{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZBADUAWWEFNDGJTZ6SDIXDEJ7N","short_pith_number":"pith:ZBADUAWW","schema_version":"1.0","canonical_sha256":"c8403a02d6215a332679f4868b8c89fb41ee03798a9a09739cb00f9ba9737a3a","source":{"kind":"arxiv","id":"2506.04613","version":3},"attestation_state":"computed","paper":{"title":"DeePoly: A High-Order Accuracy Scientific Machine Learning Framework for Function Approximation and Solving PDEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Heng Yong, Li Liu","submitted_at":"2025-06-05T04:10:52Z","abstract_excerpt":"Recently, machine learning methods have gained significant traction in scientific computing, particularly for solving Partial Differential Equations (PDEs). However, methods based on deep neural networks (DNNs) often lack convergence guarantees and computational efficiency compared to traditional numerical schemes. This work introduces DeePoly, a novel framework that transforms the solution paradigm from pure non-convex parameter optimization to a two-stage approach: first employing a DNN to capture complex global features, followed by linear space optimization with combined DNN-extracted feat"},"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":"2506.04613","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-05T04:10:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3b48ceb23ad3592323026258dce9f27389323a10927323f18c7519c6b27eb088","abstract_canon_sha256":"6fc9bc4f95c479508a2283f9df8168fa3368b107085d847d278d90f9e5bc35c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:54.919809Z","signature_b64":"Du2vbMkoZ80RbUzSZ9PWDOJGQda0QObU9yY9XXaDQzMRy5WF7pe6RTt53ug5ZzjFNwCqq2/gJUuwVB6OQFAWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8403a02d6215a332679f4868b8c89fb41ee03798a9a09739cb00f9ba9737a3a","last_reissued_at":"2026-07-05T11:20:54.919337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:54.919337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeePoly: A High-Order Accuracy Scientific Machine Learning Framework for Function Approximation and Solving PDEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Heng Yong, Li Liu","submitted_at":"2025-06-05T04:10:52Z","abstract_excerpt":"Recently, machine learning methods have gained significant traction in scientific computing, particularly for solving Partial Differential Equations (PDEs). However, methods based on deep neural networks (DNNs) often lack convergence guarantees and computational efficiency compared to traditional numerical schemes. This work introduces DeePoly, a novel framework that transforms the solution paradigm from pure non-convex parameter optimization to a two-stage approach: first employing a DNN to capture complex global features, followed by linear space optimization with combined DNN-extracted feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04613","kind":"arxiv","version":3},"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/2506.04613/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":"2506.04613","created_at":"2026-07-05T11:20:54.919398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04613v3","created_at":"2026-07-05T11:20:54.919398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04613","created_at":"2026-07-05T11:20:54.919398+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBADUAWWEFND","created_at":"2026-07-05T11:20:54.919398+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBADUAWWEFNDGJTZ","created_at":"2026-07-05T11:20:54.919398+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBADUAWW","created_at":"2026-07-05T11:20:54.919398+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02091","citing_title":"CLINN: Conservation Law Informed Neural Network for Approximating Discontinuous Solutions","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBADUAWWEFNDGJTZ6SDIXDEJ7N","json":"https://pith.science/pith/ZBADUAWWEFNDGJTZ6SDIXDEJ7N.json","graph_json":"https://pith.science/api/pith-number/ZBADUAWWEFNDGJTZ6SDIXDEJ7N/graph.json","events_json":"https://pith.science/api/pith-number/ZBADUAWWEFNDGJTZ6SDIXDEJ7N/events.json","paper":"https://pith.science/paper/ZBADUAWW"},"agent_actions":{"view_html":"https://pith.science/pith/ZBADUAWWEFNDGJTZ6SDIXDEJ7N","download_json":"https://pith.science/pith/ZBADUAWWEFNDGJTZ6SDIXDEJ7N.json","view_paper":"https://pith.science/paper/ZBADUAWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04613&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBADUAWWEFNDGJTZ6SDIXDEJ7N/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBADUAWWEFNDGJTZ6SDIXDEJ7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBADUAWWEFNDGJTZ6SDIXDEJ7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBADUAWWEFNDGJTZ6SDIXDEJ7N/action/storage_attestation","attest_author":"https://pith.science/pith/ZBADUAWWEFNDGJTZ6SDIXDEJ7N/action/author_attestation","sign_citation":"https://pith.science/pith/ZBADUAWWEFNDGJTZ6SDIXDEJ7N/action/citation_signature","submit_replication":"https://pith.science/pith/ZBADUAWWEFNDGJTZ6SDIXDEJ7N/action/replication_record"}},"created_at":"2026-07-05T11:20:54.919398+00:00","updated_at":"2026-07-05T11:20:54.919398+00:00"}