{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:HLGTTKH4XZAYODEKVESEDE7UJW","short_pith_number":"pith:HLGTTKH4","canonical_record":{"source":{"id":"1706.03041","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-03-25T15:46:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"546d1354148aa22d384a27c441509c01102e762ad50ddf7b3ff9b92bb70aba5f","abstract_canon_sha256":"6938a5a25e614f85acc1b3160134862c2a30514c6a1ce02853dfb4515824db70"},"schema_version":"1.0"},"canonical_sha256":"3acd39a8fcbe41870c8aa9244193f44d93c3cce342c366aea22aea2614b72868","source":{"kind":"arxiv","id":"1706.03041","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03041","created_at":"2026-05-18T00:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03041v2","created_at":"2026-05-18T00:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03041","created_at":"2026-05-18T00:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"HLGTTKH4XZAY","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HLGTTKH4XZAYODEK","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HLGTTKH4","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:HLGTTKH4XZAYODEKVESEDE7UJW","target":"record","payload":{"canonical_record":{"source":{"id":"1706.03041","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-03-25T15:46:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"546d1354148aa22d384a27c441509c01102e762ad50ddf7b3ff9b92bb70aba5f","abstract_canon_sha256":"6938a5a25e614f85acc1b3160134862c2a30514c6a1ce02853dfb4515824db70"},"schema_version":"1.0"},"canonical_sha256":"3acd39a8fcbe41870c8aa9244193f44d93c3cce342c366aea22aea2614b72868","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:48.512101Z","signature_b64":"JsLfILq9XEKNXM9Hx+Y6+bDYP8N1RgQEfcRu/r+024cNNxS0xEAay9NvmAE30TYgL70kVprX8EXmTWN+QywnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3acd39a8fcbe41870c8aa9244193f44d93c3cce342c366aea22aea2614b72868","last_reissued_at":"2026-05-18T00:06:48.511653Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:48.511653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.03041","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":"2026-05-18T00:06:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w4vU0e1YoSntOIldqrjNJ+g+f4iAowh1ovWIhhzu4NuE4PkabaZ7kkXXFPrYsa7sL+Mpe7hsHu2hlOKwTj5xCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:00:40.862269Z"},"content_sha256":"9aae5648262045aed7652a7061a0f95003c444e3de39220ebfb3a5c0268a1f2a","schema_version":"1.0","event_id":"sha256:9aae5648262045aed7652a7061a0f95003c444e3de39220ebfb3a5c0268a1f2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:HLGTTKH4XZAYODEKVESEDE7UJW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning optimal wavelet bases using a neural network approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Andreas S{\\o}gaard","submitted_at":"2017-03-25T15:46:01Z","abstract_excerpt":"A novel method for learning optimal, orthonormal wavelet bases for representing 1- and 2D signals, based on parallels between the wavelet transform and fully connected artificial neural networks, is described. The structural similarities between these two concepts are reviewed and combined to a \"wavenet\", allowing for the direct learning of optimal wavelet filter coefficient through stochastic gradient descent with back-propagation over ensembles of training inputs, where conditions on the filter coefficients for constituting orthonormal wavelet bases are cast as quadratic regularisations term"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03041","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":""},"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":"2026-05-18T00:06:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6lTArjUlG+WYvDWN9Qu+o+1KhVkNgKsgc2t0JFOkRXnryA8hu6kCTzlwNoHCHHXMT1hdUIUStl+tzg8r8z2RAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:00:40.863290Z"},"content_sha256":"929c2a364eaa5d4c106da95ad0fa8747a2fa2106eb5a32accdc34318f5d7eb98","schema_version":"1.0","event_id":"sha256:929c2a364eaa5d4c106da95ad0fa8747a2fa2106eb5a32accdc34318f5d7eb98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HLGTTKH4XZAYODEKVESEDE7UJW/bundle.json","state_url":"https://pith.science/pith/HLGTTKH4XZAYODEKVESEDE7UJW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HLGTTKH4XZAYODEKVESEDE7UJW/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":"2026-05-26T02:00:40Z","links":{"resolver":"https://pith.science/pith/HLGTTKH4XZAYODEKVESEDE7UJW","bundle":"https://pith.science/pith/HLGTTKH4XZAYODEKVESEDE7UJW/bundle.json","state":"https://pith.science/pith/HLGTTKH4XZAYODEKVESEDE7UJW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HLGTTKH4XZAYODEKVESEDE7UJW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:HLGTTKH4XZAYODEKVESEDE7UJW","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":"6938a5a25e614f85acc1b3160134862c2a30514c6a1ce02853dfb4515824db70","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-03-25T15:46:01Z","title_canon_sha256":"546d1354148aa22d384a27c441509c01102e762ad50ddf7b3ff9b92bb70aba5f"},"schema_version":"1.0","source":{"id":"1706.03041","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03041","created_at":"2026-05-18T00:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03041v2","created_at":"2026-05-18T00:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03041","created_at":"2026-05-18T00:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"HLGTTKH4XZAY","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HLGTTKH4XZAYODEK","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HLGTTKH4","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:929c2a364eaa5d4c106da95ad0fa8747a2fa2106eb5a32accdc34318f5d7eb98","target":"graph","created_at":"2026-05-18T00:06:48Z","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"},"paper":{"abstract_excerpt":"A novel method for learning optimal, orthonormal wavelet bases for representing 1- and 2D signals, based on parallels between the wavelet transform and fully connected artificial neural networks, is described. The structural similarities between these two concepts are reviewed and combined to a \"wavenet\", allowing for the direct learning of optimal wavelet filter coefficient through stochastic gradient descent with back-propagation over ensembles of training inputs, where conditions on the filter coefficients for constituting orthonormal wavelet bases are cast as quadratic regularisations term","authors_text":"Andreas S{\\o}gaard","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-03-25T15:46:01Z","title":"Learning optimal wavelet bases using a neural network approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03041","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":"sha256:9aae5648262045aed7652a7061a0f95003c444e3de39220ebfb3a5c0268a1f2a","target":"record","created_at":"2026-05-18T00:06:48Z","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":"6938a5a25e614f85acc1b3160134862c2a30514c6a1ce02853dfb4515824db70","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-03-25T15:46:01Z","title_canon_sha256":"546d1354148aa22d384a27c441509c01102e762ad50ddf7b3ff9b92bb70aba5f"},"schema_version":"1.0","source":{"id":"1706.03041","kind":"arxiv","version":2}},"canonical_sha256":"3acd39a8fcbe41870c8aa9244193f44d93c3cce342c366aea22aea2614b72868","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3acd39a8fcbe41870c8aa9244193f44d93c3cce342c366aea22aea2614b72868","first_computed_at":"2026-05-18T00:06:48.511653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:48.511653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JsLfILq9XEKNXM9Hx+Y6+bDYP8N1RgQEfcRu/r+024cNNxS0xEAay9NvmAE30TYgL70kVprX8EXmTWN+QywnDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:48.512101Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.03041","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9aae5648262045aed7652a7061a0f95003c444e3de39220ebfb3a5c0268a1f2a","sha256:929c2a364eaa5d4c106da95ad0fa8747a2fa2106eb5a32accdc34318f5d7eb98"],"state_sha256":"f6c9e28704681d97a1cea598715ffd5cde72ce7ed0ca9408253f7a4833a3d794"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wu/QgatGNtrMVglpwk+UR+5V+HZP65AHS2WCl4ZdAlnK66uqA4USGjEqqKVMkWOnyjuADVVr2fXtgquJsnC/Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T02:00:40.867263Z","bundle_sha256":"996c8589eb671957e6872c4bd5c0edefd3f7a7cc6d9a6c15dae406f4196157cd"}}