{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:THBYSEWLMHKDHXHB5VJ3OVJTT4","short_pith_number":"pith:THBYSEWL","schema_version":"1.0","canonical_sha256":"99c38912cb61d433dce1ed53b755339f3051a2068db32b579695c41985dcb897","source":{"kind":"arxiv","id":"2608.11937","version":1},"attestation_state":"computed","paper":{"title":"Distillation of Foundation Models for Time-dependent PDEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrei Manolache, Boshra Ariguib, Daniel Musekamp, Mathias Niepert","submitted_at":"2026-08-12T11:24:08Z","abstract_excerpt":"Foundation models for time-dependent partial differential equations (PDEs) are trained on large and diverse collections of physical systems and can generalize effectively to new downstream tasks. After fine-tuning on only a few trajectories from a target domain, they can achieve strong accuracy in low-data regimes. However, these models are typically large and computationally intensive, limiting their usefulness as fast surrogates for numerical solvers. We propose Teacher Rollout Extension (TREX), a knowledge distillation framework that transfers the predictive capability of a pretrained found"},"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":"2608.11937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T11:24:08Z","cross_cats_sorted":[],"title_canon_sha256":"c18cf6f68b0144c311b62d696fa0b7a39939dd754d157a4a88363537e49e9385","abstract_canon_sha256":"813e7222341e3b13ad78f985665e7a1ecad3f862a5b99043a908862f4fa8f9dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:28:59.987455Z","signature_b64":"OijtwuOmjV4MnYV2rFUcPOEOP4Ueef34LVa/KsDtJYneIrbwlHdX79s+R19wyldTmWrLc3oSCmkKKcbVE/8cDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99c38912cb61d433dce1ed53b755339f3051a2068db32b579695c41985dcb897","last_reissued_at":"2026-08-13T01:28:59.985228Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:28:59.985228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distillation of Foundation Models for Time-dependent PDEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrei Manolache, Boshra Ariguib, Daniel Musekamp, Mathias Niepert","submitted_at":"2026-08-12T11:24:08Z","abstract_excerpt":"Foundation models for time-dependent partial differential equations (PDEs) are trained on large and diverse collections of physical systems and can generalize effectively to new downstream tasks. After fine-tuning on only a few trajectories from a target domain, they can achieve strong accuracy in low-data regimes. However, these models are typically large and computationally intensive, limiting their usefulness as fast surrogates for numerical solvers. We propose Teacher Rollout Extension (TREX), a knowledge distillation framework that transfers the predictive capability of a pretrained found"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11937","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/2608.11937/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":"2608.11937","created_at":"2026-08-13T01:28:59.986364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11937v1","created_at":"2026-08-13T01:28:59.986364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11937","created_at":"2026-08-13T01:28:59.986364+00:00"},{"alias_kind":"pith_short_12","alias_value":"THBYSEWLMHKD","created_at":"2026-08-13T01:28:59.986364+00:00"},{"alias_kind":"pith_short_16","alias_value":"THBYSEWLMHKDHXHB","created_at":"2026-08-13T01:28:59.986364+00:00"},{"alias_kind":"pith_short_8","alias_value":"THBYSEWL","created_at":"2026-08-13T01:28:59.986364+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/THBYSEWLMHKDHXHB5VJ3OVJTT4","json":"https://pith.science/pith/THBYSEWLMHKDHXHB5VJ3OVJTT4.json","graph_json":"https://pith.science/api/pith-number/THBYSEWLMHKDHXHB5VJ3OVJTT4/graph.json","events_json":"https://pith.science/api/pith-number/THBYSEWLMHKDHXHB5VJ3OVJTT4/events.json","paper":"https://pith.science/paper/THBYSEWL"},"agent_actions":{"view_html":"https://pith.science/pith/THBYSEWLMHKDHXHB5VJ3OVJTT4","download_json":"https://pith.science/pith/THBYSEWLMHKDHXHB5VJ3OVJTT4.json","view_paper":"https://pith.science/paper/THBYSEWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11937&json=true","fetch_graph":"https://pith.science/api/pith-number/THBYSEWLMHKDHXHB5VJ3OVJTT4/graph.json","fetch_events":"https://pith.science/api/pith-number/THBYSEWLMHKDHXHB5VJ3OVJTT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/THBYSEWLMHKDHXHB5VJ3OVJTT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/THBYSEWLMHKDHXHB5VJ3OVJTT4/action/storage_attestation","attest_author":"https://pith.science/pith/THBYSEWLMHKDHXHB5VJ3OVJTT4/action/author_attestation","sign_citation":"https://pith.science/pith/THBYSEWLMHKDHXHB5VJ3OVJTT4/action/citation_signature","submit_replication":"https://pith.science/pith/THBYSEWLMHKDHXHB5VJ3OVJTT4/action/replication_record"}},"created_at":"2026-08-13T01:28:59.986364+00:00","updated_at":"2026-08-13T01:28:59.986364+00:00"}