{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:RTWZEYAJSV4E3FU3TOQEM7UJST","short_pith_number":"pith:RTWZEYAJ","canonical_record":{"source":{"id":"1512.06293","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2015-12-19T22:31:24Z","cross_cats_sorted":["cs.AI","cs.LG","math.FA","math.IT","stat.ML"],"title_canon_sha256":"278fd1ad6966a0ec4068541afe7dedb02b4476865c4e97bdcb946155d4d8a78a","abstract_canon_sha256":"723e6014024264b8df70b4adf48974903fdd99db984c7f97500bf243e513c8c9"},"schema_version":"1.0"},"canonical_sha256":"8ced92600995784d969b9ba0467e8994ffe311dd9bbbdec2291b979dbfa4eb51","source":{"kind":"arxiv","id":"1512.06293","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.06293","created_at":"2026-05-18T00:32:15Z"},{"alias_kind":"arxiv_version","alias_value":"1512.06293v3","created_at":"2026-05-18T00:32:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.06293","created_at":"2026-05-18T00:32:15Z"},{"alias_kind":"pith_short_12","alias_value":"RTWZEYAJSV4E","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RTWZEYAJSV4E3FU3","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RTWZEYAJ","created_at":"2026-05-18T12:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:RTWZEYAJSV4E3FU3TOQEM7UJST","target":"record","payload":{"canonical_record":{"source":{"id":"1512.06293","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2015-12-19T22:31:24Z","cross_cats_sorted":["cs.AI","cs.LG","math.FA","math.IT","stat.ML"],"title_canon_sha256":"278fd1ad6966a0ec4068541afe7dedb02b4476865c4e97bdcb946155d4d8a78a","abstract_canon_sha256":"723e6014024264b8df70b4adf48974903fdd99db984c7f97500bf243e513c8c9"},"schema_version":"1.0"},"canonical_sha256":"8ced92600995784d969b9ba0467e8994ffe311dd9bbbdec2291b979dbfa4eb51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:15.295025Z","signature_b64":"rD6NPXNRfnhTzMMAuP8HxEEFxt7GAw+mqUri3xHZq3QFIy2zLBqqfHx1zKeZnB9M4tYFJub1VbVFITNOZwpFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ced92600995784d969b9ba0467e8994ffe311dd9bbbdec2291b979dbfa4eb51","last_reissued_at":"2026-05-18T00:32:15.294493Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:15.294493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.06293","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:32:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VptEsdTMAuN2Tky814RvWCo5wwDssUXKH64ljue0TW4JWM0dlrhhQ2KEL3jBv3Fh3wY1dq5SBM6sJfWbemJZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:10:00.815524Z"},"content_sha256":"92cf60d4a60384fd958fd388be5d38753b7985711b53b91b19bee410deac4dc4","schema_version":"1.0","event_id":"sha256:92cf60d4a60384fd958fd388be5d38753b7985711b53b91b19bee410deac4dc4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:RTWZEYAJSV4E3FU3TOQEM7UJST","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.FA","math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Helmut B\\\"olcskei, Thomas Wiatowski","submitted_at":"2015-12-19T22:31:24Z","abstract_excerpt":"Deep convolutional neural networks have led to breakthrough results in numerous practical machine learning tasks such as classification of images in the ImageNet data set, control-policy-learning to play Atari games or the board game Go, and image captioning. Many of these applications first perform feature extraction and then feed the results thereof into a trainable classifier. The mathematical analysis of deep convolutional neural networks for feature extraction was initiated by Mallat, 2012. Specifically, Mallat considered so-called scattering networks based on a wavelet transform followed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.06293","kind":"arxiv","version":3},"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":"2026-05-18T00:32:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"10sQ1La4JuCBokxGC1qOtg9673FGMCOEg490Y+PRxJO638VFA6KCRD0TaeBpJh3FCoPbZoWw/UBEkAbwVvznDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:10:00.816133Z"},"content_sha256":"c8f6b2a030735891910723b2f0a19d857ec4bff1bd4bf328e9cc558bcd697eeb","schema_version":"1.0","event_id":"sha256:c8f6b2a030735891910723b2f0a19d857ec4bff1bd4bf328e9cc558bcd697eeb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RTWZEYAJSV4E3FU3TOQEM7UJST/bundle.json","state_url":"https://pith.science/pith/RTWZEYAJSV4E3FU3TOQEM7UJST/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RTWZEYAJSV4E3FU3TOQEM7UJST/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":"2026-05-27T10:10:00Z","links":{"resolver":"https://pith.science/pith/RTWZEYAJSV4E3FU3TOQEM7UJST","bundle":"https://pith.science/pith/RTWZEYAJSV4E3FU3TOQEM7UJST/bundle.json","state":"https://pith.science/pith/RTWZEYAJSV4E3FU3TOQEM7UJST/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RTWZEYAJSV4E3FU3TOQEM7UJST/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:RTWZEYAJSV4E3FU3TOQEM7UJST","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":"723e6014024264b8df70b4adf48974903fdd99db984c7f97500bf243e513c8c9","cross_cats_sorted":["cs.AI","cs.LG","math.FA","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2015-12-19T22:31:24Z","title_canon_sha256":"278fd1ad6966a0ec4068541afe7dedb02b4476865c4e97bdcb946155d4d8a78a"},"schema_version":"1.0","source":{"id":"1512.06293","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.06293","created_at":"2026-05-18T00:32:15Z"},{"alias_kind":"arxiv_version","alias_value":"1512.06293v3","created_at":"2026-05-18T00:32:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.06293","created_at":"2026-05-18T00:32:15Z"},{"alias_kind":"pith_short_12","alias_value":"RTWZEYAJSV4E","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RTWZEYAJSV4E3FU3","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RTWZEYAJ","created_at":"2026-05-18T12:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:c8f6b2a030735891910723b2f0a19d857ec4bff1bd4bf328e9cc558bcd697eeb","target":"graph","created_at":"2026-05-18T00:32:15Z","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":"Deep convolutional neural networks have led to breakthrough results in numerous practical machine learning tasks such as classification of images in the ImageNet data set, control-policy-learning to play Atari games or the board game Go, and image captioning. Many of these applications first perform feature extraction and then feed the results thereof into a trainable classifier. The mathematical analysis of deep convolutional neural networks for feature extraction was initiated by Mallat, 2012. Specifically, Mallat considered so-called scattering networks based on a wavelet transform followed","authors_text":"Helmut B\\\"olcskei, Thomas Wiatowski","cross_cats":["cs.AI","cs.LG","math.FA","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2015-12-19T22:31:24Z","title":"A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.06293","kind":"arxiv","version":3},"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":"sha256:92cf60d4a60384fd958fd388be5d38753b7985711b53b91b19bee410deac4dc4","target":"record","created_at":"2026-05-18T00:32:15Z","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":"723e6014024264b8df70b4adf48974903fdd99db984c7f97500bf243e513c8c9","cross_cats_sorted":["cs.AI","cs.LG","math.FA","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2015-12-19T22:31:24Z","title_canon_sha256":"278fd1ad6966a0ec4068541afe7dedb02b4476865c4e97bdcb946155d4d8a78a"},"schema_version":"1.0","source":{"id":"1512.06293","kind":"arxiv","version":3}},"canonical_sha256":"8ced92600995784d969b9ba0467e8994ffe311dd9bbbdec2291b979dbfa4eb51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ced92600995784d969b9ba0467e8994ffe311dd9bbbdec2291b979dbfa4eb51","first_computed_at":"2026-05-18T00:32:15.294493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:15.294493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rD6NPXNRfnhTzMMAuP8HxEEFxt7GAw+mqUri3xHZq3QFIy2zLBqqfHx1zKeZnB9M4tYFJub1VbVFITNOZwpFDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:15.295025Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.06293","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92cf60d4a60384fd958fd388be5d38753b7985711b53b91b19bee410deac4dc4","sha256:c8f6b2a030735891910723b2f0a19d857ec4bff1bd4bf328e9cc558bcd697eeb"],"state_sha256":"5255d1e6f9e4bfb132896b123c24cfc332a1513df02f19515e1c636ccaa4cb5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LlqdkqS1UVYo9YH/9UzZ+cVIv0xNpH6ppQaL26N50TFaIr2U6E2shvj30snr0jxIxcf4wbWqJy7rCRW61PRtDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T10:10:00.819358Z","bundle_sha256":"292b9aa3d6a7ab238747428bad32b680b7e42cbcf252fbe6900ba8c8dda7d5a3"}}