{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CLQO62CMUW6IMUXMWNXCPT6ALT","short_pith_number":"pith:CLQO62CM","schema_version":"1.0","canonical_sha256":"12e0ef684ca5bc8652ecb36e27cfc05ce2c5f1d25464d395a22647739c3af63c","source":{"kind":"arxiv","id":"2408.16168","version":2},"attestation_state":"computed","paper":{"title":"LeMON: Learning to Learn Multi-Operator Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hayden Schaeffer, Jingmin Sun, Zecheng Zhang","submitted_at":"2024-08-28T23:20:03Z","abstract_excerpt":"Single-operator learning involves training a deep neural network to learn a specific operator, whereas recent work in multi-operator learning uses an operator embedding structure to train a single neural network on data from multiple operators. Thus, multi-operator learning is capable of predicting a range of operators within one model. In this work, we propose pretraining and fine-tuning strategies for solving PDEs using multi-operator learning. One key aspect is that by increasing the number of families of operators used in pretraining, a PDE foundation model can be fine-tuned to downstream "},"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":"2408.16168","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-28T23:20:03Z","cross_cats_sorted":[],"title_canon_sha256":"d170ef54a84cfeb9bd4453bec257350ca868c4b7ec8a3d3bb83c522879329e40","abstract_canon_sha256":"b42349d872bfe7f5ac03dec4b408db4b81a82fb7cb7685af673e151672037b27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:45.984734Z","signature_b64":"ZkSU41DuW79O4VTkE0HCAl+zmhRUoLXNv/dwefvG6sNVDzFT5Z4lUtqM/T18nt1j17aGgY9xe7Ysnf8obVTpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12e0ef684ca5bc8652ecb36e27cfc05ce2c5f1d25464d395a22647739c3af63c","last_reissued_at":"2026-07-05T11:20:45.984232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:45.984232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LeMON: Learning to Learn Multi-Operator Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hayden Schaeffer, Jingmin Sun, Zecheng Zhang","submitted_at":"2024-08-28T23:20:03Z","abstract_excerpt":"Single-operator learning involves training a deep neural network to learn a specific operator, whereas recent work in multi-operator learning uses an operator embedding structure to train a single neural network on data from multiple operators. Thus, multi-operator learning is capable of predicting a range of operators within one model. In this work, we propose pretraining and fine-tuning strategies for solving PDEs using multi-operator learning. One key aspect is that by increasing the number of families of operators used in pretraining, a PDE foundation model can be fine-tuned to downstream "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16168","kind":"arxiv","version":2},"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/2408.16168/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":"2408.16168","created_at":"2026-07-05T11:20:45.984291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.16168v2","created_at":"2026-07-05T11:20:45.984291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16168","created_at":"2026-07-05T11:20:45.984291+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLQO62CMUW6I","created_at":"2026-07-05T11:20:45.984291+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLQO62CMUW6IMUXM","created_at":"2026-07-05T11:20:45.984291+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLQO62CM","created_at":"2026-07-05T11:20:45.984291+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12318","citing_title":"Harness In-Context Operator Learning with Chain of Operators","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2510.00233","citing_title":"Differentiable Autoencoding Neural Operator for Interpretable and Integrable Latent Space Modeling","ref_index":93,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLQO62CMUW6IMUXMWNXCPT6ALT","json":"https://pith.science/pith/CLQO62CMUW6IMUXMWNXCPT6ALT.json","graph_json":"https://pith.science/api/pith-number/CLQO62CMUW6IMUXMWNXCPT6ALT/graph.json","events_json":"https://pith.science/api/pith-number/CLQO62CMUW6IMUXMWNXCPT6ALT/events.json","paper":"https://pith.science/paper/CLQO62CM"},"agent_actions":{"view_html":"https://pith.science/pith/CLQO62CMUW6IMUXMWNXCPT6ALT","download_json":"https://pith.science/pith/CLQO62CMUW6IMUXMWNXCPT6ALT.json","view_paper":"https://pith.science/paper/CLQO62CM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.16168&json=true","fetch_graph":"https://pith.science/api/pith-number/CLQO62CMUW6IMUXMWNXCPT6ALT/graph.json","fetch_events":"https://pith.science/api/pith-number/CLQO62CMUW6IMUXMWNXCPT6ALT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLQO62CMUW6IMUXMWNXCPT6ALT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLQO62CMUW6IMUXMWNXCPT6ALT/action/storage_attestation","attest_author":"https://pith.science/pith/CLQO62CMUW6IMUXMWNXCPT6ALT/action/author_attestation","sign_citation":"https://pith.science/pith/CLQO62CMUW6IMUXMWNXCPT6ALT/action/citation_signature","submit_replication":"https://pith.science/pith/CLQO62CMUW6IMUXMWNXCPT6ALT/action/replication_record"}},"created_at":"2026-07-05T11:20:45.984291+00:00","updated_at":"2026-07-05T11:20:45.984291+00:00"}