{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WOBH4HSNLVOBNO7PZFUTDXF2XS","short_pith_number":"pith:WOBH4HSN","canonical_record":{"source":{"id":"1707.02813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-10T12:01:30Z","cross_cats_sorted":[],"title_canon_sha256":"66dad0489a6d52dea08b1fb0e968a561da7b449fbd5ce01c4cbb8477dad0d3c0","abstract_canon_sha256":"ecac18ae294298c167459b5c74f304f62c9efb73f9248ccdef2c0ce60c7620e5"},"schema_version":"1.0"},"canonical_sha256":"b3827e1e4d5d5c16bbefc96931dcbabcbc57dff002e295ec19502e6cdd26900e","source":{"kind":"arxiv","id":"1707.02813","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.02813","created_at":"2026-05-18T00:40:35Z"},{"alias_kind":"arxiv_version","alias_value":"1707.02813v1","created_at":"2026-05-18T00:40:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.02813","created_at":"2026-05-18T00:40:35Z"},{"alias_kind":"pith_short_12","alias_value":"WOBH4HSNLVOB","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WOBH4HSNLVOBNO7P","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WOBH4HSN","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WOBH4HSNLVOBNO7PZFUTDXF2XS","target":"record","payload":{"canonical_record":{"source":{"id":"1707.02813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-10T12:01:30Z","cross_cats_sorted":[],"title_canon_sha256":"66dad0489a6d52dea08b1fb0e968a561da7b449fbd5ce01c4cbb8477dad0d3c0","abstract_canon_sha256":"ecac18ae294298c167459b5c74f304f62c9efb73f9248ccdef2c0ce60c7620e5"},"schema_version":"1.0"},"canonical_sha256":"b3827e1e4d5d5c16bbefc96931dcbabcbc57dff002e295ec19502e6cdd26900e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:35.726260Z","signature_b64":"i0zupSMbCcTyVUMQJ85Pk/kxoK9sSAwmN6SkxnhuBANaBjswkSYgi5dhYwIBEq4g6A/oUDygIqQ9LrQHz8MPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3827e1e4d5d5c16bbefc96931dcbabcbc57dff002e295ec19502e6cdd26900e","last_reissued_at":"2026-05-18T00:40:35.725676Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:35.725676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.02813","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":"2026-05-18T00:40:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ECWccRx7wgm93kI+b11o4n1kcN4pxSwauXueugwFKatAI6I7pzizn/mfPSfsF6wWOzCeJ0JiSNWbQrEvEqyhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T20:36:25.809575Z"},"content_sha256":"36540d87ed64ad68667cca288559f8e10419121ee9ac0ac76bdda4f37731df2f","schema_version":"1.0","event_id":"sha256:36540d87ed64ad68667cca288559f8e10419121ee9ac0ac76bdda4f37731df2f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WOBH4HSNLVOBNO7PZFUTDXF2XS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scale-Regularized Filter Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fran\\c{c}ois Lauze, Marco Loog","submitted_at":"2017-07-10T12:01:30Z","abstract_excerpt":"We start out by demonstrating that an elementary learning task, corresponding to the training of a single linear neuron in a convolutional neural network, can be solved for feature spaces of very high dimensionality. In a second step, acknowledging that such high-dimensional learning tasks typically benefit from some form of regularization and arguing that the problem of scale has not been taken care of in a very satisfactory manner, we come to a combined resolution of both of these shortcomings by proposing a form of scale regularization. Moreover, using variational method, this regularizatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.02813","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":""},"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":"2026-05-18T00:40:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ld4s57mCNJ6aDsmwrXClj5MKLrV/f72SqgIFod6Rl7s6OwjjpypiaGjQJGCecxrFvkS5EghsLynTrFLwyPsQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T20:36:25.809927Z"},"content_sha256":"7beb5619554df84cf47aba7d848a18b9ca490a5355a0b1675cb60fe6f8c1b637","schema_version":"1.0","event_id":"sha256:7beb5619554df84cf47aba7d848a18b9ca490a5355a0b1675cb60fe6f8c1b637"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WOBH4HSNLVOBNO7PZFUTDXF2XS/bundle.json","state_url":"https://pith.science/pith/WOBH4HSNLVOBNO7PZFUTDXF2XS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WOBH4HSNLVOBNO7PZFUTDXF2XS/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":"2026-05-23T20:36:25Z","links":{"resolver":"https://pith.science/pith/WOBH4HSNLVOBNO7PZFUTDXF2XS","bundle":"https://pith.science/pith/WOBH4HSNLVOBNO7PZFUTDXF2XS/bundle.json","state":"https://pith.science/pith/WOBH4HSNLVOBNO7PZFUTDXF2XS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WOBH4HSNLVOBNO7PZFUTDXF2XS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WOBH4HSNLVOBNO7PZFUTDXF2XS","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":"ecac18ae294298c167459b5c74f304f62c9efb73f9248ccdef2c0ce60c7620e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-10T12:01:30Z","title_canon_sha256":"66dad0489a6d52dea08b1fb0e968a561da7b449fbd5ce01c4cbb8477dad0d3c0"},"schema_version":"1.0","source":{"id":"1707.02813","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.02813","created_at":"2026-05-18T00:40:35Z"},{"alias_kind":"arxiv_version","alias_value":"1707.02813v1","created_at":"2026-05-18T00:40:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.02813","created_at":"2026-05-18T00:40:35Z"},{"alias_kind":"pith_short_12","alias_value":"WOBH4HSNLVOB","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WOBH4HSNLVOBNO7P","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WOBH4HSN","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:7beb5619554df84cf47aba7d848a18b9ca490a5355a0b1675cb60fe6f8c1b637","target":"graph","created_at":"2026-05-18T00:40:35Z","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":"We start out by demonstrating that an elementary learning task, corresponding to the training of a single linear neuron in a convolutional neural network, can be solved for feature spaces of very high dimensionality. In a second step, acknowledging that such high-dimensional learning tasks typically benefit from some form of regularization and arguing that the problem of scale has not been taken care of in a very satisfactory manner, we come to a combined resolution of both of these shortcomings by proposing a form of scale regularization. Moreover, using variational method, this regularizatio","authors_text":"Fran\\c{c}ois Lauze, Marco Loog","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-10T12:01:30Z","title":"Scale-Regularized Filter Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.02813","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":"sha256:36540d87ed64ad68667cca288559f8e10419121ee9ac0ac76bdda4f37731df2f","target":"record","created_at":"2026-05-18T00:40:35Z","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":"ecac18ae294298c167459b5c74f304f62c9efb73f9248ccdef2c0ce60c7620e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-10T12:01:30Z","title_canon_sha256":"66dad0489a6d52dea08b1fb0e968a561da7b449fbd5ce01c4cbb8477dad0d3c0"},"schema_version":"1.0","source":{"id":"1707.02813","kind":"arxiv","version":1}},"canonical_sha256":"b3827e1e4d5d5c16bbefc96931dcbabcbc57dff002e295ec19502e6cdd26900e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3827e1e4d5d5c16bbefc96931dcbabcbc57dff002e295ec19502e6cdd26900e","first_computed_at":"2026-05-18T00:40:35.725676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:35.725676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i0zupSMbCcTyVUMQJ85Pk/kxoK9sSAwmN6SkxnhuBANaBjswkSYgi5dhYwIBEq4g6A/oUDygIqQ9LrQHz8MPDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:35.726260Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.02813","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36540d87ed64ad68667cca288559f8e10419121ee9ac0ac76bdda4f37731df2f","sha256:7beb5619554df84cf47aba7d848a18b9ca490a5355a0b1675cb60fe6f8c1b637"],"state_sha256":"63a69685138fc40f4f8cc832ba350bb887b334ccd712a482b03376af23460583"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RO9F6kuD7cH9l7QZmeByg7FMxsNTOlJ7XYSC+KS1pL+m383b0c2wp/pDNsHb7Cm6+atAjlR3EuX3HQJAI5dYCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T20:36:25.812198Z","bundle_sha256":"6bf39294954f8121a4474ebd81bc847ab2d031fc121c442e7a8bfba66e9f8b8a"}}