{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CXUV5FHRC2AECPJYZCIL2AH2NG","short_pith_number":"pith:CXUV5FHR","canonical_record":{"source":{"id":"2605.04126","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-05T15:35:24Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"7f34b6eca510e0dbdf42e154c23af053762343e69c40f374c0c9e051ad3b15a4","abstract_canon_sha256":"118df57f213fe0f8330de8ce88cb04103da98af74bf032c696b5ffecc3322a65"},"schema_version":"1.0"},"canonical_sha256":"15e95e94f11680413d38c890bd00fa69b47ac656be38bc2c710f51e5c124e25c","source":{"kind":"arxiv","id":"2605.04126","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.04126","created_at":"2026-06-23T02:13:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.04126v2","created_at":"2026-06-23T02:13:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04126","created_at":"2026-06-23T02:13:24Z"},{"alias_kind":"pith_short_12","alias_value":"CXUV5FHRC2AE","created_at":"2026-06-23T02:13:24Z"},{"alias_kind":"pith_short_16","alias_value":"CXUV5FHRC2AECPJY","created_at":"2026-06-23T02:13:24Z"},{"alias_kind":"pith_short_8","alias_value":"CXUV5FHR","created_at":"2026-06-23T02:13:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CXUV5FHRC2AECPJYZCIL2AH2NG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.04126","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-05T15:35:24Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"7f34b6eca510e0dbdf42e154c23af053762343e69c40f374c0c9e051ad3b15a4","abstract_canon_sha256":"118df57f213fe0f8330de8ce88cb04103da98af74bf032c696b5ffecc3322a65"},"schema_version":"1.0"},"canonical_sha256":"15e95e94f11680413d38c890bd00fa69b47ac656be38bc2c710f51e5c124e25c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:24.655166Z","signature_b64":"wDswHJcgwffkqmfbVZ8qvSZnpRI/gcT+FkXRAP3hOc7BFEu1iTwdzXGfmM2TtgrhGV6WAiuwxxs82uLY6+0yCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15e95e94f11680413d38c890bd00fa69b47ac656be38bc2c710f51e5c124e25c","last_reissued_at":"2026-06-23T02:13:24.654670Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:24.654670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.04126","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/3qoq6Bi6E7sSgE1brjO6mZohzrRkdYu9QYdMfPNQOYSd/tv61Y5c9t3ljb4bjC4bG4FEduZ2uLiGgTyVOioDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T06:27:54.798750Z"},"content_sha256":"0b73966cd2b4feb3d2c7dd9bad6e8d7edc0040b1985b45aef9fed9cc70e88649","schema_version":"1.0","event_id":"sha256:0b73966cd2b4feb3d2c7dd9bad6e8d7edc0040b1985b45aef9fed9cc70e88649"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CXUV5FHRC2AECPJYZCIL2AH2NG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simultaneous CNN Approximation on Manifolds with Applications to Boundary Value Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CNNs approximate manifold functions and their derivatives at rates set by intrinsic dimension alone.","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Hanfei Zhou, Lei Shi","submitted_at":"2026-05-05T15:35:24Z","abstract_excerpt":"This paper develops convolutional neural network (CNN) methods for simultaneous Sobolev approximation and elliptic boundary value problems on compact Riemannian manifolds. We prove approximation estimates for single- and multichannel CNNs, with rates governed by the intrinsic dimension and the smoothness gap. Motivated by elliptic stability, we propose a physics-informed CNN framework with a spectral boundary loss. The boundary residual is expanded in boundary Laplace--Beltrami eigenmodes and penalized by Sobolev trace weights, matching the natural \\(\\mathcal H^{2s-1/2}(\\partial\\mathcal M^d)\\)"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We establish simultaneous Sobolev approximation results for single- and multichannel CNNs, showing that manifold functions and their derivatives can be approximated with rates governed by the intrinsic dimension and the smoothness gap, rather than by the ambient dimension.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the CNN architecture can be adapted to the Riemannian manifold structure such that the approximation rates transfer from Euclidean CNN theory without additional manifold-specific error terms that dominate the claimed rates.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CNNs achieve simultaneous Sobolev approximation on manifolds with intrinsic-dimension rates and enable a PICNN for BVPs via spectral boundary loss that improves stability over standard PINNs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CNNs approximate manifold functions and their derivatives at rates set by intrinsic dimension alone.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"82d4bd9152caa74ddcec78da37c28d6ecd791580e9c160c911269b046083f29d"},"source":{"id":"2605.04126","kind":"arxiv","version":2},"verdict":{"id":"3d2bfee3-6b15-4cee-9453-bb15dc2387b7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T18:17:53.271338Z","strongest_claim":"We establish simultaneous Sobolev approximation results for single- and multichannel CNNs, showing that manifold functions and their derivatives can be approximated with rates governed by the intrinsic dimension and the smoothness gap, rather than by the ambient dimension.","one_line_summary":"CNNs achieve simultaneous Sobolev approximation on manifolds with intrinsic-dimension rates and enable a PICNN for BVPs via spectral boundary loss that improves stability over standard PINNs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the CNN architecture can be adapted to the Riemannian manifold structure such that the approximation rates transfer from Euclidean CNN theory without additional manifold-specific error terms that dominate the claimed rates.","pith_extraction_headline":"CNNs approximate manifold functions and their derivatives at rates set by intrinsic dimension alone."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.04126/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T12:42:20.649026Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T00:01:21.770953Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T14:58:56.578013Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e40ddb382a4e80078bcc87fc880f7650177a4667739be1d41e4619013648b2b6"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":3,"snapshot_sha256":"0b1e0cbe4b35e3337d0930356331c9092618c3b96e7caff6a5244119a22107f6"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"3d2bfee3-6b15-4cee-9453-bb15dc2387b7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uRNuWmDkDvdMoT7rBKXWFoJ2CSlmskMZSYV5nwgD8ytm6GglqTtSUt794wj1A/k7lwA3COs0ZHscjDU59ATTBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T06:27:54.799253Z"},"content_sha256":"160b0994815134da05ea62754216d7811df973f0c688bc04e2cc33c917cf769e","schema_version":"1.0","event_id":"sha256:160b0994815134da05ea62754216d7811df973f0c688bc04e2cc33c917cf769e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CXUV5FHRC2AECPJYZCIL2AH2NG/bundle.json","state_url":"https://pith.science/pith/CXUV5FHRC2AECPJYZCIL2AH2NG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CXUV5FHRC2AECPJYZCIL2AH2NG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T06:27:54Z","links":{"resolver":"https://pith.science/pith/CXUV5FHRC2AECPJYZCIL2AH2NG","bundle":"https://pith.science/pith/CXUV5FHRC2AECPJYZCIL2AH2NG/bundle.json","state":"https://pith.science/pith/CXUV5FHRC2AECPJYZCIL2AH2NG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CXUV5FHRC2AECPJYZCIL2AH2NG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CXUV5FHRC2AECPJYZCIL2AH2NG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"118df57f213fe0f8330de8ce88cb04103da98af74bf032c696b5ffecc3322a65","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-05T15:35:24Z","title_canon_sha256":"7f34b6eca510e0dbdf42e154c23af053762343e69c40f374c0c9e051ad3b15a4"},"schema_version":"1.0","source":{"id":"2605.04126","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.04126","created_at":"2026-06-23T02:13:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.04126v2","created_at":"2026-06-23T02:13:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04126","created_at":"2026-06-23T02:13:24Z"},{"alias_kind":"pith_short_12","alias_value":"CXUV5FHRC2AE","created_at":"2026-06-23T02:13:24Z"},{"alias_kind":"pith_short_16","alias_value":"CXUV5FHRC2AECPJY","created_at":"2026-06-23T02:13:24Z"},{"alias_kind":"pith_short_8","alias_value":"CXUV5FHR","created_at":"2026-06-23T02:13:24Z"}],"graph_snapshots":[{"event_id":"sha256:160b0994815134da05ea62754216d7811df973f0c688bc04e2cc33c917cf769e","target":"graph","created_at":"2026-06-23T02:13:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We establish simultaneous Sobolev approximation results for single- and multichannel CNNs, showing that manifold functions and their derivatives can be approximated with rates governed by the intrinsic dimension and the smoothness gap, rather than by the ambient dimension."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the CNN architecture can be adapted to the Riemannian manifold structure such that the approximation rates transfer from Euclidean CNN theory without additional manifold-specific error terms that dominate the claimed rates."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CNNs achieve simultaneous Sobolev approximation on manifolds with intrinsic-dimension rates and enable a PICNN for BVPs via spectral boundary loss that improves stability over standard PINNs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CNNs approximate manifold functions and their derivatives at rates set by intrinsic dimension alone."}],"snapshot_sha256":"82d4bd9152caa74ddcec78da37c28d6ecd791580e9c160c911269b046083f29d"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"0b1e0cbe4b35e3337d0930356331c9092618c3b96e7caff6a5244119a22107f6"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T12:42:20.649026Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T00:01:21.770953Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T14:58:56.578013Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.04126/integrity.json","findings":[],"snapshot_sha256":"e40ddb382a4e80078bcc87fc880f7650177a4667739be1d41e4619013648b2b6","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper develops convolutional neural network (CNN) methods for simultaneous Sobolev approximation and elliptic boundary value problems on compact Riemannian manifolds. We prove approximation estimates for single- and multichannel CNNs, with rates governed by the intrinsic dimension and the smoothness gap. Motivated by elliptic stability, we propose a physics-informed CNN framework with a spectral boundary loss. The boundary residual is expanded in boundary Laplace--Beltrami eigenmodes and penalized by Sobolev trace weights, matching the natural \\(\\mathcal H^{2s-1/2}(\\partial\\mathcal M^d)\\)","authors_text":"Hanfei Zhou, Lei Shi","cross_cats":["cs.NA","math.NA"],"headline":"CNNs approximate manifold functions and their derivatives at rates set by intrinsic dimension alone.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-05T15:35:24Z","title":"Simultaneous CNN Approximation on Manifolds with Applications to Boundary Value Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.04126","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T18:17:53.271338Z","id":"3d2bfee3-6b15-4cee-9453-bb15dc2387b7","model_set":{"reader":"grok-4.3"},"one_line_summary":"CNNs achieve simultaneous Sobolev approximation on manifolds with intrinsic-dimension rates and enable a PICNN for BVPs via spectral boundary loss that improves stability over standard PINNs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CNNs approximate manifold functions and their derivatives at rates set by intrinsic dimension alone.","strongest_claim":"We establish simultaneous Sobolev approximation results for single- and multichannel CNNs, showing that manifold functions and their derivatives can be approximated with rates governed by the intrinsic dimension and the smoothness gap, rather than by the ambient dimension.","weakest_assumption":"That the CNN architecture can be adapted to the Riemannian manifold structure such that the approximation rates transfer from Euclidean CNN theory without additional manifold-specific error terms that dominate the claimed rates."}},"verdict_id":"3d2bfee3-6b15-4cee-9453-bb15dc2387b7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0b73966cd2b4feb3d2c7dd9bad6e8d7edc0040b1985b45aef9fed9cc70e88649","target":"record","created_at":"2026-06-23T02:13:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"118df57f213fe0f8330de8ce88cb04103da98af74bf032c696b5ffecc3322a65","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-05T15:35:24Z","title_canon_sha256":"7f34b6eca510e0dbdf42e154c23af053762343e69c40f374c0c9e051ad3b15a4"},"schema_version":"1.0","source":{"id":"2605.04126","kind":"arxiv","version":2}},"canonical_sha256":"15e95e94f11680413d38c890bd00fa69b47ac656be38bc2c710f51e5c124e25c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15e95e94f11680413d38c890bd00fa69b47ac656be38bc2c710f51e5c124e25c","first_computed_at":"2026-06-23T02:13:24.654670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:24.654670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wDswHJcgwffkqmfbVZ8qvSZnpRI/gcT+FkXRAP3hOc7BFEu1iTwdzXGfmM2TtgrhGV6WAiuwxxs82uLY6+0yCw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:24.655166Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.04126","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b73966cd2b4feb3d2c7dd9bad6e8d7edc0040b1985b45aef9fed9cc70e88649","sha256:160b0994815134da05ea62754216d7811df973f0c688bc04e2cc33c917cf769e"],"state_sha256":"25753eca0325e78e0b19d3f7dbe30f014f83798a7b8341f079ada9b8db1e04b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+gOkm66rvThh+I6oeDf8rrLijgP6SX8u31monttGMY7NOyXP5/IGU6W0sMtiHsEkV39dwW4st7PT6m4pt9CEDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T06:27:54.801650Z","bundle_sha256":"1c2487fec26a1791566fcd03b41a2b724c352198cba5970e7e0da40b4b09b2be"}}