{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CZH7SXLTQN6O5H3SDQE3SQASQ3","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":"9fb3a984276c599ec0f87f6d4a7616adf76d11638de1866edacd8d6c5f5cc7a2","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T00:32:59Z","title_canon_sha256":"e3f4444b52e573f983f54a17dd601f4dd3b52aec0c5d2e5f9a39db3283a1f249"},"schema_version":"1.0","source":{"id":"2306.00258","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00258","created_at":"2026-07-05T07:30:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00258v1","created_at":"2026-07-05T07:30:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00258","created_at":"2026-07-05T07:30:03Z"},{"alias_kind":"pith_short_12","alias_value":"CZH7SXLTQN6O","created_at":"2026-07-05T07:30:03Z"},{"alias_kind":"pith_short_16","alias_value":"CZH7SXLTQN6O5H3S","created_at":"2026-07-05T07:30:03Z"},{"alias_kind":"pith_short_8","alias_value":"CZH7SXLT","created_at":"2026-07-05T07:30:03Z"}],"graph_snapshots":[{"event_id":"sha256:ddfaa68039ac92d073ebf80b8791e01549b14c99defef29943574c7ab1f34858","target":"graph","created_at":"2026-07-05T07:30:03Z","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/2306.00258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained machine learning (ML) models have shown great performance for a wide range of applications, in particular in natural language processing (NLP) and computer vision (CV). Here, we study how pre-training could be used for scientific machine learning (SciML) applications, specifically in the context of transfer learning. We study the transfer behavior of these models as (i) the pre-trained model size is scaled, (ii) the downstream training dataset size is scaled, (iii) the physics parameters are systematically pushed out of distribution, and (iv) how a single model pre-trained on a mix","authors_text":"Amir Gholami, Dmitriy Morozov, Kurt Keutzer, Michael Mahoney, Peter Harrington, Shashank Subramanian, Wahid Bhimji","cross_cats":["cs.NA","math.NA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T00:32:59Z","title":"Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00258","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:e1b140644ad4addf46be996b11120ee8a189731cf5c68a37994ef05d1a015c39","target":"record","created_at":"2026-07-05T07:30:03Z","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":"9fb3a984276c599ec0f87f6d4a7616adf76d11638de1866edacd8d6c5f5cc7a2","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T00:32:59Z","title_canon_sha256":"e3f4444b52e573f983f54a17dd601f4dd3b52aec0c5d2e5f9a39db3283a1f249"},"schema_version":"1.0","source":{"id":"2306.00258","kind":"arxiv","version":1}},"canonical_sha256":"164ff95d73837cee9f721c09b9401286ff98e39b1885d5a2bfc0a572b7dc70fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"164ff95d73837cee9f721c09b9401286ff98e39b1885d5a2bfc0a572b7dc70fc","first_computed_at":"2026-07-05T07:30:03.047089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:03.047089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gXW322gkt2grwZIMeH0ETAuDnytiX5228Nq3MrkB7vAH3R3YysbsLT6hSf/fmUPTvEpNkCyyr2ERFd/WoCTjDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:03.047551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00258","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1b140644ad4addf46be996b11120ee8a189731cf5c68a37994ef05d1a015c39","sha256:ddfaa68039ac92d073ebf80b8791e01549b14c99defef29943574c7ab1f34858"],"state_sha256":"2fc61f0d64793d22714fd6e6f710b2781d26299757380e632755e74a5eb5832f"}