{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SS4EM4JNWRLUXDCYOYNSD5G3R4","short_pith_number":"pith:SS4EM4JN","schema_version":"1.0","canonical_sha256":"94b846712db4574b8c58761b21f4db8f002dfe49a82ea0eac2f2e7c8b68ef54b","source":{"kind":"arxiv","id":"2605.29283","version":1},"attestation_state":"computed","paper":{"title":"Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ayan Biswas, Han-Wei Shen, Mengdi Chu, Yang Liu","submitted_at":"2026-05-28T03:08:57Z","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"},"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":"2605.29283","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T03:08:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ac76c8ba7d5909af27af4ee4bdd38ce2039c6f42d451272062600b85538bbf8b","abstract_canon_sha256":"d45e95e4a8cfa3f8e7acec49ef298861ac92259616aade8ed66c4d32c7f02e81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:29.352714Z","signature_b64":"6lOtE5TIUtlaRsoLuTWSCnY4zsbqwKUSxJVaAjnbatdvMwRTs9sX9W3qqCISx0CHlHDbzhiFdTjj9UBn/9TnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94b846712db4574b8c58761b21f4db8f002dfe49a82ea0eac2f2e7c8b68ef54b","last_reissued_at":"2026-05-29T01:05:29.351878Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:29.351878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ayan Biswas, Han-Wei Shen, Mengdi Chu, Yang Liu","submitted_at":"2026-05-28T03:08:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29283","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/2605.29283/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":"2605.29283","created_at":"2026-05-29T01:05:29.352019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29283v1","created_at":"2026-05-29T01:05:29.352019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29283","created_at":"2026-05-29T01:05:29.352019+00:00"},{"alias_kind":"pith_short_12","alias_value":"SS4EM4JNWRLU","created_at":"2026-05-29T01:05:29.352019+00:00"},{"alias_kind":"pith_short_16","alias_value":"SS4EM4JNWRLUXDCY","created_at":"2026-05-29T01:05:29.352019+00:00"},{"alias_kind":"pith_short_8","alias_value":"SS4EM4JN","created_at":"2026-05-29T01:05:29.352019+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/SS4EM4JNWRLUXDCYOYNSD5G3R4","json":"https://pith.science/pith/SS4EM4JNWRLUXDCYOYNSD5G3R4.json","graph_json":"https://pith.science/api/pith-number/SS4EM4JNWRLUXDCYOYNSD5G3R4/graph.json","events_json":"https://pith.science/api/pith-number/SS4EM4JNWRLUXDCYOYNSD5G3R4/events.json","paper":"https://pith.science/paper/SS4EM4JN"},"agent_actions":{"view_html":"https://pith.science/pith/SS4EM4JNWRLUXDCYOYNSD5G3R4","download_json":"https://pith.science/pith/SS4EM4JNWRLUXDCYOYNSD5G3R4.json","view_paper":"https://pith.science/paper/SS4EM4JN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29283&json=true","fetch_graph":"https://pith.science/api/pith-number/SS4EM4JNWRLUXDCYOYNSD5G3R4/graph.json","fetch_events":"https://pith.science/api/pith-number/SS4EM4JNWRLUXDCYOYNSD5G3R4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SS4EM4JNWRLUXDCYOYNSD5G3R4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SS4EM4JNWRLUXDCYOYNSD5G3R4/action/storage_attestation","attest_author":"https://pith.science/pith/SS4EM4JNWRLUXDCYOYNSD5G3R4/action/author_attestation","sign_citation":"https://pith.science/pith/SS4EM4JNWRLUXDCYOYNSD5G3R4/action/citation_signature","submit_replication":"https://pith.science/pith/SS4EM4JNWRLUXDCYOYNSD5G3R4/action/replication_record"}},"created_at":"2026-05-29T01:05:29.352019+00:00","updated_at":"2026-05-29T01:05:29.352019+00:00"}