{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LVUQ3ZOLNV5FU5ZMTBJJN7GRS3","short_pith_number":"pith:LVUQ3ZOL","canonical_record":{"source":{"id":"2410.00053","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-28T14:49:23Z","cross_cats_sorted":[],"title_canon_sha256":"a5729c9e7d1e4a1e8c0431ab25ba96e80b4ec908e0c1f74a2dd09c3d9eed107d","abstract_canon_sha256":"d70bdef423d1360ef9a5207f54664080df2eb034de922d5db0c5fc4fcf157428"},"schema_version":"1.0"},"canonical_sha256":"5d690de5cb6d7a5a772c985296fcd196e9454246a07a17994dd8d53b3f5ea6d1","source":{"kind":"arxiv","id":"2410.00053","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00053","created_at":"2026-07-05T09:13:58Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00053v1","created_at":"2026-07-05T09:13:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00053","created_at":"2026-07-05T09:13:58Z"},{"alias_kind":"pith_short_12","alias_value":"LVUQ3ZOLNV5F","created_at":"2026-07-05T09:13:58Z"},{"alias_kind":"pith_short_16","alias_value":"LVUQ3ZOLNV5FU5ZM","created_at":"2026-07-05T09:13:58Z"},{"alias_kind":"pith_short_8","alias_value":"LVUQ3ZOL","created_at":"2026-07-05T09:13:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LVUQ3ZOLNV5FU5ZMTBJJN7GRS3","target":"record","payload":{"canonical_record":{"source":{"id":"2410.00053","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-28T14:49:23Z","cross_cats_sorted":[],"title_canon_sha256":"a5729c9e7d1e4a1e8c0431ab25ba96e80b4ec908e0c1f74a2dd09c3d9eed107d","abstract_canon_sha256":"d70bdef423d1360ef9a5207f54664080df2eb034de922d5db0c5fc4fcf157428"},"schema_version":"1.0"},"canonical_sha256":"5d690de5cb6d7a5a772c985296fcd196e9454246a07a17994dd8d53b3f5ea6d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:58.804261Z","signature_b64":"0WwtimRktLVggk1Q8Xw7fqgPsqa74U3hV4Md6JOpLh7ssxB5cqwsd/P+IMLpiEDZsmbzYxxy/bVkxUCp7qAKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d690de5cb6d7a5a772c985296fcd196e9454246a07a17994dd8d53b3f5ea6d1","last_reissued_at":"2026-07-05T09:13:58.801894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:58.801894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.00053","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:13:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PRjcOhosIDWKD9Kd2VZN1kcGip947ukjQtKHleDg21um6VKqvkurmznhnzJNSzqHB9T94GC0ycjDBSIPqD9FBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:06:46.240116Z"},"content_sha256":"0faa4148e685a77abda37846bc5e47eef829c1c4f137a9e1ae59d911a5189bc6","schema_version":"1.0","event_id":"sha256:0faa4148e685a77abda37846bc5e47eef829c1c4f137a9e1ae59d911a5189bc6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LVUQ3ZOLNV5FU5ZMTBJJN7GRS3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Frequency-adaptive Multi-scale Deep Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jizu Huang, Rukang You, Tao Zhou","submitted_at":"2024-09-28T14:49:23Z","abstract_excerpt":"Multi-scale deep neural networks (MscaleDNNs) with downing-scaling mapping have demonstrated superiority over traditional DNNs in approximating target functions characterized by high frequency features. However, the performance of MscaleDNNs heavily depends on the parameters in the downing-scaling mapping, which limits their broader application. In this work, we establish a fitting error bound to explain why MscaleDNNs are advantageous for approximating high frequency functions. Building on this insight, we construct a hybrid feature embedding to enhance the accuracy and robustness of the down"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00053","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/2410.00053/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":"2026-07-05T09:13:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Cud5RJDIijVxvzUeWHs6ZHdDhuWRmgTwNGJBH60oL87Il9eVAvIVY9EtHPS6FZEYLe7c6Hj75k3b4RdjAo3Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:06:46.240781Z"},"content_sha256":"5d5d36caf6d1ab5d3d467cb7df596e0230a7a717e8dc32ca2d75a7d0ba79e64e","schema_version":"1.0","event_id":"sha256:5d5d36caf6d1ab5d3d467cb7df596e0230a7a717e8dc32ca2d75a7d0ba79e64e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LVUQ3ZOLNV5FU5ZMTBJJN7GRS3/bundle.json","state_url":"https://pith.science/pith/LVUQ3ZOLNV5FU5ZMTBJJN7GRS3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LVUQ3ZOLNV5FU5ZMTBJJN7GRS3/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":"2026-08-19T19:06:46Z","links":{"resolver":"https://pith.science/pith/LVUQ3ZOLNV5FU5ZMTBJJN7GRS3","bundle":"https://pith.science/pith/LVUQ3ZOLNV5FU5ZMTBJJN7GRS3/bundle.json","state":"https://pith.science/pith/LVUQ3ZOLNV5FU5ZMTBJJN7GRS3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LVUQ3ZOLNV5FU5ZMTBJJN7GRS3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LVUQ3ZOLNV5FU5ZMTBJJN7GRS3","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":"d70bdef423d1360ef9a5207f54664080df2eb034de922d5db0c5fc4fcf157428","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-28T14:49:23Z","title_canon_sha256":"a5729c9e7d1e4a1e8c0431ab25ba96e80b4ec908e0c1f74a2dd09c3d9eed107d"},"schema_version":"1.0","source":{"id":"2410.00053","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00053","created_at":"2026-07-05T09:13:58Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00053v1","created_at":"2026-07-05T09:13:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00053","created_at":"2026-07-05T09:13:58Z"},{"alias_kind":"pith_short_12","alias_value":"LVUQ3ZOLNV5F","created_at":"2026-07-05T09:13:58Z"},{"alias_kind":"pith_short_16","alias_value":"LVUQ3ZOLNV5FU5ZM","created_at":"2026-07-05T09:13:58Z"},{"alias_kind":"pith_short_8","alias_value":"LVUQ3ZOL","created_at":"2026-07-05T09:13:58Z"}],"graph_snapshots":[{"event_id":"sha256:5d5d36caf6d1ab5d3d467cb7df596e0230a7a717e8dc32ca2d75a7d0ba79e64e","target":"graph","created_at":"2026-07-05T09:13:58Z","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/2410.00053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-scale deep neural networks (MscaleDNNs) with downing-scaling mapping have demonstrated superiority over traditional DNNs in approximating target functions characterized by high frequency features. However, the performance of MscaleDNNs heavily depends on the parameters in the downing-scaling mapping, which limits their broader application. In this work, we establish a fitting error bound to explain why MscaleDNNs are advantageous for approximating high frequency functions. Building on this insight, we construct a hybrid feature embedding to enhance the accuracy and robustness of the down","authors_text":"Jizu Huang, Rukang You, Tao Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-28T14:49:23Z","title":"Frequency-adaptive Multi-scale Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00053","kind":"arxiv","version":1},"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":"sha256:0faa4148e685a77abda37846bc5e47eef829c1c4f137a9e1ae59d911a5189bc6","target":"record","created_at":"2026-07-05T09:13:58Z","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":"d70bdef423d1360ef9a5207f54664080df2eb034de922d5db0c5fc4fcf157428","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-28T14:49:23Z","title_canon_sha256":"a5729c9e7d1e4a1e8c0431ab25ba96e80b4ec908e0c1f74a2dd09c3d9eed107d"},"schema_version":"1.0","source":{"id":"2410.00053","kind":"arxiv","version":1}},"canonical_sha256":"5d690de5cb6d7a5a772c985296fcd196e9454246a07a17994dd8d53b3f5ea6d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d690de5cb6d7a5a772c985296fcd196e9454246a07a17994dd8d53b3f5ea6d1","first_computed_at":"2026-07-05T09:13:58.801894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:58.801894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0WwtimRktLVggk1Q8Xw7fqgPsqa74U3hV4Md6JOpLh7ssxB5cqwsd/P+IMLpiEDZsmbzYxxy/bVkxUCp7qAKBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:58.804261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.00053","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0faa4148e685a77abda37846bc5e47eef829c1c4f137a9e1ae59d911a5189bc6","sha256:5d5d36caf6d1ab5d3d467cb7df596e0230a7a717e8dc32ca2d75a7d0ba79e64e"],"state_sha256":"1de75a99992c5144fc20d0990d920c5ef7ee1622900bc1e6e2f042e65a59466f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M+a5mfo0BlMlxRybPa1QRCgh/78uwzZIgd/TuZ5slB4LR7U0YSsnfiRycl7XdIrz88MfJKV+nxGKAeoApQ09BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T19:06:46.246184Z","bundle_sha256":"2086f9393a596da6c4123e9a4eadd3f04cb5bdf9a92271dc349ae66ed52e5d35"}}