{"id":"60adf81c-c959-4369-8766-769a3c860ea1","arxiv_id":"2607.16717","paper_version":1,"verdict":"CONDITIONAL","confidence":"MODERATE","novelty_score":6.0,"correctness_risk":"medium","formal_verification":"none","parameter_count":0,"one_line_summary":"A causal graph's children of a node act as value screens: conditioned on them, a node's value is independent of all non-ancestors, yielding a causal decomposition of utility.","lead":"A new principle for decision-making says the value of an action should depend on its real effects, not on arbitrary preferences. The paper proves this can split utility into small causal pieces and extend Bellman-style reasoning to any causal diagram.","discovery_kind":"new_method","skeptic_critique":{"model":"deepseek-v4-flash","headline":"The normative justification of the v-CMC is close to circular: child mediation (Def. 7) is the v-CMC restricted to descendants, and the CDT property (Def. 9) is the same screening-off intuition for interventions; so Theorem 3 assumes the central claim rather than deriving it from weaker or independe","rationale":"The reader's weakest assumption correctly identifies the common-scale/domain requirement for subtractive conditional value as a genuine limitation. That concern is real: Definition 1's common positive-affine scale across all subsets is nontrivial and rules out many standard utility representations. However, the more load-bearing concern for the paper's central normative claim is that, even granting the domain assumptions, the justification of the v-CMC is not independent of the conclusion. Theorem 3's child-mediation premise is the descendant part of the v-CMC, and the CDT property is the same screening-off intuition for interventions; modularity then transfers it back to the original graph. In the simplest nontrivial DAG, the proof simply assumes the v-CMC. This does not make the formal results wrong, but it means the paper has not shown that rational utility functions should obey the v-CMC; it has shown that if one accepts a causal-decision-theoretic screening-off intuition, the v-CMC follows. Since the reader's verdict is already CONDITIONAL and this concern supports that assessment, no change in verdict is needed; the reader should perhaps weight the circularity more heavily in the rationale, but the conditional verdict stands.","tokens_in":21950,"tokens_out":19859,"duration_ms":199458,"concrete_test":"Analytical check on the minimal DAG W→Y→Z. Construct a value function u (defined on all relevant subsets, satisfying Definition 3 consistency and hence the semi-graphoid axioms) such that W ⊥⊥_u Z | Y fails, while respecting Definition 8 modularity and choosing interventional utilities u_do(Y), u_do(Z) to satisfy Definition 9 for Y and Z. Because modularity leaves u_do(Y) and u_do(Z) unconstrained on sets containing the intervened node, such a u should exist whenever child mediation is not assumed. If it exists, Theorem 3's entailment of the local v-CMC depends essentially on assuming child mediation, which is precisely the v-CMC for the descendant part, and the normative justification is circular. If no such u exists, the concern is refuted.","verdict_should_be":"UNCHANGED","load_bearing_attack":"The central claim is Definition 4 (local v-CMC) as a normative constraint on rational utility. The formal equivalences (Thms 4–5) are conditional; they show what follows if one accepts the v-CMC, not that rational utility must obey it. The only general justification offered is Theorem 3, but its premises are near-identical to the conclusion. Definition 7 (child mediation) asserts exactly W ⊥⊥_u D' | Ch(W) for every set D' of non-child descendants of W—that is the local v-CMC restricted to the descendant part of NA(W). In the minimal DAG W→Y→Z, child mediation is the whole v-CMC for W (W ⊥⊥_u Z | Y): no other non-ancestors exist. Meanwhile, Definition 9 (CDT property) is vacuous for the root W (it has no non-descendants) and, for non-root nodes, it constrains the interventional utility u_do(W), which modularity (Def. 8) leaves unconstrained on sets containing W. Thus the proof's work is done by a premise that is exactly the v-CMC for the descendant part, and the CDT property is itself a causal-decision-theoretic screening-off intuition ('value depends only on effects')—the same normative idea being defended. The paper concedes scope limits (Appendix A, Section 4 footnote 2) but provides no independent argument that rational preferences must screen off non-child descendants once children are fixed. Without that, the abstract's claim that v-CMC is a normative constraint is unsupported; the formal results remain conditional mathematics.","agreement_with_reader":"partial"},"referee_report":{"model":"deepseek-v4-flash","summary":"The paper proposes a 'value Causal Markov Condition' (v-CMC): for a value-sufficient causal DAG and a utility function defined on subsets of variables, each node is conditionally value independent of its non-ancestors given its children (Definition 4). It argues this is a normative constraint on rational utility, introduces a probability--value duality (Section 5), and proves three equivalent formulations: local, global (v-separation), and decomposition (Definitions 10--12, Theorem 4). It also proves soundness and completeness of v-separation (Theorem 5), derives a Bellman-type recursion on DAGs (Theorem 6), and applies the decomposition to utility elicitation, modular transfer under interventions, and automatic influence-diagram construction (Section 7). The formal development is conditional on the v-CMC and on the assumption that utilities are defined on arbitrary subsets with a common positive affine scale.","tokens_in":22362,"tokens_out":10870,"duration_ms":102024,"significance":"The formal core is useful and mostly sound. The equivalence of local/global/decomposition versions is a natural dual of standard results, and the completeness proof using u = log P is a clean construction that does not rely on any fitted parameters. The Bellman-type decomposition, if correctly proved, gives a principled generalization of Bellman recursion to DAGs, and the elicitation and transfer algorithms are concrete and potentially practical. These conditional results are a genuine contribution to graphical utility models. The main weakness is that the paper's central normative claim -- that rational utility should obey the v-CMC -- is not independently established: the justification theorem derives the principle from premises that largely restate it. The paper would be publishable as a conditional mathematical framework, but not, in its current form, as an argument that rational preferences must satisfy the v-CMC.","major_comments":[{"comment":"The normative justification is close to circular. Definition 7 (child mediation) requires W ⊥_u D' | Ch(W) for every non-child descendant set D', which is exactly the local v-CMC restricted to the descendant part of NA(W). In the minimal DAG W→Y→Z, child mediation is the whole v-CMC for W. The CDT property (Definition 9) supplies the remaining non-descendant part, but only for the interventional utility u_do(W); utility modularity (Definition 8) transfers that screening-off back to u. Thus Theorem 3 derives the v-CMC from premises that already contain the same screening-off intuition. The paper's caveats in Section 4 footnote 2 and Appendix A acknowledge scope limits, but they do not provide an independent argument that rational utility must screen off non-child descendants once children are fixed. Since the abstract claims v-CMC is a normative constraint, this is load-bearing. Please ei","section":"§4, Definitions 7--9 and Theorem 3"},{"comment":"The proof of the key lemma (37) is under-specified. In the induction step, the proof uses the v-CMC to assert u({W} | Ch(W) ∪ S' ∪ Ch(S')) = u(W | Ch(W)) and u(S' | Ch(S') ∪ Ch(W)) = u(S' | Ch(S')). The conditioning set includes Ch(S'), which may contain nodes that are descendants of W, e.g., a common child of W and a node S' ∈ S. The local v-CMC (Definition 4) applies only to non-ancestors, and the stated reason 'W has no ancestors in S' does not rule out such descendants. The step can be repaired by invoking the global v-CMC and showing that S' ∪ Ch(S') is v-separated from W by Ch(W), but as written the proof is incomplete. This matters because Theorem 6 is the paper's advertised Bellman-type generalization.","section":"§7.1, Theorem 6 and Appendix G, Eq. (37)"},{"comment":"The framework requires utilities to be defined on arbitrary subsets of variables and to be unique up to a common positive affine scale across all subsets, and it imposes conditional consistency (Definition 3) as an additional axiom. These are strong assumptions. The paper notes that it is framework-neutral and cites existing frameworks, but it does not establish that rational preferences in those frameworks always admit such a common-scale representation on all subsets of a causal variable set. If utilities are only ordinally comparable, or are defined only on acts, the v-CMC and all equivalences in Theorems 4--6 have no domain. The paper should state this limitation prominently and specify which decision-theoretic settings satisfy the required scale condition.","section":"§2, Definitions 1--3"}],"minor_comments":[{"comment":"The symbol ND is used both for N ∩ (D \\ Ch(W)) and for the set of all non-descendants of W in Gdo(W). This makes the proof of Theorem 3 hard to follow and should be disambiguated.","section":"Appendix D"},{"comment":"The claim that 'the graphical relations between W, NND, and D are not affected by the intervention do(W)' is imprecise. The needed argument is that utility modularity (Definition 8) applies to the specific subsets that enter the conditional-value expression; please spell this out.","section":"Appendix D, after Eq. (17)"},{"comment":"In the completeness proof, the constructed value function u = log P is a formal witness only; it is not claimed to be a normatively justified utility. Stating this explicitly would avoid unnecessary objections.","section":"Appendix F"}],"recommendation":"major_revision","confidential_remarks":"The formal, conditional part of the paper is solid and could be a good contribution to graphical utility models. The main obstacle is the normative claim: Theorem 3 does not provide an independent derivation of the v-CMC. If the author is willing to reframe the paper as 'consequences of accepting the v-CMC' and to move the normative argument to a clearly labeled conjecture or to add genuinely independent decision-theoretic foundations, I would support publication. I see no evidence of citation manipulation or other ethical concerns."},"author_rebuttal":null,"desk_editor":{"model":"deepseek-v4-flash","letter":"Colleague,\n\nThe formal core of this paper is genuine and largely sound: local, global, and decomposition versions of the v-CMC are proven equivalent; v-separation is sound and complete; and the Bellman-type recursion on causal DAGs is a real generalization of standard Bellman recursion, with the log-P completeness witness a nice trick. The reversal from parent-based to child-based screening is a legitimate gap relative to Brafman and Engel, and the utility-transfer and influence-diagram applications are useful. I checked the algebra in the main proofs and the equivalences and found no error.\n\nThe soft spot is the normative argument, and the stress-test note lands. Theorem 3 claims to justify the v-CMC from three premises, but child mediation (Def. 7) is exactly the v-CMC restricted to descendants: in the minimal chain W→Y→Z, child mediation for W is the entire v-CMC for W. The CDT property supplies the non-descendant part, but it is the same screening-off intuition the v-CMC is defending. So the theorem is conditional mathematics, not an independent derivation of a rational-utility constraint. The paper concedes scope in Appendix A and footnote 2, but the abstract's claim that v-CMC is a normative constraint overreaches what the premises establish.\n\nThe domain assumptions are also strong: utilities on arbitrary subsets with a common positive affine scale, plus value sufficiency. Those are stated clearly, so not a flaw, but they limit the range of application.\n\nMinor point: Theorem 3's proof sketch is compressed; the full appendix version is fine. The Bellman lemma (37) is sketched but fixable.\n\nBottom line: this is a solid subfield contribution with a candid limitation at its center. It deserves a serious referee and likely publication with revisions that reframe the normative claim. I'd cite it if I worked on causal decision theory or graphical utility models, and I'd bring it to a reading group to argue about the circularity.","headline":"The v-CMC machinery is a real formal contribution, but the normative justification is close to circular—still deserves a serious referee.","tokens_in":22786,"tokens_out":2577,"would_cite":true,"duration_ms":28271,"reading_group":"yes","serious_thinker":"yes","would_accept_peer_review":true},"rs_alignment":null,"lean_confirmation":null,"pith_extraction":{"msc":["91B06"],"pacs":[],"model":"deepseek-v4-flash","headline":"The paper proposes the value Causal Markov Condition (v-CMC), a normative principle asserting that in a causally sufficient DAG a variable's value is independent of its non-ancestors conditional on its causal children, and proves this yield","keywords":["value Causal Markov Condition","conditional value independence","v-separation","causal DAG","utility decomposition","Bellman recursion","utility elicitation","influence diagrams"],"falsifier":"Construct a utility function on a small DAG (say three nodes with A→B←C) that satisfies the decomposition v-CMC but for which u(A | B, C) ≠ u(A | B); if such a function exists, the claimed equivalence between local and decomposition v-CMC fails, and the appendix's proof would be contradicted.","tokens_in":21843,"feed_emoji":"🧩","tokens_out":6021,"duration_ms":59497,"temperature":0.7,"pith_summary":"Value, the paper claims, should obey a causal independence principle just as probability does. It proposes the value Causal Markov Condition (v-CMC): in a causally sufficient DAG, once you fix the causal children of a variable, its conditional value contribution should not depend on any of its non-ancestors. The payoff is that a rational utility function then decomposes over the DAG into a sum of local child-conditional terms, a Bellman-style recursion on causal graphs, and a graphical criterion (v-separation) that is sound and complete for conditional value independence. If accepted, this gives a normative bridge between causal knowledge and preference, enabling modular transfer of utility information across contexts and structured elicitation procedures.","feed_headline":"Markov condition for value: children screen off non-ancestors","feed_subtitle":"Causal structure should constrain utility: a new rule yields DAG decompositions and Bellman-type recursions.","key_machinery":"The load-bearing objects are the subtractive conditional value u(x|y)=u(x,y)-u(y), which turns utilities into a semi-graphoid independence relation; the child-closed subgraph; and the translation key that swaps parents with children, non-descendants with non-ancestors, common causes with common effects, and p(A|B)=p(A,B)/p(B) with u(A|B)=u(A,B)-u(B). This key translates probabilistic CMC results into value results, and v-separation (defined as the value-dual of d-separation) provides the graphical criterion that is proven sound and complete for conditional value independence.","core_discovery":"The paper's central discovery is a duality between probability and value in causal graphs: probability flows downstream, value flows upstream. Formalizing this, it defines conditional value as subtraction, u(x|y)=u(x,y)-u(y), and conditional value independence accordingly, then states the local v-CMC: for any node Xi and any set N of non-ancestors, Xi is value-independent of N given its children Ch(Xi), whenever the graph is value-sufficient (all shared causal effects are included). The paper proves this local statement is equivalent to a global statement using v-separation (the exact dual of d-separation) and to a decomposition statement: over any child-closed subgraph, total utility is the","pith_inferences":["The same probability-value duality may dualize further causal-inference concepts—transportability, confounding, counterfactuals—into value analogues, suggesting a broader program of causal value theory beyond the equivalences proven here.","Applied to inverse reinforcement learning, v-CMC could serve as a structural prior that selects among the many reward functions consistent with observed behavior; a natural test is whether recovered rewards on a known causal graph approximate the child-conditional decomposition.","The value-sufficiency requirement implies that practical elicitation protocols must explicitly include shared causal effects as variables; if common effects are omitted, the v-CMC will appear to be violated, which gives a diagnostic for model misspecification in preference elicitation.","The equivalence results depend on utilities being on a common interval or ratio scale across subsets; if only ordinal preferences are available, the v-CMC has no subtractive conditional value to constrain, so its normative force is tied to a cardinal utility interpretation."],"forward_implications":["Under the v-CMC, any rational utility function compatible with a value-sufficient DAG decomposes as u(V') = Σ u(Xi|Ch(Xi)) on every child-closed set, turning a joint elicitation problem into a sum of small local assessments.","v-separation gives a sound and complete graphical test for conditional value independence, so one can read utility independencies directly off the causal DAG.","Bellman recursion is the special case of the v-CMC decomposition on a linear chain when local conditional values do not depend on the children; the DAG version extends it to arbitrary causal graphs.","Updating utilities after an intervention or after adding a new common effect requires revising only the local terms whose child sets change, so the cost scales with the number of affected nodes, not the whole graph.","The decomposition licenses an elicitation algorithm whose number of required utility queries is at most n·2^{1+|Ch(W)|}, linear in the number of variables."],"fun_headline_variants":["Value flows upstream: children screen off non-ancestors","v-CMC: value independence dual to d-separation","Bellman recursion on causal DAGs: a v-CMC special case","Probability down, value up: a new causal Markov condition","Children screen value: causal Markov for utility"],"cache_read_input_tokens":2304,"weakest_assumption_plain":"The whole edifice is load-bearing on utilities that are defined on arbitrary subsets of the variables and are unique up to a common positive affine scale, so that the subtractive conditional value u(x|y)=u(x,y)-u(y) is meaningful; without that scale, the v-CMC cannot even be stated.","fun_headline_variants_meta":{"raw":{"variants":["Value flows upstream: children screen off non-ancestors","v-CMC: value independence dual to d-separation","Bellman recursion on causal DAGs: a v-CMC special case","Probability down, value up: a new causal Markov condition","Children screen value: causal Markov for utility"]},"model":"deepseek-v4-flash","effort":"low","cost_usd":0.000731,"raw_usage":{"total_tokens":3078,"prompt_tokens":684,"completion_tokens":2394,"prompt_tokens_details":{"cached_tokens":256},"prompt_cache_hit_tokens":256,"prompt_cache_miss_tokens":428,"completion_tokens_details":{"reasoning_tokens":2311}},"tokens_in":428,"tokens_out":2394,"duration_ms":15596,"temperature":1.0,"reasoning_tokens":2311,"cache_read_input_tokens":256,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-08-01T20:10:57.054146+00:00","model_set":{"reader":"deepseek-v4-flash"},"falsifier":"Construct a utility function on a small DAG (say three nodes with A→B←C) that satisfies the decomposition v-CMC but for which u(A | B, C) ≠ u(A | B); if such a function exists, the claimed equivalence between local and decomposition v-CMC fails, and the appendix's proof would be contradicted.","supporting_citations":[],"review_version":1}