{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FSEP7FSJK3DMX7JRXKJZMU5SCT","short_pith_number":"pith:FSEP7FSJ","schema_version":"1.0","canonical_sha256":"2c88ff964956c6cbfd31ba939653b214e067ecc0a7bfa1f44354703ad3ee6fe3","source":{"kind":"arxiv","id":"2202.09340","version":2},"attestation_state":"computed","paper":{"title":"Learning Physics-Informed Neural Networks without Stacked Back-propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Di He, Jiang Bian, Jia Zhang, Liwei Wang, Shanda Li, Tie-Yan Liu, Wenlei Shi, Xiaotian Gao","submitted_at":"2022-02-18T18:07:54Z","abstract_excerpt":"Physics-Informed Neural Network (PINN) has become a commonly used machine learning approach to solve partial differential equations (PDE). But, facing high-dimensional secondorder PDE problems, PINN will suffer from severe scalability issues since its loss includes second-order derivatives, the computational cost of which will grow along with the dimension during stacked back-propagation. In this work, we develop a novel approach that can significantly accelerate the training of Physics-Informed Neural Networks. In particular, we parameterize the PDE solution by the Gaussian smoothed model and"},"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":"2202.09340","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-18T18:07:54Z","cross_cats_sorted":[],"title_canon_sha256":"aab0e832fc5395ea2475a0fd509fac6ed4092e1f4078f051b2f9ee9c2730208f","abstract_canon_sha256":"51af776a4a16ffad9baabb61757a88615b406f6c50877ad8a0bef94c33e9d31c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:17.057664Z","signature_b64":"iIX29bBIerKBoi1U9/IBg5/eP4nNwOZRWOjjmhOAnlHEWRumtBtvtFCCtVAqw0PEPzeVKJj+9vTpJsT0A9y7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c88ff964956c6cbfd31ba939653b214e067ecc0a7bfa1f44354703ad3ee6fe3","last_reissued_at":"2026-07-05T05:45:17.057150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:17.057150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Physics-Informed Neural Networks without Stacked Back-propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Di He, Jiang Bian, Jia Zhang, Liwei Wang, Shanda Li, Tie-Yan Liu, Wenlei Shi, Xiaotian Gao","submitted_at":"2022-02-18T18:07:54Z","abstract_excerpt":"Physics-Informed Neural Network (PINN) has become a commonly used machine learning approach to solve partial differential equations (PDE). But, facing high-dimensional secondorder PDE problems, PINN will suffer from severe scalability issues since its loss includes second-order derivatives, the computational cost of which will grow along with the dimension during stacked back-propagation. In this work, we develop a novel approach that can significantly accelerate the training of Physics-Informed Neural Networks. In particular, we parameterize the PDE solution by the Gaussian smoothed model and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09340","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/2202.09340/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":"2202.09340","created_at":"2026-07-05T05:45:17.057209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.09340v2","created_at":"2026-07-05T05:45:17.057209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09340","created_at":"2026-07-05T05:45:17.057209+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSEP7FSJK3DM","created_at":"2026-07-05T05:45:17.057209+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSEP7FSJK3DMX7JR","created_at":"2026-07-05T05:45:17.057209+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSEP7FSJ","created_at":"2026-07-05T05:45:17.057209+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/FSEP7FSJK3DMX7JRXKJZMU5SCT","json":"https://pith.science/pith/FSEP7FSJK3DMX7JRXKJZMU5SCT.json","graph_json":"https://pith.science/api/pith-number/FSEP7FSJK3DMX7JRXKJZMU5SCT/graph.json","events_json":"https://pith.science/api/pith-number/FSEP7FSJK3DMX7JRXKJZMU5SCT/events.json","paper":"https://pith.science/paper/FSEP7FSJ"},"agent_actions":{"view_html":"https://pith.science/pith/FSEP7FSJK3DMX7JRXKJZMU5SCT","download_json":"https://pith.science/pith/FSEP7FSJK3DMX7JRXKJZMU5SCT.json","view_paper":"https://pith.science/paper/FSEP7FSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.09340&json=true","fetch_graph":"https://pith.science/api/pith-number/FSEP7FSJK3DMX7JRXKJZMU5SCT/graph.json","fetch_events":"https://pith.science/api/pith-number/FSEP7FSJK3DMX7JRXKJZMU5SCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSEP7FSJK3DMX7JRXKJZMU5SCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSEP7FSJK3DMX7JRXKJZMU5SCT/action/storage_attestation","attest_author":"https://pith.science/pith/FSEP7FSJK3DMX7JRXKJZMU5SCT/action/author_attestation","sign_citation":"https://pith.science/pith/FSEP7FSJK3DMX7JRXKJZMU5SCT/action/citation_signature","submit_replication":"https://pith.science/pith/FSEP7FSJK3DMX7JRXKJZMU5SCT/action/replication_record"}},"created_at":"2026-07-05T05:45:17.057209+00:00","updated_at":"2026-07-05T05:45:17.057209+00:00"}