{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SRM4L7VVG4QKIVZUEBQRRWAJFO","short_pith_number":"pith:SRM4L7VV","schema_version":"1.0","canonical_sha256":"9459c5feb53720a45734206118d8092ba8bf383142f3499bd10bedd4dfca0a76","source":{"kind":"arxiv","id":"2606.00643","version":1},"attestation_state":"computed","paper":{"title":"Taming the Loss Landscape of PINNs with Noisy Feynman-Kac Supervision: Operator Preconditioning and Non-Asymptotic Error Bounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Chengyu Liu, Hanyu Hu, Nathanael Tepakbong, Xiang Zhou","submitted_at":"2026-05-30T09:38:48Z","abstract_excerpt":"Physics-Informed Neural Networks (PINNs) often train slowly or fail to converge on challenging partial differential equations (PDEs), a behavior recently linked to severely ill-conditioned loss landscapes inherited from the underlying differential operator. We study PINNs augmented with a pointwise data-fidelity term, added at a few points in the domain to the standard residual and boundary losses. We show that this supervision term acts as an operator-level preconditioner: for suitable weights, our comparison bounds guarantee a substantially smaller condition number than under the standard PI"},"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":"2606.00643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-30T09:38:48Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","math.OC","math.ST","stat.TH"],"title_canon_sha256":"650181d4d1c3725c46c02661ca6ab8f9f1fed5973d7370621ac12c11e7ec53f9","abstract_canon_sha256":"3fefa871d746083d009b7c0245c9d25e58066ba36830a43f16c21d83e5f6a806"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:00.727019Z","signature_b64":"H5/tw0h0mDCflktIg5uz9+XfgbjEtIRNJ2rx1c57rP5ao3wKyF6SjGTXKNzQHWkllyZAMg11lYShzWSkB4S2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9459c5feb53720a45734206118d8092ba8bf383142f3499bd10bedd4dfca0a76","last_reissued_at":"2026-06-02T01:04:00.726603Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:00.726603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Taming the Loss Landscape of PINNs with Noisy Feynman-Kac Supervision: Operator Preconditioning and Non-Asymptotic Error Bounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Chengyu Liu, Hanyu Hu, Nathanael Tepakbong, Xiang Zhou","submitted_at":"2026-05-30T09:38:48Z","abstract_excerpt":"Physics-Informed Neural Networks (PINNs) often train slowly or fail to converge on challenging partial differential equations (PDEs), a behavior recently linked to severely ill-conditioned loss landscapes inherited from the underlying differential operator. We study PINNs augmented with a pointwise data-fidelity term, added at a few points in the domain to the standard residual and boundary losses. We show that this supervision term acts as an operator-level preconditioner: for suitable weights, our comparison bounds guarantee a substantially smaller condition number than under the standard PI"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00643","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/2606.00643/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":"2606.00643","created_at":"2026-06-02T01:04:00.726659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00643v1","created_at":"2026-06-02T01:04:00.726659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00643","created_at":"2026-06-02T01:04:00.726659+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRM4L7VVG4QK","created_at":"2026-06-02T01:04:00.726659+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRM4L7VVG4QKIVZU","created_at":"2026-06-02T01:04:00.726659+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRM4L7VV","created_at":"2026-06-02T01:04:00.726659+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/SRM4L7VVG4QKIVZUEBQRRWAJFO","json":"https://pith.science/pith/SRM4L7VVG4QKIVZUEBQRRWAJFO.json","graph_json":"https://pith.science/api/pith-number/SRM4L7VVG4QKIVZUEBQRRWAJFO/graph.json","events_json":"https://pith.science/api/pith-number/SRM4L7VVG4QKIVZUEBQRRWAJFO/events.json","paper":"https://pith.science/paper/SRM4L7VV"},"agent_actions":{"view_html":"https://pith.science/pith/SRM4L7VVG4QKIVZUEBQRRWAJFO","download_json":"https://pith.science/pith/SRM4L7VVG4QKIVZUEBQRRWAJFO.json","view_paper":"https://pith.science/paper/SRM4L7VV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00643&json=true","fetch_graph":"https://pith.science/api/pith-number/SRM4L7VVG4QKIVZUEBQRRWAJFO/graph.json","fetch_events":"https://pith.science/api/pith-number/SRM4L7VVG4QKIVZUEBQRRWAJFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRM4L7VVG4QKIVZUEBQRRWAJFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRM4L7VVG4QKIVZUEBQRRWAJFO/action/storage_attestation","attest_author":"https://pith.science/pith/SRM4L7VVG4QKIVZUEBQRRWAJFO/action/author_attestation","sign_citation":"https://pith.science/pith/SRM4L7VVG4QKIVZUEBQRRWAJFO/action/citation_signature","submit_replication":"https://pith.science/pith/SRM4L7VVG4QKIVZUEBQRRWAJFO/action/replication_record"}},"created_at":"2026-06-02T01:04:00.726659+00:00","updated_at":"2026-06-02T01:04:00.726659+00:00"}