{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SS4EM4JNWRLUXDCYOYNSD5G3R4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d45e95e4a8cfa3f8e7acec49ef298861ac92259616aade8ed66c4d32c7f02e81","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T03:08:57Z","title_canon_sha256":"ac76c8ba7d5909af27af4ee4bdd38ce2039c6f42d451272062600b85538bbf8b"},"schema_version":"1.0","source":{"id":"2605.29283","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29283","created_at":"2026-05-29T01:05:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29283v1","created_at":"2026-05-29T01:05:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29283","created_at":"2026-05-29T01:05:29Z"},{"alias_kind":"pith_short_12","alias_value":"SS4EM4JNWRLU","created_at":"2026-05-29T01:05:29Z"},{"alias_kind":"pith_short_16","alias_value":"SS4EM4JNWRLUXDCY","created_at":"2026-05-29T01:05:29Z"},{"alias_kind":"pith_short_8","alias_value":"SS4EM4JN","created_at":"2026-05-29T01:05:29Z"}],"graph_snapshots":[{"event_id":"sha256:2c9a7644c3727efa45cbceb1ae7fe47888e98f7005c5f5f6e6a119851f3df82c","target":"graph","created_at":"2026-05-29T01:05:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.29283/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent physics foundation models claim general spatiotemporal forecasting ability, yet their evaluations often collapse performance into a single average score under a fixed training distribution. This makes it difficult to determine whether a model has learned generalizable physical dynamics or only performs well under particular settings. We construct a benchmark with 8 physical dynamics, 3 training-data mixtures, and 25 test regimes induced by dynamic-scale and initial-condition complexity shifts, covering in-distribution, distribution-shift, and out-of-distribution settings. We evaluate fi","authors_text":"Ayan Biswas, Han-Wei Shen, Mengdi Chu, Yang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T03:08:57Z","title":"Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29283","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6410aa8641614145043ae8dd917b04e2eb2186344036d56657c0aa9f8bd8330e","target":"record","created_at":"2026-05-29T01:05:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d45e95e4a8cfa3f8e7acec49ef298861ac92259616aade8ed66c4d32c7f02e81","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T03:08:57Z","title_canon_sha256":"ac76c8ba7d5909af27af4ee4bdd38ce2039c6f42d451272062600b85538bbf8b"},"schema_version":"1.0","source":{"id":"2605.29283","kind":"arxiv","version":1}},"canonical_sha256":"94b846712db4574b8c58761b21f4db8f002dfe49a82ea0eac2f2e7c8b68ef54b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94b846712db4574b8c58761b21f4db8f002dfe49a82ea0eac2f2e7c8b68ef54b","first_computed_at":"2026-05-29T01:05:29.351878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:29.351878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6lOtE5TIUtlaRsoLuTWSCnY4zsbqwKUSxJVaAjnbatdvMwRTs9sX9W3qqCISx0CHlHDbzhiFdTjj9UBn/9TnBQ==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:29.352714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29283","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6410aa8641614145043ae8dd917b04e2eb2186344036d56657c0aa9f8bd8330e","sha256:2c9a7644c3727efa45cbceb1ae7fe47888e98f7005c5f5f6e6a119851f3df82c"],"state_sha256":"ef98af8a739d7f4ffb3597b7fb2faafe19b550e3b4484a1e8051e9c1762762ab"}