{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7SCM5HV3W3NEZY2VZGDOQYRAIL","short_pith_number":"pith:7SCM5HV3","schema_version":"1.0","canonical_sha256":"fc84ce9ebbb6da4ce355c986e8622042c853d0602d7901d37517eba3d6430a94","source":{"kind":"arxiv","id":"2403.03542","version":4},"attestation_state":"computed","paper":{"title":"DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Chang Su, Chengyang Ying, Hang Su, Jian Song, Julius Berner, Jun Zhu, Songming Liu, Zhongkai Hao","submitted_at":"2024-03-06T08:38:34Z","abstract_excerpt":"Pre-training has been investigated to improve the efficiency and performance of training neural operators in data-scarce settings. However, it is largely in its infancy due to the inherent complexity and diversity, such as long trajectories, multiple scales and varying dimensions of partial differential equations (PDEs) data. In this paper, we present a new auto-regressive denoising pre-training strategy, which allows for more stable and efficient pre-training on PDE data and generalizes to various downstream tasks. Moreover, by designing a flexible and scalable model architecture based on Fou"},"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":"2403.03542","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-06T08:38:34Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"ee78529f67634b7d96d61bffaf77e57ff83f4d78e273599275adeed9121a2447","abstract_canon_sha256":"89a342c6aa1557afc3660a7eb40b9a0a992b80f8844ab343ebaecc84ea6f0d6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:08.766544Z","signature_b64":"lEwvCzrGDu51cglwK/s+bro9PuxE7f8kyUgtzO3y0ZwjsUP4l7Wn20F7iteOpgIVOWCPMm5Xi+h2AhlNDEnyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc84ce9ebbb6da4ce355c986e8622042c853d0602d7901d37517eba3d6430a94","last_reissued_at":"2026-07-05T08:16:08.766093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:08.766093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Chang Su, Chengyang Ying, Hang Su, Jian Song, Julius Berner, Jun Zhu, Songming Liu, Zhongkai Hao","submitted_at":"2024-03-06T08:38:34Z","abstract_excerpt":"Pre-training has been investigated to improve the efficiency and performance of training neural operators in data-scarce settings. However, it is largely in its infancy due to the inherent complexity and diversity, such as long trajectories, multiple scales and varying dimensions of partial differential equations (PDEs) data. In this paper, we present a new auto-regressive denoising pre-training strategy, which allows for more stable and efficient pre-training on PDE data and generalizes to various downstream tasks. Moreover, by designing a flexible and scalable model architecture based on Fou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03542","kind":"arxiv","version":4},"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/2403.03542/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":"2403.03542","created_at":"2026-07-05T08:16:08.766142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03542v4","created_at":"2026-07-05T08:16:08.766142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03542","created_at":"2026-07-05T08:16:08.766142+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SCM5HV3W3NE","created_at":"2026-07-05T08:16:08.766142+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SCM5HV3W3NEZY2V","created_at":"2026-07-05T08:16:08.766142+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SCM5HV3","created_at":"2026-07-05T08:16:08.766142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12318","citing_title":"Harness In-Context Operator Learning with Chain of Operators","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10752","citing_title":"AutoPDE: Reliable Agentic PDE Solving via Explicitly Represented Solver Strategies","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31574","citing_title":"Temperature Field Reconstruction of Tungsten Monoblock Divertor on EAST using Physics-aware Neural Operator Transformer","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22222","citing_title":"ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22663","citing_title":"Therm-FM: Foundation Model is ALL YOU NEED for 3D-ICs Thermal Simulation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25949","citing_title":"Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22222","citing_title":"ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2502.01476","citing_title":"Neuro-Symbolic AI for Analytical Solutions of Differential Equations","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22222","citing_title":"ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22663","citing_title":"Therm-FM: Foundation Model is ALL YOU NEED for 3D-ICs Thermal Simulation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18611","citing_title":"Flow marching for a generative PDE foundation model","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11229","citing_title":"Latent Generative Solvers for Generalizable Long-Term Physics Simulation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04832","citing_title":"Replay-Based Continual Learning for Physics-Informed Neural Operators","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7SCM5HV3W3NEZY2VZGDOQYRAIL","json":"https://pith.science/pith/7SCM5HV3W3NEZY2VZGDOQYRAIL.json","graph_json":"https://pith.science/api/pith-number/7SCM5HV3W3NEZY2VZGDOQYRAIL/graph.json","events_json":"https://pith.science/api/pith-number/7SCM5HV3W3NEZY2VZGDOQYRAIL/events.json","paper":"https://pith.science/paper/7SCM5HV3"},"agent_actions":{"view_html":"https://pith.science/pith/7SCM5HV3W3NEZY2VZGDOQYRAIL","download_json":"https://pith.science/pith/7SCM5HV3W3NEZY2VZGDOQYRAIL.json","view_paper":"https://pith.science/paper/7SCM5HV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03542&json=true","fetch_graph":"https://pith.science/api/pith-number/7SCM5HV3W3NEZY2VZGDOQYRAIL/graph.json","fetch_events":"https://pith.science/api/pith-number/7SCM5HV3W3NEZY2VZGDOQYRAIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SCM5HV3W3NEZY2VZGDOQYRAIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SCM5HV3W3NEZY2VZGDOQYRAIL/action/storage_attestation","attest_author":"https://pith.science/pith/7SCM5HV3W3NEZY2VZGDOQYRAIL/action/author_attestation","sign_citation":"https://pith.science/pith/7SCM5HV3W3NEZY2VZGDOQYRAIL/action/citation_signature","submit_replication":"https://pith.science/pith/7SCM5HV3W3NEZY2VZGDOQYRAIL/action/replication_record"}},"created_at":"2026-07-05T08:16:08.766142+00:00","updated_at":"2026-07-05T08:16:08.766142+00:00"}