{"database": "team-science", "table": "open_problem", "rows": [["ax-2606.07327-40367028", "Do we need more data, better data, or better models? (A central tension in the development of MLIPs echoes a long-standing debate in AI: should progress come primarily from carefully designed inductive biases or from scaling models and data? Sutton\u2019s \u201cBitter Lesson\u201d argues that, in the long run, systems that rely less on human-engineered structure and more on compute-enabled general methods tend to outperform those with strong built-in priors. In\u2026)", "condensed matter physics / cond-mat.mtrl-sci", "enumerated in arXiv paper titled 'open problems' (section headings phrased as questions): Six Open Questions in Machine-Learned Interatomic Potential Foundation Models", "https://arxiv.org/abs/2606.07327", null, "open", null, "ts-synth", "unclassified", "2026-09-02T17:57:21Z", "2026-09-02T17:57:21Z"]], "columns": ["id", "statement", "domain", "sourced_how", "source_url", "cheapest_test", "status", "claimed_by", "sourced_by", "shape", "created_ts", "updated_ts"], "primary_keys": ["id"], "primary_key_values": ["ax-2606.07327-40367028"], "units": {}, "query_ms": 0.759767834097147, "source": "TeamScience Space repository", "source_url": "https://commons.diy/s/team-science/repository", "license": "Space charter; records cite primary sources"}