{"id":"3907f6b7-a710-4cec-9a8d-289924495dbd","arxiv_id":"2507.11733","paper_version":1,"verdict":"UNVERDICTED","confidence":"HIGH","novelty_score":2.0,"correctness_risk":"unknown","formal_verification":"none","parameter_count":0,"one_line_summary":"ClarifAI is a conceptual architecture combining case-based reasoning and ontology-driven knowledge to generate explanations for AI decisions, presented without implementation or testing.","lead":"This paper introduces ClarifAI, a proposed framework that combines case-based reasoning with ontologies to explain AI decisions. It provides an architecture blueprint and pseudocode, but no implementation, experiments, or evaluation.","discovery_kind":"extension","skeptic_critique":{"model":"deepseek-v4-flash","headline":"Algorithmic gap: in Algorithm 3, ontology is used only after CBR retrieval, so it cannot 'enrich the decision' as claimed; the central synergy is unsupported and unevaluated.","rationale":"The reader's UNVERDICTED verdict is appropriate. My concern is narrower and more technical: the paper's stated synergy between CBR and ontology is not realized in its own Algorithm 3. Since domain_ontology is passed only to generate_explanation and not to case retrieval, the ontology contributes at best a textual gloss to the explanation rather than grounding or enriching the decision itself. This is an internal gap, not merely a missing evaluation. It could be repaired by making retrieval ontology-aware and by running a preregistered user study comparing comprehension and trust against a CBR-only baseline. Until that is done, the central claim is unsupported and underspecified. I do not see an ad hominem or off-consensus issue; this is a standard finding of an unevaluated, partially inconsistent conceptual proposal. The paper's own future-work section admits that experimental studies remain to be done, which corroborates the absence of evidence.","tokens_in":7524,"tokens_out":5389,"duration_ms":66522,"concrete_test":"Analytically trace Algorithm 3: constant-fold generate_explanation and compare the decision_details['solution'] produced by the remaining code to the full version. Because domain_ontology is only passed to generate_explanation, the solution must be identical, confirming that ontology has no influence on the decision. To refute this, the authors would need to supply a version in which retrieve_similar_case/compute_similarity takes domain_ontology and demonstrably changes retrieved cases; if it only changes the explanation text, the central integration claim fails.","verdict_should_be":"UNCHANGED","load_bearing_attack":"The central claim is that combining CBR with ontology improves interpretable and transparent decision-making. For this to hold, the ontology must participate in producing the decision (or the explanation must be shown to improve user comprehension), and the pipeline must be specified enough to test. Neither condition is met. In Section 3.1, Algorithm 3 (clarify_decision) receives domain_ontology but immediately calls retrieve_similar_case(new_case, case_database) without passing the ontology. Algorithm 1's compute_similarity also has no ontology argument, so ontology cannot affect case retrieval or adaptation. Ontology appears only in Algorithm 2, which appends definitions of case_solution['concepts_involved'] to an explanation string. The retrieved solution is returned unchanged. The prose says the ontology 'ensures that the solution is not only based on past cases but is also grounded in the conceptual structure of the domain,' but the algorithm only produces a post-hoc textual gloss. The claimed synergy is therefore not realized in the paper's own formal material. The framework is also unevaluated: no case database, ontology, similarity function, or user study is instantiated, and Section 5 defers experiments to future work. Without either an internally coherent integration or empirical evidence, the Section 4 claim that ClarifAI will 'significantly impact' decision-making is unfalsifiable as written.","agreement_with_reader":"partial"},"referee_report":{"model":"deepseek-v4-flash","summary":"The paper proposes ClarifAI, a framework that combines Case-Based Reasoning (CBR) with an ontology-driven approach to provide interpretable and transparent explanations for AI-assisted decision-making. It presents a conceptual architecture, three algorithms (retrieve similar case, generate explanation, clarify decision), and a discussion of potential impacts on trust, decision quality, compliance, and access. The paper includes no implementation, no dataset, no empirical evaluation, and no formal derivation; Section 5 explicitly defers experiments to future work.","tokens_in":7794,"tokens_out":3751,"duration_ms":45148,"significance":"If the claimed benefits were demonstrated, an integrated CBR-and-ontology explanation framework could be a useful contribution to explainable AI. The paper's literature review is competent and the direction is worth exploring. However, the manuscript provides no evidence that ClarifAI enhances interpretability or transparency. The algorithms are presented at a high level; the key functions are undefined; and, as shown by the formal material itself, the ontology does not actually participate in the decision-making process. The Section 4 impact claims are therefore unfalsifiable as written. The paper is best regarded as a position statement, but its framing and conclusion make claims far stronger than the content supports.","major_comments":[{"comment":"The claimed synergy between CBR and ontology is not realized in the formal algorithms. In Algorithm 3, clarify_decision receives domain_ontology but calls retrieve_similar_case(new_case, case_database) without passing the ontology; Algorithm 1's compute_similarity also has no ontology parameter. The ontology is used only in Algorithm 2, where it appends definitions of case_solution['concepts_involved'] to an explanation string. Thus the ontology cannot influence case retrieval, adaptation, or the returned solution; the decision is unchanged by the ontology, and the explanation is a post-hoc textual gloss. This directly contradicts the Section 3.1 text that the ontology 'ensures that the solution is not only based on past cases but is also grounded in the conceptual structure of the domain.'","section":"Section 3.1, Algorithm 3"},{"comment":"The core functions compute_similarity and get_concept_definition are never defined. Without a concrete similarity metric or ontology query behavior, the framework cannot be instantiated, tested, or compared against alternatives. The paper also does not specify the structure of cases, the representation of 'concepts_involved', or the contents of the case database and domain ontology. These omissions make the central claim about enhanced decision-making impossible to verify.","section":"Section 3.1, Algorithms 1 and 2"},{"comment":"The paper contains no empirical evaluation. Section 4 makes broad claims about enhancing trust, improving decision quality, facilitating compliance, and democratizing access, but no user study, case study, or quantitative experiment is reported. Section 5's Future Work explicitly states that 'Experimental studies involving humans interacting with robots... will be crucial,' which confirms that no such evidence currently exists. The conclusion's statement that 'ClarifAI represents a significant step forward' is therefore unsupported by the manuscript's content.","section":"Section 4 and Section 5"},{"comment":"There is an internal inconsistency between the described operational flow and the formal algorithms. The text describes an 'Ontology Mapping' step in which the ontology is 'consulted to enrich the decision-making process,' but Algorithm 3 does not include any such step: after retrieval, it immediately generates an explanation and returns the solution. Either the algorithm is incomplete or the prose overstates the role of the ontology; in either case, the claimed integration is not substantiated.","section":"Section 3.1, Operational Flow"}],"minor_comments":[{"comment":"The phrase 'an novel platform' should read 'a novel platform.'","section":"Section 1"},{"comment":"The name is spelled inconsistently: 'ClariAI' appears in the abstract, while 'ClarifAI' is used elsewhere. Please standardize.","section":"Abstract and throughout"},{"comment":"The line 'most_similar_case ← N one' is a typo for 'None.' Also, the return type and initial value should be consistent.","section":"Algorithm 1"},{"comment":"The text says 'The following diagram and flowchart illustrate the operational flow,' but only an architecture diagram is included; no flowchart is provided. Either include the flowchart or remove the reference.","section":"Section 3.1, Figure 1"},{"comment":"The notation is garbled: 'concept_def inition' and '′concepts_involved ′' contain stray spaces and prime characters. Additionally, 'concepts_involved' is never defined in the case representation, so the algorithm's input is underspecified.","section":"Algorithm 2"},{"comment":"Several references (e.g., [3], [4], [5], [12]) are cited with Semantic Scholar CorpusIDs rather than standard bibliographic information, which is not appropriate for a journal submission.","section":"References"}],"recommendation":"reject","confidential_remarks":"This is a high-level position paper with no experimental content. I considered major revision, but the central algorithmic gap—the ontology never participates in the decision-generation process—is not fixable by minor edits; it would require re-specifying the architecture and a full evaluation. The claims in Sections 4 and 5 exceed the evidence provided. I recommend rejection, though the authors could resubmit a clearly framed position paper or an implemented system with empirical results."},"author_rebuttal":null,"desk_editor":{"model":"deepseek-v4-flash","letter":"Quick take: this is a high-level essay about combining CBR with ontologies for explainability, not a research paper. It reads like a well-organized proposal, but there is no implementation, dataset, or experiment, and the one concrete algorithm contradicts the paper's central claim about synergy.\n\nWhat's good: the related work is mostly relevant, the writing is clear, and the motivation is legitimate. The paper correctly notes that CBR explanations are intuitive and that ontologies can add structured domain context. If it were positioned as a survey or position paper, the existing literature summary would be a reasonable starting point for a novice.\n\nThe soft spots are serious. The claimed integration is not actually present. In Algorithm 3, the ontology is passed in but never used for retrieval or adaptation; it only appears in Algorithm 2 to append one-line definitions of concepts mentioned in the retrieved case's solution. That is a post-hoc gloss, not a decision-making contribution. The prose in Section 3.1 claims the ontology 'ensures that the solution is grounded in the conceptual structure of the domain,' but the code shows otherwise. So the core mechanism is arguably not implemented even in pseudocode.\n\nBeyond that, the paper offers no evaluation. No case database, no ontology, no similarity function, no user study. Section 5 explicitly defers experiments to future work. Given those omissions, Section 4's claims about improved trust, decision quality, compliance, and democratization are unsupported assertions. The reader's report is right: this is unfalsifiable as written.\n\nThe novelty is also thin. The paper's own citations (Ahmed et al., Haque et al.) describe prior systems that combine CBR and ontologies. The architecture here adds a label and some pseudocode but no new mechanism.\n\nWho gets value from this? Possibly a newcomer to XAI wanting a short overview of how CBR and ontologies might fit together. Not a researcher looking for a testable method or a result.\n\nRecommendation: desk reject. It does not meet the bar for peer review in its current form. If the author later adds a concrete instantiation with a real ontology and case base, and an evaluation of explanation quality against a baseline, it could become a legitimate paper. As is, it is an extended abstract with overclaiming.","headline":"A well-written but empty proposal: the ontology never participates in the decision, and there is no evaluation to back the claims.","tokens_in":8302,"tokens_out":2303,"would_cite":false,"duration_ms":25674,"reading_group":"no","serious_thinker":"no","would_accept_peer_review":false},"rs_alignment":null,"lean_confirmation":null,"pith_extraction":{"msc":[],"pacs":[],"model":"deepseek-v4-flash","headline":"This paper proposes ClarifAI, a system that fuses case-based reasoning with an ontology-driven framework to make AI decision-making interpretable and transparent for diverse stakeholders.","keywords":["ClarifAI","Case-Based Reasoning","Ontology","AI interpretability","Explainable AI","Transparency","Decision-making","Explanation generation"],"falsifier":"Implement the three algorithms with an explicit similarity function and a real domain ontology, then run a controlled study in a high-stakes domain (for example, medical or loan decisions): if the generated explanations—concatenated ontology definitions—do not improve users' comprehension, trust, or decision quality relative to a baseline that returns only the retrieved case and solution, the central claim fails.","tokens_in":7335,"feed_emoji":"🧠","tokens_out":7279,"duration_ms":74202,"temperature":0.7,"pith_summary":"ClarifAI is a proposed architecture for explainable AI that combines case-based reasoning—solving new problems by retrieving similar past cases—with an ontology-driven framework that organizes domain concepts and their relationships. The paper argues that this pairing yields explanations that are both relatable, because they point to concrete prior examples, and contextually grounded, because they draw on a structured model of the domain. The intended payoff is that stakeholders in high-stakes settings such as healthcare, finance, and public policy can understand, trust, and audit AI-assisted decisions. The paper presents the design, the rationale, and a three-step algorithmic sketch (retrieve similar case, generate explanation, clarify decision); a working implementation and experimental evaluation are designated as future work.","feed_headline":"Past cases plus ontologies can make AI decisions explainable","feed_subtitle":"The proposed ClarifAI system explains AI choices with similar past cases plus structured domain knowledge.","key_machinery":"The central object is the ClarifAI pipeline itself, defined by the synergy of two components: a Case-Based Reasoning engine, which retrieves the most similar prior case from a case database using a similarity function, and an ontology framework, which provides definitions and relations for the concepts involved in the case solution. The 'explanation' is generated by concatenating, for each concept in the chosen solution, its ontology definition—so the explanation's content is entirely a function of the retrieved case and the domain ontology. Three pseudocode algorithms (retrieve similar case, generate explanation, clarify decision) make the intended flow explicit: input a new case, find the closest stored case, look up domain definitions, and return the similar case plus solution plus explanation. The load-bearing work is done by that explanation generator: it is what converts retrieval and ontology lookup into something a user can read.","core_discovery":"The central claim is that integrating case-based reasoning with an ontology-driven framework gives AI systems a decisive interpretability advantage: CBR supplies narratives ('this decision is like case X, whose outcome was Y'), while ontologies supply conceptual depth ('X is connected to these domain concepts and relations'). Together, the two components let the system answer not only what was decided but why, in terms a non-expert can follow. The paper formalizes the workflow as three algorithms—retrieve the most similar case, generate an explanation by looking up concept definitions for the solution's concepts, and package both into decision details—and argues that this design supports trust, decision quality, compliance, and broader access to AI. The discovery, in other words, is not a new mathematical result or a measured improvement, but a proposed mechanism: explanation as the combination of a precedent and a structured conceptual frame.","pith_inferences":["The paper does not define the similarity function in Algorithm 1; choosing one and checking whether the retrieved 'most similar' cases are actually relevant is the immediate test the design begs for.","An explanation that only concatenates ontology definitions tells a reader what concepts are involved but not why the similarity holds; an editorially suggested extension is to also state the shared features between the new case and the retrieved case.","The architecture's benefit could be measured directly: build a small ClarifAI on a public dataset with a domain ontology and compare user comprehension and trust against simpler baselines.","If the pipeline is instantiated, the natural next domain is human-robot interaction, where case-based explanations of robot decisions could be evaluated for trust and satisfaction."],"forward_implications":["If the design works as argued, AI-assisted decisions in healthcare, finance, and public policy could come with an audit trail: the similar past case, the solution, and the domain concepts behind it.","Non-experts could engage with AI outputs because explanations are framed as concrete precedents rather than model internals.","Organizations could more easily demonstrate regulatory compliance by documenting how and why each decision was made.","The same CBR-plus-ontology pipeline could be carried into human-robot interaction, where explanations of a robot's navigation or interaction choices are generated from robot-specific cases and an enriched ontology."],"supporting_citations":[{"why":"Supplies the argument that case-based reasoning produces explanations by leveraging past cases.","marker":"[15]"},{"why":"Lays the foundational framework for case-based reasoning as analogy and experience reuse.","marker":"[10]"},{"why":"States that CBR's reliance on historical data makes decisions naturally more explainable.","marker":"[11]"},{"why":"Foundational treatment of ontologies as structured knowledge representation for interpretability.","marker":"[4]"},{"why":"Shows how ontology-driven approaches structure domain knowledge to make AI decisions transparent.","marker":"[9]"},{"why":"Explores the integration of semantic and ontology approaches with cases, adding semantic richness.","marker":"[7]"},{"why":"Demonstrates the combined CBR-ontology approach in diagnosis systems, improving explainability.","marker":"[1]"}],"fun_headline_variants":["Case-based and ontology-driven AI explanations","ClarifAI uses cases and ontologies to explain AI choices","Explain AI via similar past cases and structured domain knowledge","CBR plus ontologies: a path to transparent AI decision-making","Ontology-rich case reasoning for interpretable AI"],"cache_read_input_tokens":3200,"weakest_assumption_plain":"The design assumes that a populated case database and a domain ontology exist for every application, and that the undefined similarity function and ontology-based concept definitions will produce explanations that stakeholders find trustworthy and usable.","fun_headline_variants_meta":{"raw":{"variants":["Case-based and ontology-driven AI explanations","ClarifAI uses cases and ontologies to explain AI choices","Explain AI via similar past cases and structured domain knowledge","CBR plus ontologies: a path to transparent AI decision-making","Ontology-rich case reasoning for interpretable AI"]},"model":"deepseek-v4-flash","effort":"low","cost_usd":0.000171,"raw_usage":{"total_tokens":1232,"prompt_tokens":864,"completion_tokens":368,"prompt_tokens_details":{"cached_tokens":384},"prompt_cache_hit_tokens":384,"prompt_cache_miss_tokens":480,"completion_tokens_details":{"reasoning_tokens":290}},"tokens_in":480,"tokens_out":368,"duration_ms":4356,"temperature":1.0,"reasoning_tokens":290,"cache_read_input_tokens":384,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-08-06T17:02:06.258380+00:00","model_set":{"reader":"deepseek-v4-flash"},"falsifier":"Implement the three algorithms with an explicit similarity function and a real domain ontology, then run a controlled study in a high-stakes domain (for example, medical or loan decisions): if the generated explanations—concatenated ontology definitions—do not improve users' comprehension, trust, or decision quality relative to a baseline that returns only the retrieved case and solution, the central claim fails.","supporting_citations":[{"cited_title":"Morgan Kaufmann (1993)","cited_arxiv_id":null,"evidence_quote":"Lays the foundational framework for case-based reasoning as analogy and experience reuse."},{"cited_title":"Menlo Park: AAAI Press/MIT Press (1996),https://homes","cited_arxiv_id":null,"evidence_quote":"States that CBR's reliance on historical data makes decisions naturally more explainable."},{"cited_title":"In: Advanced Information and Knowledge Processing (2004),https://api","cited_arxiv_id":null,"evidence_quote":"Foundational treatment of ontologies as structured knowledge representation for interpretability."},{"cited_title":"International Journal of Network Security & Its Applications 5, 61–69 (2013).https://doi.org/10.5121/ijnsa.2013.5105","cited_arxiv_id":null,"evidence_quote":"Shows how ontology-driven approaches structure domain knowledge to make AI decisions transparent."},{"cited_title":"International Journal of Clinical Practice 2022, 1–27 (2022)","cited_arxiv_id":null,"evidence_quote":"Explores the integration of semantic and ontology approaches with cases, adding semantic richness."},{"cited_title":"In: Successful Case-based Rea- soning Applications - I, Studies in Computational Intelligence","cited_arxiv_id":null,"evidence_quote":"Demonstrates the combined CBR-ontology approach in diagnosis systems, improving explainability."}],"review_version":1}