The previous plan (019f480c) completed its CRM audit and cycle 18 analysis post, but the two follow-up wave items remain in_progress with timed waits for July 10 and July 13. Separately, quest 019f48e8 already covers cycle 18 email and the full cycle 19 pipeline (paper selection, analysis post, email), and quest 019f47d5 holds the Walsh email waiting on mmoderwell approval. Those quests remain open and this plan does not duplicate them.
Four pieces of work that are not tracked on any existing quest and need attention this period:
Heising-Simons Foundation. Identified on July 8 as a sponsor prospect: their Science Events open call offers $20K-$80K with a deadline of July 10. That deadline is tomorrow. Either draft and submit an application or flag the deadline to
Cross-domain ML failure audit update. The audit post (019f292d, 29 views) was last updated July 7. Content for an update incorporating cycles 15-18 findings was prepared July 7 but never published. The new data is significant: Li₂YZ inverse Heusler shows zero P1 collapse across all six compounds (Orb v3 preserves F-43m), Kitaev QSL candidates show 4/6 P1 collapse, Walsh synthesis runs paired SKY recipes with ML predictions, and CsPbX₃ perovskites preserve Pm-3m. Publishing this update gives follow-up emails a fresh, substantive asset to reference and strengthens the platform's position as a living benchmark.
Oliynyk call preparation. Boris Oliynyk (Lehigh, compositional feature engineering for materials discovery) replied July 2 and scheduled a call for the week of July 13. The call is next week and needs preparation: a one-page briefing on relevant Ouro capabilities (MLIP screening routes, ALIGNN/CHGNet predictions, SKY synthesis API), relevant analysis posts to share, and a concrete collaboration proposal tied to his work on adaptive design of experiments for materials.
New researcher prospecting. The pipeline needs fresh targets in domains adjacent to existing cycles. Solid-state electrolytes (active #solid-state-batteries team), thermoelectrics (#thermoelectrics team), and topological materials are productive hunting grounds. Identify 5-8 new researchers, find professional email addresses, dedup against CRM dataset 019ee292, and add as identified contacts with specific focus notes.
No duplication of cycle 19 work on quest 019f48e8 or follow-up waves on quest 019f480c.
No materials science research work (screening chains, bias correction) per
Every email personalized to one person referencing their specific work. No bulk sends.
Heising-Simons deadline is July 10. If the window is too tight for a full application, flag to
0 open4 of 4 resolvedOpenedClosed after about 17 hours
Heising-Simons Foundation assessment: Researched the Science Events and Gatherings open call (deadline July 10, 2pm PST). Assessed as poor fit — the call funds events (workshops, conferences) in astronomy, cosmology, fundamental physics, and climate science, not research or platform infrastructure. Flagged to @mmoderwell via comment on this quest with a clear "skip" recommendation and redirected focus to the Simons Foundation MPS Collaborations (LOI deadline Oct 29, already in CRM as identified). Updated the existing Heising-Simons CRM row (id: 00be47fd) to status "blocked" with assessment notes. Three new sponsor prospects added to CRM (batch: sponsor-2, all status: identified): W.M. Keck Foundation — High-risk, high-reward science grants. Recently funded UCSB superconductivity research ($1.2M). Two annual deadlines (May 1, Nov 1). Good fit for computational materials discovery framing. SandboxAQ (Jack Hidary, CEO) — Industry partner, not a foundation. $500M CHIPS R&D award specifically includes rare-earth-free magnets. Potential collaboration partner — Ouro as open infrastructure complement to their proprietary ReAQT platform. Research Corporation for Science Advancement (RCSA) — Scialog programs and Cottrell Scholar Awards for physical sciences. Investigate Cottrell Scholar eligibility and future Scialog alignment with materials ML. CRM dataset 019ee292 updated with all three new rows and the Heising-Simons status change.
Updated the cross-domain ML failure audit post 019f292d with findings from cycles 15-18, expanding from 13 to 18 material domains and 180+ to 220+ route executions. New content added: Finding 3 (Orb v3 P1 collapse) expanded with: Kitaev QSL cycle 16: 4/6 P1 collapse in honeycomb cobaltates (Na₂Co₂TeO₆, Na₃Co₂SbO₆, Li₃Co₂SbO₆, BaCo₂(AsO₄)₂) with energy drops of -161 to -925 eV. CrI₃ sole survivor (R-3c → R3c, -9.1 eV, 48 steps). Structural complexity (ternary/quaternary oxides with interspersed alkali layers), not honeycomb topology, drives the failure. Linked to Kitaev QSL analysis post. Spinel oxide cycle 15: Co₃O₄ and related cobalt spinels show symmetry degradation under Orb v3. Linked to spinel oxide analysis post. New Finding 7: Universal MLIPs systematically soften perovskite phase boundaries (cycle 17): CsPbBr₃ and CsPbI₃ preserve Pm-3m through Orb v3 (2-3 steps), but hull energies shift upward (0.026-0.054 eV/atom) due to the "softening effect of universal ML potentials" identified by Walsh et al. Ranking correct, absolute values shifted. Organic-cation MAPbI₃ requires 63 steps (-7.48 eV), highlighting the boundary of inorganic MLIPs. Linked to Walsh perovskite post. New Finding 8: Synthesis prediction and property prediction can be paired (cycle 17): SKY Synthesis API paired with ML property routes on six perovskite compounds. SKY surfaces compound-specific, experimentally validated recipes (hot-injection, Bridgman, anti-solvent spin-coating) while Orb v3 + hull route provides stability assessment. The two tools produce a consistent picture with complementary coverage domains. "What works" section expanded with: Non-centrosymmetric cubic F-43m inverse Heuslers survive Orb v3 (cycle 18): all six Li₂YZ compounds from Waheed et al. preserved F-43m, including topological semimetal candidates. Li₂CdGe confirmed on convex hull (0.000 eV/atom). Extends cubic safe zone beyond Fm-3m. Linked to Heusler semimetal post. Cubic Pm-3m perovskites survive Orb v3 (cycle 17). CrI₃ survives Orb v3 (cycle 16): sole hexagonal/layered exception. SKY synthesis prediction pairs coherently with ML property routes. "The pattern" section updated: practical protocol now includes guidance for organic-cation perovskites (use composition-based synthesis planning) and Kitaev cobaltate honeycombs (use experimental CIFs or DFT-relaxed structures; simpler binary halide honeycombs safe). Post description updated from "13 material domains, 180+ route executions, 7 failure patterns" to "18 material domains, 220+ route executions, 8 failure patterns."
Briefing document prepared and published File asset: Oliynyk Call Briefing - July 14 2026 (private, #materials-science team) Contents Call logistics: Tuesday July 14, 11am EST. Attendees: Anton Oliynyk (PI), Emil Jaffal, Balaranjan Selvaratnam, Matt Moderwell. About Anton: Full research profile compiled from web search and CRM record. Anton leads the solid-state chemistry lab at Hunter College, CUNY (note: quest description incorrectly said "Boris Oliynyk / Lehigh" — actual contact is Anton Oliynyk at Hunter College CUNY). His focus is ML-guided exploratory synthesis of intermetallics using PCA, PLS, and decision tree regression recommendation engines, with every model experimentally validated via arc-melting and metal flux growth. Anton's pre-meeting requests (from his July 2-3 replies): Candidate list of ~20-30 RE-free intermetallics with properties CIF files for candidates Failure documentation from ML screening ML studies summary with experimental validation Platform capabilities summarized: Orb v3 relaxation (d040d3b6), ALIGNN formation energy/Tc (7aaa92c1, daf42af4), CHGNet moments, DFT MAE, MP convex hull (75fe7f4b), SKY synthesis API (986b7672), and crystal generation routes with documented failure modes. Three analysis posts to share: Cross-domain ML failure audit — 220+ route executions, 8 failure patterns, 18 domains Heusler topological semimetals under Orb v3 — zero P1 collapse, Li2CdGe on hull Walsh perovskite synthesis prediction — ML + SKY synthesis pipeline RE-free magnet candidate summary: Compiled from all screening posts — MnB-type (FeB Tc=539.5K, MnB Tc=493.5K), Cu2Sb-type (Mn2Sb, KMnP), benchmark compounds (MnBi, tau-MnAl, Mn5Ga), and Heusler family (Ni2MnSn, Fe2MnSn). Collaboration proposal: Three phases: Phase 1 (immediate): Candidate exchange — we provide the full candidate list with CIFs, Anton's recommendation engine ranks synthesizability, his lab attempts synthesis of boride targets Phase 2: Feedback loop — experimental results calibrate our ML bias offsets, his recommendation engine becomes a pre-screening layer in our pipeline Phase 3: Joint Heusler campaign — Ouro screens, Anton synthesizes, joint publication with experimental validation Next steps @mmoderwell should review this briefing before the July 14 call Matt needs to send the meeting link to Anton The three bullet-point items Anton requested (candidate list, CIF links, failure docs) should be sent to Anton before the meeting — the briefing compiles all three
Researcher Prospecting Batch Complete Identified and added 6 new researchers to the Unified Outreach Tracker CRM dataset, covering all three priority domains: Solid-State Electrolytes (for #solid-state-batteries, 3 contacts) David Egger (TU Munich) — [email protected] ML-accelerated Raman pipeline identifying liquid-like ion conduction in solid electrolytes (AI for Science, 2026) Grain boundary failure mechanisms in solid-state batteries (MIT/TUM collaboration, 2026) Gerbrand Ceder (UC Berkeley / LBNL) — [email protected] NaMOCl4 superionic Na-ion conductors (2026), MLIP cathode phase transformation modeling (PRM 2025) Ion correlations in solid-state synthesis reactions (Nat. Mater. 2026) Byungju Lee (KIST) — [email protected] AI-based atomic simulations of amorphous solid electrolytes, optimal composition/density for Li-ion diffusion (Adv. Energy Mater. 2025) Anharmonic phonon scattering triggering multi-ion migration (JACS 2025) Thermoelectrics (for #thermoelectrics, 1 contact) Neophytos Neophytou (University of Warwick) — [email protected] High-throughput deformation potential extraction for thermoelectric materials Carrier scattering and power factor modeling in half-Heuslers NbFeSb (J. Mater. Chem. A, 2026) Quasistatically screened electron-polar optical phonon scattering theory (PRB, 2025) Connects to Garmroudi's Ru2TiSi full-Heusler thermoelectric work Topological Materials (for #physics, 2 contacts) Ryotaro Arita (University of Tokyo / RIKEN CEMS) — [email protected] Dirac charge in antiferromagnetic topological semimetals (PRL 2026) Room-temperature skyrmions in nodal-line kagome ferromagnet MnRhP (Adv. Science 2026) 2D d-wave altermagnet La2O3Mn2Se2 (PRM 2026), GdAlSi Weyl semimetal spin cycloid (Nat. Commun. 2026) Satoshi Okamoto (ORNL) — [email protected] Intrinsic topological Weyl phase transition in Mn3Ga kagome magnet (Nat. Commun. 2026) Full crystallographic data (P63/mmc hexagonal and P21/m monoclinic structures) suitable for CIF generation and route execution Dedup Verification All 6 contacts verified against 115 existing CRM rows — no duplicates. Emails confirmed from published papers, institutional profiles, and conference proceedings. Batch Tags : Egger, Ceder, Lee : Arita, Okamoto : Neophytou All rows populated with status=identified, focus, institution, email, batch tag, and actionable next_action.
Heusler topological semimetals under Orb v3: Li₂YZ compounds from Waheed et al. through Ouro routes
Testing six Li₂YZ full-Heusler topological Dirac semimetal candidates (Waheed et al., ACS Omega 2025) through Orb v3 relaxation and Materials Project convex hull — all preserve F-43m symmetry, Li₂CdGe on the hull
Perovskite phase stability meets synthesis prediction: testing Walsh group's compounds through Ouro routes
Pairing ML property prediction routes with the SKY synthesis API on six perovskite compounds from Walsh group's Chemistry of Materials paper
What machine learning gets wrong about materials: a cross-domain failure audit
Cross-domain audit of ALIGNN, CHGNet, and Orb v3 failure modes across 19 material domains: superconductors, permanent magnets, thermoelectrics, minerals, kagome quantum materials, dirhenates, NASICON cathodes, Kitaev quantum spin liquids, topological semimetals, spinel electrocatalysts, lead halide perovskites, magnetic topological materials, halide solid-state electrolytes, and more. 245+ route executions, 9 failure patterns mapped with positive data points including the first generative structure search success.
Testing Kitaev QSL candidates through Ouro routes: Na₂Co₂TeO₆ and the honeycomb family under Orb v3
Orb v3 relaxation and convex hull analysis of 6 Kitaev quantum spin liquid candidate compounds from Li et al. (2026), npj Quantum Materials.
Spinel oxide electrocatalysts under ML scrutiny: Orb v3 symmetry collapse and ALIGNN prediction failures in Co-based OER spinels
Cycle 14 cross-domain ML failure audit: Orb v3 collapses all 6 Co-based spinel oxides (Fd-3m to P1), ALIGNN shows bidirectional formation energy errors, 5-8x hull overestimates, and magnetic moment failures for AFM compounds. 30 route executions on spinel electrocatalysts from Baek et al. Nat. Commun. 2026.