{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X3OLXMVJ4M573ND6AKR7ALSRIC","short_pith_number":"pith:X3OLXMVJ","schema_version":"1.0","canonical_sha256":"bedcbbb2a9e33bfdb47e02a3f02e514091187e71aa4af9dbda4f5cf5160f6393","source":{"kind":"arxiv","id":"2301.11701","version":1},"attestation_state":"computed","paper":{"title":"TransNet: Transferable Neural Networks for Partial Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Feng Bao, Guannan Zhang, Lili Ju, Zezhong Zhang","submitted_at":"2023-01-27T13:26:25Z","abstract_excerpt":"Transfer learning for partial differential equations (PDEs) is to develop a pre-trained neural network that can be used to solve a wide class of PDEs. Existing transfer learning approaches require much information of the target PDEs such as its formulation and/or data of its solution for pre-training. In this work, we propose to construct transferable neural feature spaces from purely function approximation perspectives without using PDE information. The construction of the feature space involves re-parameterization of the hidden neurons and uses auxiliary functions to tune the resulting featu"},"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":"2301.11701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2023-01-27T13:26:25Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"77119c5651432204484624ccd185a0499654c4430963c7a40910cf813c74936a","abstract_canon_sha256":"32197632acfd61effea855580420501948446077680ce85be3011bee1e9419df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:25.321061Z","signature_b64":"RbVfKvAnE2IedyEfSWJltVNPtPcPny7F+iKCMpruFLDEo7OHCKQP0oYmIiBaD2NrHbCYwd7reqnge70rTLNqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bedcbbb2a9e33bfdb47e02a3f02e514091187e71aa4af9dbda4f5cf5160f6393","last_reissued_at":"2026-07-05T05:36:25.320583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:25.320583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TransNet: Transferable Neural Networks for Partial Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Feng Bao, Guannan Zhang, Lili Ju, Zezhong Zhang","submitted_at":"2023-01-27T13:26:25Z","abstract_excerpt":"Transfer learning for partial differential equations (PDEs) is to develop a pre-trained neural network that can be used to solve a wide class of PDEs. Existing transfer learning approaches require much information of the target PDEs such as its formulation and/or data of its solution for pre-training. In this work, we propose to construct transferable neural feature spaces from purely function approximation perspectives without using PDE information. The construction of the feature space involves re-parameterization of the hidden neurons and uses auxiliary functions to tune the resulting featu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11701","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/2301.11701/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":"2301.11701","created_at":"2026-07-05T05:36:25.320641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.11701v1","created_at":"2026-07-05T05:36:25.320641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11701","created_at":"2026-07-05T05:36:25.320641+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3OLXMVJ4M57","created_at":"2026-07-05T05:36:25.320641+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3OLXMVJ4M573ND6","created_at":"2026-07-05T05:36:25.320641+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3OLXMVJ","created_at":"2026-07-05T05:36:25.320641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.17776","citing_title":"Solving and learning advective multiscale Darcian dynamics with the Neural Basis Method","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X3OLXMVJ4M573ND6AKR7ALSRIC","json":"https://pith.science/pith/X3OLXMVJ4M573ND6AKR7ALSRIC.json","graph_json":"https://pith.science/api/pith-number/X3OLXMVJ4M573ND6AKR7ALSRIC/graph.json","events_json":"https://pith.science/api/pith-number/X3OLXMVJ4M573ND6AKR7ALSRIC/events.json","paper":"https://pith.science/paper/X3OLXMVJ"},"agent_actions":{"view_html":"https://pith.science/pith/X3OLXMVJ4M573ND6AKR7ALSRIC","download_json":"https://pith.science/pith/X3OLXMVJ4M573ND6AKR7ALSRIC.json","view_paper":"https://pith.science/paper/X3OLXMVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.11701&json=true","fetch_graph":"https://pith.science/api/pith-number/X3OLXMVJ4M573ND6AKR7ALSRIC/graph.json","fetch_events":"https://pith.science/api/pith-number/X3OLXMVJ4M573ND6AKR7ALSRIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3OLXMVJ4M573ND6AKR7ALSRIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3OLXMVJ4M573ND6AKR7ALSRIC/action/storage_attestation","attest_author":"https://pith.science/pith/X3OLXMVJ4M573ND6AKR7ALSRIC/action/author_attestation","sign_citation":"https://pith.science/pith/X3OLXMVJ4M573ND6AKR7ALSRIC/action/citation_signature","submit_replication":"https://pith.science/pith/X3OLXMVJ4M573ND6AKR7ALSRIC/action/replication_record"}},"created_at":"2026-07-05T05:36:25.320641+00:00","updated_at":"2026-07-05T05:36:25.320641+00:00"}