmarks. It deserves peer review because the encoding is reproducible in principle and the empirical target is clear; the missing details on knowledge acquisition are fixable and worth requesting rather than grounds for desk rejection.","headline":"The paper encodes WSC items as graphs and solves 240/291 via ASP subgraph isomorphism, but the commonsense knowledge source and construction remain unclear.","tokens_in":2196,"tokens_out":369,"would_cite":false,"duration_ms":40142,"reading_group":"maybe","serious_thinker":"yes","would_accept_peer_review":true},"rs_alignment":{"model":"grok-4.3","evidence":[{"relation":"unclear","rs_module":"IndisputableMonolith/Foundation/AbsoluteFloorClosure.lean","rs_theorem":"absolute_floor_iff_bare_distinguishability","paper_passage":"By using an approach built on top of graph-subgraph isomorphism encoded using Answer Set Programming (ASP) we were able to handle 240 out of 291 WSC problems."},{"relation":"unclear","rs_module":"IndisputableMonolith/Cost/FunctionalEquation.lean","rs_theorem":"washburn_uniqueness_aczel","paper_passage":"The ASP encoding allows us to add additional constraints in an elaboration tolerant manner."}],"headline":"ASP graph-isomorphism for WSC pronoun resolution shares no primitives with RS distinction-to-physics forcing chain","alignment":"orthogonal","rationale":"Paper encodes WSC sentences/knowledge as labeled DAGs, detects isomorphisms via ASP constraints (rules s31–s37), and resolves via 'is same as' edges (Def. 7–8, WiSCR algorithm). This is classical logic-programming search over manually supplied per-schema facts. RS derives J(x)=½(x+x⁻¹)−1, φ, 8-tick period, D=3 and constants from bare distinguishability (reality_from_one_distinction, absolute_floor_iff_bare_distinguishability, AlexanderDuality.alexander_duality_circle_linking). No J-cost, ratio symmetry, periodicity or parameter-free constant derivation appears; domain is NLP/commonsense, not foundational physics.","tokens_in":55339,"confidence":"high","tokens_out":355,"duration_ms":7061,"cache_read_input_tokens":38528,"cache_creation_input_tokens":0},"lean_confirmation":null,"pith_extraction":{"msc":[],"pacs":[],"model":"grok-4.3","headline":"Answer Set Programming on graph representations solves 240 out of 291 Winograd Schema problems with added commonsense knowledge.","keywords":["Winograd Schema Challenge","Answer Set Programming","Commonsense Reasoning","Graph Isomorphism","Natural Language Understanding","Elaboration Tolerance","Pronoun Resolution"],"falsifier":"Running the ASP program on the 51 unsolved problems and checking whether it returns the correct referent, no stable model, or an incorrect referent for each.","tokens_in":2478,"feed_emoji":"🧩","tokens_out":598,"duration_ms":18895,"temperature":0.7,"pith_summary":"The paper sets out to show that Winograd Schema Challenge problems, which test pronoun reference through commonsense, can be solved by turning each schema into a graph and using Answer Set Programming to match it against a separate commonsense graph. The ASP encoding supports adding new facts and rules without rewriting the base program. A reader would care because the method makes the required knowledge explicit and testable rather than hidden inside statistical patterns. The reported coverage of 240 problems indicates that the combination of representation and solver reaches most cases in the standard collection.","feed_headline":"ASP resolves 240 of 291 Winograd schemas with commonsense","feed_subtitle":"Graph encodings let added rules distinguish referents in pronoun puzzles without altering the core solver.","key_machinery":"Graph-subgraph isomorphism encoded in Answer Set Programming on representations of the schema and commonsense facts.","core_discovery":"The paper claims that a graph based representation of WSC problems combined with an Answer Set Programming encoding of graph-subgraph isomorphism, supplied with relevant commonsense knowledge, correctly resolves 240 out of 291 schemas. This encoding permits additional constraints to be added in an elaboration tolerant manner.","pith_inferences":["The method could serve as a verification layer that checks or explains decisions made by statistical pronoun-resolution models.","Systematically extending the commonsense graph until all 291 problems are covered would test whether knowledge coverage is the main remaining bottleneck.","Similar graph encodings might transfer to coreference resolution in longer documents where multiple referents must be tracked."],"forward_implications":["New commonsense rules can be added to the program without changes to the core encoding or solver.","The stable models produced by ASP make the reasoning steps that select one referent over another explicit and inspectable.","Unsolved cases indicate gaps in the supplied knowledge base rather than limits of the matching procedure itself.","The same graph-plus-ASP structure can be reused for other language tasks that require matching a partial description to world knowledge."],"fun_headline_variants":["ASP resolves 240 schemas with graph commonsense","240 Winograd schemas resolved via ASP graphs","ASP uses graphs to solve 240 Winograd schemas","Commonsense graphs in ASP resolve 240 schemas","Graph ASP solves 240 of 291 Winograd schemas"],"cache_read_input_tokens":2112,"weakest_assumption_plain":"The additional commonsense knowledge supplied to the ASP program is accurate and sufficient to select the correct referent without allowing incorrect solutions.","fun_headline_variants_meta":{"raw":{"variants":["ASP resolves 240 schemas with graph commonsense","240 Winograd schemas resolved via ASP graphs","ASP uses graphs to solve 240 Winograd schemas","Commonsense graphs in ASP resolve 240 schemas","Graph ASP solves 240 of 291 Winograd schemas"]},"model":"grok-4.3","cost_usd":0.00794,"raw_usage":{"total_tokens":3548,"prompt_tokens":529,"num_sources_used":0,"completion_tokens":63,"cost_in_usd_ticks":79399500,"prompt_tokens_details":{"text_tokens":529,"audio_tokens":0,"image_tokens":0,"cached_tokens":256},"completion_tokens_details":{"audio_tokens":0,"reasoning_tokens":2956,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"tokens_in":529,"tokens_out":63,"duration_ms":20441,"temperature":1.0,"reasoning_tokens":2956,"cache_read_input_tokens":256,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-05-24T16:11:18.021593+00:00","model_set":{"reader":"grok-4.3"},"falsifier":"Running the ASP program on the 51 unsolved problems and checking whether it returns the correct referent, no stable model, or an incorrect referent for each.","supporting_citations":[],"review_version":1}