{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RNQAX6BECETAHGCCFRISRUVWWL","short_pith_number":"pith:RNQAX6BE","canonical_record":{"source":{"id":"2109.02832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-09-07T02:58:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"df848013b4fa020e39d862b288c4986504be987e5032669be4e1dde35f7cc9c2","abstract_canon_sha256":"a457187d8223fd4ace7c148abdb899217c3990d54b43a58821adad703ea7279a"},"schema_version":"1.0"},"canonical_sha256":"8b600bf82411260398422c5128d2b6b2c446c0fea74b9226320abc890afae230","source":{"kind":"arxiv","id":"2109.02832","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02832","created_at":"2026-07-05T03:13:05Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02832v2","created_at":"2026-07-05T03:13:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02832","created_at":"2026-07-05T03:13:05Z"},{"alias_kind":"pith_short_12","alias_value":"RNQAX6BECETA","created_at":"2026-07-05T03:13:05Z"},{"alias_kind":"pith_short_16","alias_value":"RNQAX6BECETAHGCC","created_at":"2026-07-05T03:13:05Z"},{"alias_kind":"pith_short_8","alias_value":"RNQAX6BE","created_at":"2026-07-05T03:13:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RNQAX6BECETAHGCCFRISRUVWWL","target":"record","payload":{"canonical_record":{"source":{"id":"2109.02832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-09-07T02:58:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"df848013b4fa020e39d862b288c4986504be987e5032669be4e1dde35f7cc9c2","abstract_canon_sha256":"a457187d8223fd4ace7c148abdb899217c3990d54b43a58821adad703ea7279a"},"schema_version":"1.0"},"canonical_sha256":"8b600bf82411260398422c5128d2b6b2c446c0fea74b9226320abc890afae230","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:05.929164Z","signature_b64":"E97zNL8SScC1Rw5ZDhFj6GVuqfjKGffkr1hwbgPk1Cenoa0J+P/IdChQywkmjOUiyD0bLT0F5cgSZFgmX/IKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b600bf82411260398422c5128d2b6b2c446c0fea74b9226320abc890afae230","last_reissued_at":"2026-07-05T03:13:05.928747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:05.928747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.02832","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":"2026-07-05T03:13:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sa8pv/FX5YFuyawAb98bhOusgS6iYZQ3bJayd8iQx7dYGHZeIA+u9fWbKvPkNxixQqNj3jOmkBU/n/NLn85pBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:25:34.149106Z"},"content_sha256":"e781d7fd9b1029f47ef48748acf6e13ce3be11429274e32a8e06ad3aba0b5b43","schema_version":"1.0","event_id":"sha256:e781d7fd9b1029f47ef48748acf6e13ce3be11429274e32a8e06ad3aba0b5b43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RNQAX6BECETAHGCCFRISRUVWWL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hao Liu, Minshuo Chen, Tuo Zhao, Wenjing Liao","submitted_at":"2021-09-07T02:58:11Z","abstract_excerpt":"Most of existing statistical theories on deep neural networks have sample complexities cursed by the data dimension and therefore cannot well explain the empirical success of deep learning on high-dimensional data. To bridge this gap, we propose to exploit low-dimensional geometric structures of the real world data sets. We establish theoretical guarantees of convolutional residual networks (ConvResNet) in terms of function approximation and statistical estimation for binary classification. Specifically, given the data lying on a $d$-dimensional manifold isometrically embedded in $\\mathbb{R}^D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02832","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/2109.02832/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:13:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YVK7GliKpKgPSHVhgSnOfH3Fox8vLyvOM+HRJXXSoO4g42eUcFDtjqSoH9IgEDGDntYIMzJ1OE9X+5N8jI+xBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:25:34.149498Z"},"content_sha256":"758c7863e8e291bae4e9a39681f49d11858919fbc039bf2b722f295e60a93286","schema_version":"1.0","event_id":"sha256:758c7863e8e291bae4e9a39681f49d11858919fbc039bf2b722f295e60a93286"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RNQAX6BECETAHGCCFRISRUVWWL/bundle.json","state_url":"https://pith.science/pith/RNQAX6BECETAHGCCFRISRUVWWL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RNQAX6BECETAHGCCFRISRUVWWL/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":"2026-07-07T13:25:34Z","links":{"resolver":"https://pith.science/pith/RNQAX6BECETAHGCCFRISRUVWWL","bundle":"https://pith.science/pith/RNQAX6BECETAHGCCFRISRUVWWL/bundle.json","state":"https://pith.science/pith/RNQAX6BECETAHGCCFRISRUVWWL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RNQAX6BECETAHGCCFRISRUVWWL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RNQAX6BECETAHGCCFRISRUVWWL","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":"a457187d8223fd4ace7c148abdb899217c3990d54b43a58821adad703ea7279a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-09-07T02:58:11Z","title_canon_sha256":"df848013b4fa020e39d862b288c4986504be987e5032669be4e1dde35f7cc9c2"},"schema_version":"1.0","source":{"id":"2109.02832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02832","created_at":"2026-07-05T03:13:05Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02832v2","created_at":"2026-07-05T03:13:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02832","created_at":"2026-07-05T03:13:05Z"},{"alias_kind":"pith_short_12","alias_value":"RNQAX6BECETA","created_at":"2026-07-05T03:13:05Z"},{"alias_kind":"pith_short_16","alias_value":"RNQAX6BECETAHGCC","created_at":"2026-07-05T03:13:05Z"},{"alias_kind":"pith_short_8","alias_value":"RNQAX6BE","created_at":"2026-07-05T03:13:05Z"}],"graph_snapshots":[{"event_id":"sha256:758c7863e8e291bae4e9a39681f49d11858919fbc039bf2b722f295e60a93286","target":"graph","created_at":"2026-07-05T03:13:05Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.02832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most of existing statistical theories on deep neural networks have sample complexities cursed by the data dimension and therefore cannot well explain the empirical success of deep learning on high-dimensional data. To bridge this gap, we propose to exploit low-dimensional geometric structures of the real world data sets. We establish theoretical guarantees of convolutional residual networks (ConvResNet) in terms of function approximation and statistical estimation for binary classification. Specifically, given the data lying on a $d$-dimensional manifold isometrically embedded in $\\mathbb{R}^D","authors_text":"Hao Liu, Minshuo Chen, Tuo Zhao, Wenjing Liao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-09-07T02:58:11Z","title":"Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02832","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e781d7fd9b1029f47ef48748acf6e13ce3be11429274e32a8e06ad3aba0b5b43","target":"record","created_at":"2026-07-05T03:13:05Z","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":"a457187d8223fd4ace7c148abdb899217c3990d54b43a58821adad703ea7279a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-09-07T02:58:11Z","title_canon_sha256":"df848013b4fa020e39d862b288c4986504be987e5032669be4e1dde35f7cc9c2"},"schema_version":"1.0","source":{"id":"2109.02832","kind":"arxiv","version":2}},"canonical_sha256":"8b600bf82411260398422c5128d2b6b2c446c0fea74b9226320abc890afae230","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b600bf82411260398422c5128d2b6b2c446c0fea74b9226320abc890afae230","first_computed_at":"2026-07-05T03:13:05.928747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:05.928747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E97zNL8SScC1Rw5ZDhFj6GVuqfjKGffkr1hwbgPk1Cenoa0J+P/IdChQywkmjOUiyD0bLT0F5cgSZFgmX/IKCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:05.929164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.02832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e781d7fd9b1029f47ef48748acf6e13ce3be11429274e32a8e06ad3aba0b5b43","sha256:758c7863e8e291bae4e9a39681f49d11858919fbc039bf2b722f295e60a93286"],"state_sha256":"2da9735dfa2847cab5132ad21266c8576d54ed23a6a464d3b4bbdbca1ef5c4fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HOIox+BpbSmpLCmS+uHQzsNKazC/+GGf2arMGw3RhoLh8F+O7fEYlh9LQXR1vU/L83nL5mFT1Eem7cGWg3+LBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:25:34.151443Z","bundle_sha256":"5e3f828b774944811cd15313287e76cf09be1c8f0450c908fac824447e0046fe"}}