{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DEKZEUJN6DUYJ4IMGBQYRHBCZJ","short_pith_number":"pith:DEKZEUJN","schema_version":"1.0","canonical_sha256":"191592512df0e984f10c3061889c22ca6ddae1ad1360245b728ce04fc7beb666","source":{"kind":"arxiv","id":"2606.31660","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Regularization of Machine Learning Potentials","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"physics.chem-ph","authors_text":"Alberto Rosso, Dimitrios Tzivrailis, Eiji Kawasaki, Georgios Sotiropoulos","submitted_at":"2026-06-30T13:39:50Z","abstract_excerpt":"Machine learning interatomic potentials are trained to predict energies and forces but built to be sampled: their purpose is to drive molecular simulations whose observables average over the equilibrium distribution the potential defines. They exemplify a broader AI problem -- learned regressors deployed as generators -- where pointwise accuracy does not guarantee a correct distribution. We show that potentials trained by standard Mean Squared Error (MSE) minimization on Density Functional Theory (DFT) data can reach chemical accuracy on held-out data, yet still fail as samplers: their traject"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.31660","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2026-06-30T13:39:50Z","cross_cats_sorted":["cond-mat.mtrl-sci"],"title_canon_sha256":"6bf1d770582adc355c551c7f27ab8b3f3d1214d0dfc374fb311726b61d1d241a","abstract_canon_sha256":"05d68627fd3565dc6928f5c027e2e763c820797a7b5a0ee413268fe98849b14f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:10.905561Z","signature_b64":"/ouAe4mTmQwPi521dWMTWD+HKIYKOnclbId5G0Silp+GmlAvDOTNKA1K8Agesb2VkNT1ZA/+9BKOqe5S5yUFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"191592512df0e984f10c3061889c22ca6ddae1ad1360245b728ce04fc7beb666","last_reissued_at":"2026-07-01T01:18:10.905077Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:10.905077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Regularization of Machine Learning Potentials","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"physics.chem-ph","authors_text":"Alberto Rosso, Dimitrios Tzivrailis, Eiji Kawasaki, Georgios Sotiropoulos","submitted_at":"2026-06-30T13:39:50Z","abstract_excerpt":"Machine learning interatomic potentials are trained to predict energies and forces but built to be sampled: their purpose is to drive molecular simulations whose observables average over the equilibrium distribution the potential defines. They exemplify a broader AI problem -- learned regressors deployed as generators -- where pointwise accuracy does not guarantee a correct distribution. We show that potentials trained by standard Mean Squared Error (MSE) minimization on Density Functional Theory (DFT) data can reach chemical accuracy on held-out data, yet still fail as samplers: their traject"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31660","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.31660/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.31660","created_at":"2026-07-01T01:18:10.905148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31660v1","created_at":"2026-07-01T01:18:10.905148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31660","created_at":"2026-07-01T01:18:10.905148+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEKZEUJN6DUY","created_at":"2026-07-01T01:18:10.905148+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEKZEUJN6DUYJ4IM","created_at":"2026-07-01T01:18:10.905148+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEKZEUJN","created_at":"2026-07-01T01:18:10.905148+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DEKZEUJN6DUYJ4IMGBQYRHBCZJ","json":"https://pith.science/pith/DEKZEUJN6DUYJ4IMGBQYRHBCZJ.json","graph_json":"https://pith.science/api/pith-number/DEKZEUJN6DUYJ4IMGBQYRHBCZJ/graph.json","events_json":"https://pith.science/api/pith-number/DEKZEUJN6DUYJ4IMGBQYRHBCZJ/events.json","paper":"https://pith.science/paper/DEKZEUJN"},"agent_actions":{"view_html":"https://pith.science/pith/DEKZEUJN6DUYJ4IMGBQYRHBCZJ","download_json":"https://pith.science/pith/DEKZEUJN6DUYJ4IMGBQYRHBCZJ.json","view_paper":"https://pith.science/paper/DEKZEUJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31660&json=true","fetch_graph":"https://pith.science/api/pith-number/DEKZEUJN6DUYJ4IMGBQYRHBCZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DEKZEUJN6DUYJ4IMGBQYRHBCZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEKZEUJN6DUYJ4IMGBQYRHBCZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEKZEUJN6DUYJ4IMGBQYRHBCZJ/action/storage_attestation","attest_author":"https://pith.science/pith/DEKZEUJN6DUYJ4IMGBQYRHBCZJ/action/author_attestation","sign_citation":"https://pith.science/pith/DEKZEUJN6DUYJ4IMGBQYRHBCZJ/action/citation_signature","submit_replication":"https://pith.science/pith/DEKZEUJN6DUYJ4IMGBQYRHBCZJ/action/replication_record"}},"created_at":"2026-07-01T01:18:10.905148+00:00","updated_at":"2026-07-01T01:18:10.905148+00:00"}