{"id":"b49cb7f7-26a2-41c0-aa9c-0c62454fcedb","arxiv_id":"2603.06396","paper_version":2,"verdict":"UNVERDICTED","confidence":"LOW","novelty_score":5.0,"correctness_risk":"medium","formal_verification":"none","parameter_count":3,"one_line_summary":"Environment-dependent, optionally charge-conserving Coulomb terms grafted onto Moment Tensor Potentials recover LO–TO splitting and experimental dielectric constants for NaCl and improve dimer binding curves.","lead":"The authors add environment-dependent Coulomb charges to local machine-learning potentials so long-range electrostatics are explicit. On NaCl this recovers LO–TO phonon splitting and a dielectric constant close to experiment; organic dimers and PbTiO3 are also tested.","discovery_kind":"new_method","skeptic_critique":{"model":"grok-4.5","headline":"No significant objection identified to the abstract's strongest claim; the supplied full text is a different paper, so the load-bearing physics cannot be stress-tested.","rationale":"The reader correctly set UNVERDICTED with low confidence after noting that the cached full text is a different paper. My pass confirms the same mismatch: the abstract of 2603.06396 cannot be checked against methods or results that are not present. No internal inconsistency or weakest-assumption failure can be demonstrated without the matching manuscript. The honest outcome is therefore no significant objection to the scientific claim itself, and no change to the reader's UNVERDICTED verdict. The single concrete check is to obtain and re-review the correct full text of 2603.06396.","tokens_in":27131,"tokens_out":452,"duration_ms":10343,"concrete_test":"Confirm that the full PDF/source of arXiv:2603.06396 (not 2603.06394) is loaded; then re-run the stress-test on the actual charge-model equations, the isotropic phonon derivation, the reported LO–TO and dielectric values vs experiment/DFT, and the PbTiO3 spectrum comparison.","verdict_should_be":"UNCHANGED","load_bearing_attack":"The reader's strongest claim is that an environment-dependent, total-charge-conserving Coulomb model plus local MTP, fitted only to energies/forces/stresses, recovers correct NaCl LO–TO splitting at Γ and a dielectric constant from MD dipole fluctuations that matches experiment, with a phonon method that also works for uniaxial PbTiO3. That claim is load-bearing only if the full methods, charge model, phonon construction, baselines, and numerical results are present. The CACHEABLE full manuscript is arXiv:2603.06394 (schema-gated agentic AI workflows), not 2603.06396. No equations for the charge model, no LO–TO numbers, no dielectric comparison table, and no PbTiO3 phonon plots are available to audit. The concern therefore does not land as a flaw in the physics argument; it is an identity/content mismatch that prevents any technical stress test of the claim.","agreement_with_reader":"agree"},"referee_report":{"model":"grok-4.5","summary":"The manuscript (as represented by its abstract) proposes two machine-learning interatomic potentials that add explicit long-range Coulomb electrostatics via environment-dependent point charges, one of which also enforces total-charge conservation. These long-range terms are combined with a local Moment Tensor Potential (MTP) and trained on energies, forces, and stresses for non-periodic organic dimers (CH3COO− with 4-methylphenol or 4-methylimidazole) and periodic NaCl. The abstract claims lower training errors than local MTP alone, qualitatively correct dimer binding curves, a phonon method for isotropic materials that recovers the correct LO–TO splitting at Γ for NaCl, a dielectric constant from MD dipole fluctuations in good agreement with experiment, and a phonon spectrum for uniaxial tetragonal PbTiO3 that matches DFT despite the method being formally derived for isotropic systems.","tokens_in":27433,"tokens_out":1022,"duration_ms":16085,"significance":"If the full results hold under scrutiny, the work would be a meaningful contribution to long-range ML potentials: recovering LO–TO splitting and a dielectric constant from models fitted only to energies, forces, and stresses (rather than to those observables) is a strong, falsifiable test of electrostatic representation. Combining environment-dependent charges with total-charge conservation and a local MTP is a clear, reusable design choice. The claimed extension from isotropic NaCl to uniaxial PbTiO3 would broaden impact if the phonon construction is shown to be controlled rather than fortuitous. These strengths cannot be confirmed from the abstract alone and require the actual methods, numbers, and baselines.","major_comments":[{"comment":"The supplied full-text body does not match arXiv:2603.06396. The cached manuscript is a different paper (schema-gated agentic AI workflows). Without the correct methods, equations for the charge models, phonon construction, tables of LO–TO/dielectric values, and PbTiO3 spectra, the central claims cannot be audited. A complete technical review requires the actual manuscript of 2603.06396.","section":null},{"comment":"Abstract claim on LO–TO: the charge-conserving long-range model is said to predict the correct Γ-point LO–TO splitting for isotropic NaCl when fitted only to E/F/stress. This is the load-bearing result. The full paper must report the numerical LO and TO frequencies (model vs DFT/experiment), the non-analytic correction or equivalent construction used at Γ, and a local-MTP-only baseline showing that LO–TO is not recovered without the long-range term.","section":null},{"comment":"Abstract claim on the phonon method: a method is introduced for phonon spectra of isotropic materials using only the long-range models, then applied to uniaxial tetragonal PbTiO3 with the statement that it is 'also perspective' for uniaxial materials. The formal isotropic derivation and the controlled approximation (or correction) used for uniaxial systems must be stated explicitly; qualitative DFT agreement alone does not establish that the isotropic construction is reliable for PbTiO3.","section":null},{"comment":"Dielectric constant from MD dipole fluctuations: the abstract asserts good agreement with experiment for NaCl. The full paper must specify ensemble, boundary conditions, system size, fluctuation formula, and numerical value with uncertainty, plus comparison to experiment and to a local-only baseline, so that agreement is not under-specified.","section":null}],"minor_comments":[{"comment":"The abstract should state whether LO–TO and the dielectric constant were held out as pure predictions (never used in training or hyperparameter selection) and give at least one quantitative LO–TO and dielectric number for NaCl.","section":null},{"comment":"Clarify early how total-charge conservation is enforced (soft penalty vs hard constraint) and whether charges are predicted per environment with a global correction, as this affects transferability between charged dimers and neutral crystals.","section":null},{"comment":"Name the long-range summation scheme (Ewald/PME/etc.) and any dielectric boundary conditions used for periodic NaCl and PbTiO3, since these choices affect LO–TO and dielectric results.","section":null}],"recommendation":"uncertain","confidential_remarks":"There is a hard identity mismatch: the review package labels arXiv:2603.06396 (long-range ML potentials / LO–TO) but the full manuscript text provided is arXiv:2603.06394 (schema-gated agentic AI). I cannot responsibly accept, revise, or reject the physics claims on that basis. Please resupply the correct PDF/source for 2603.06396 and reassign for a full technical review. My recommendation is 'uncertain' solely for that reason, not because the abstract’s physics program looks unsound."},"author_rebuttal":null,"desk_editor":{"model":"grok-4.5","letter":"The abstract for 2603.06396 is a solid, targeted claim in ML interatomic potentials: environment-dependent point charges (one version conserving total charge) plus classical Coulomb, grafted onto local MTP, fitted only to energies/forces/stresses, then used to recover LO–TO splitting at Γ for NaCl, a dielectric constant from MD dipole fluctuations that matches experiment, better dimer binding curves, and a phonon spectrum for uniaxial PbTiO3 that tracks DFT. That is the right structure—electrostatics as prediction, not a fitted target—and it would matter for ionic crystals and charged organics if the numbers hold.\n\nWhat is new is not the idea of environment-dependent charges or long-range MLIPs (those already exist), but the concrete combination with MTP plus the phonon construction that is claimed to work from the long-range model alone, and the demonstration that the charge-conserving version gets LO–TO right. The abstract also reports lower training errors on the same sets and qualitative binding curves for the organic dimers. That is useful engineering if true.\n\nThe soft spot is not a flaw in the argument; it is that we cannot check any of it. The full text supplied under this arXiv id is Strickland et al. on schema-gated agentic AI workflows (2603.06394). No charge-model equations, no LO–TO numbers, no dielectric table, no PbTiO3 plots, no baselines. So free parameters (charge network, MTP basis, Ewald settings) and the isotropic-to-uniaxial leap stay unexamined. Circularity risk looks low from the abstract alone, but residual risk cannot be ruled out without methods.\n\nThis is for people building or using MLIPs for polar/ionic systems. It deserves a serious referee once the correct manuscript is attached. Right now I would not cite it or bring it to reading group; I would wait for the real paper and then re-read. If the full methods match the abstract’s claims, engage. Until then, treat the abstract as a promise, not a result.","headline":"Abstract promises a real MLIP advance (charge-conserving long-range MTP recovering NaCl LO–TO and dielectric constants from E/F/stress only), but the cached full text is a completely different paper, so the physics cannot be audited.","tokens_in":28045,"tokens_out":526,"would_cite":false,"duration_ms":6409,"reading_group":"no","serious_thinker":"unclear","would_accept_peer_review":true},"rs_alignment":null,"lean_confirmation":null,"pith_extraction":{"msc":[],"pacs":["63.20.D-","77.22.-d","31.15.xv","71.15.Pd"],"model":"grok-4.5","headline":"Environment-dependent charges plus Coulomb terms let machine-learning potentials recover LO–TO splitting and dielectric constants from energies, forces, and stresses alone.","keywords":["machine-learning potentials","long-range electrostatics","environment-dependent charges","Moment Tensor Potential","LO-TO splitting","dielectric constant","phonon spectra","NaCl"],"falsifier":"Compute LO–TO splitting at Γ and the static dielectric constant for NaCl (and the full phonon spectrum for tetragonal PbTiO₃) with the charge-conserving long-range MTP and compare to high-quality density-functional theory or experiment: a large mismatch in the LO–TO gap or dielectric constant would refute the central claim.","tokens_in":28000,"feed_emoji":"⚡","tokens_out":1043,"duration_ms":12720,"temperature":0.7,"pith_summary":"Local machine-learning potentials miss long-range electrostatics, so they struggle with charged molecular complexes and polar crystals. This paper adds explicit Coulomb interactions driven by point charges that depend on each atom’s local environment, and optionally conserves the system’s total charge, then couples those terms to a local Moment Tensor Potential. On organic anion–molecule dimers and NaCl, the hybrid models cut training error relative to pure local fits and produce qualitatively correct binding curves. A phonon method that uses only the long-range models fitted to energies, forces, and stresses recovers the correct LO–TO splitting at the Γ-point for isotropic NaCl; molecular-dynamics dipole fluctuations with the same model yield a dielectric constant close to experiment. The same approach also gives a PbTiO₃ phonon spectrum that matches density-functional theory, even though the phonon construction was formally derived for isotropic materials. The practical claim is that environment-dependent charges plus classical Coulomb electrostatics are enough to restore the polar and dielectric observables that pure short-range machine-learning potentials cannot capture.","feed_headline":"ML potentials with local charges recover LO–TO splitting","feed_subtitle":"Coulomb terms from environment-dependent charges match NaCl dielectric data and PbTiO₃ phonons","key_machinery":"Environment-dependent point charges inside classical Coulomb interactions (with optional total-charge conservation), combined with a local Moment Tensor Potential: the charges supply the missing long-range electrostatics while the local potential handles short-range chemistry, enabling phonon spectra and dielectric response without fitting those observables directly.","core_discovery":"A long-range model whose point charges depend on local atomic environments and that conserves total charge, combined with a local Moment Tensor Potential and trained only on energies, forces, and stresses, predicts the correct LO–TO splitting at the Γ-point for isotropic NaCl and a dielectric constant from molecular-dynamics dipole fluctuations that agrees with experiment; the same long-range construction also yields a PbTiO₃ phonon spectrum consistent with density-functional theory.","pith_inferences":["If environment-dependent charges generalize, many existing short-range machine-learning force fields could be retrofitted with a charge model rather than retrained from scratch for polar materials.","Failure modes will likely appear first in systems with strong charge transfer, metallic screening, or highly anisotropic Born charges where a classical point-charge Coulomb form is inadequate.","The charge-conserving variant may be the more transferable default for charged non-periodic systems and defective crystals, even when total charge is nominally zero.","A natural next test is whether the same models recover infrared intensities or Born effective charges without extra training data."],"forward_implications":["Machine-learning potentials trained only on energies, forces, and stresses can still target polar and dielectric observables if long-range electrostatics are modeled with environment-dependent charges.","LO–TO splitting in isotropic crystals becomes accessible without separate Born-effective-charge or dielectric fitting.","Binding curves of charged organic dimers improve when total charge is conserved and Coulomb interactions are explicit.","The same long-range construction appears usable beyond isotropic crystals, as shown by agreement with DFT phonons for uniaxial PbTiO₃.","Dielectric constants can be estimated from molecular-dynamics dipole fluctuations driven by the long-range potential rather than from separate response calculations."],"fun_headline_variants":["Environment-dependent charges recover LO-TO splitting in ML potentials","Long-range ML potentials with local charges predict NaCl LO-TO and dielectric","Charge-conserving ML models yield LO-TO splitting and dielectric constants","Local-environment charges enable correct LO-TO and phonons in ML potentials","ML potentials with adaptive charges match NaCl dielectric and PbTiO3 phonons"],"cache_read_input_tokens":16512,"weakest_assumption_plain":"That environment-dependent point charges plus classical Coulomb terms are a sufficient and transferable stand-in for true long-range electrostatics across both charged organic dimers and ionic or ferroelectric crystals, and that a phonon method derived for isotropic materials remains reliable for uniaxial systems such as PbTiO₃.","fun_headline_variants_meta":{"raw":{"variants":["Environment-dependent charges recover LO-TO splitting in ML potentials","Long-range ML potentials with local charges predict NaCl LO-TO and dielectric","Charge-conserving ML models yield LO-TO splitting and dielectric constants","Local-environment charges enable correct LO-TO and phonons in ML potentials","ML potentials with adaptive charges match NaCl dielectric and PbTiO3 phonons"]},"model":"grok-4.5","effort":"low","cost_usd":0.003358,"raw_usage":{"total_tokens":1209,"prompt_tokens":878,"num_sources_used":0,"completion_tokens":82,"cost_in_usd_ticks":33580000,"prompt_tokens_details":{"text_tokens":878,"audio_tokens":0,"image_tokens":0,"cached_tokens":256},"completion_tokens_details":{"audio_tokens":0,"reasoning_tokens":249,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"tokens_in":878,"tokens_out":82,"duration_ms":2930,"temperature":1.0,"reasoning_tokens":249,"cache_read_input_tokens":256,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-07-15T13:52:01.295692+00:00","model_set":{"reader":"grok-4.5"},"falsifier":"Compute LO–TO splitting at Γ and the static dielectric constant for NaCl (and the full phonon spectrum for tetragonal PbTiO₃) with the charge-conserving long-range MTP and compare to high-quality density-functional theory or experiment: a large mismatch in the LO–TO gap or dielectric constant would refute the central claim.","supporting_citations":[],"review_version":1}