{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DFGECB5MPDNXH724JUV56NOGRL","short_pith_number":"pith:DFGECB5M","canonical_record":{"source":{"id":"1803.08416","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-22T15:49:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5f87e8a46d83fdfae578467b32b3cad0410f559209cc6398a3fa8260cc8cfb5f","abstract_canon_sha256":"de8a75d21505aaacf345cfba8b766a4522ab22af1e00881e53e03234826a1a4e"},"schema_version":"1.0"},"canonical_sha256":"194c4107ac78db73ff5c4d2bdf35c68ac8703945e6601569717e74eeb7991e9e","source":{"kind":"arxiv","id":"1803.08416","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.08416","created_at":"2026-05-18T00:20:22Z"},{"alias_kind":"arxiv_version","alias_value":"1803.08416v1","created_at":"2026-05-18T00:20:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08416","created_at":"2026-05-18T00:20:22Z"},{"alias_kind":"pith_short_12","alias_value":"DFGECB5MPDNX","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DFGECB5MPDNXH724","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DFGECB5M","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DFGECB5MPDNXH724JUV56NOGRL","target":"record","payload":{"canonical_record":{"source":{"id":"1803.08416","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-22T15:49:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5f87e8a46d83fdfae578467b32b3cad0410f559209cc6398a3fa8260cc8cfb5f","abstract_canon_sha256":"de8a75d21505aaacf345cfba8b766a4522ab22af1e00881e53e03234826a1a4e"},"schema_version":"1.0"},"canonical_sha256":"194c4107ac78db73ff5c4d2bdf35c68ac8703945e6601569717e74eeb7991e9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:22.889441Z","signature_b64":"+RNEUDoKdq+RygcPa3r6hjmBpI0WhRn/Gxw/9qoKnA1xXmE1tYl89nzR6TOjwTBgqsJ9R2uYKB2nLSGT2NLyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"194c4107ac78db73ff5c4d2bdf35c68ac8703945e6601569717e74eeb7991e9e","last_reissued_at":"2026-05-18T00:20:22.888985Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:22.888985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.08416","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":"2026-05-18T00:20:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tWextcZdC8x19tdk2On7ggL9/XWKgCNyCoKKbxz1Vk6oSlfkERpE0C1L8SwH/RGO+r0RZGK7WiPNsfS6moHbCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:24:22.478446Z"},"content_sha256":"3f8cbea9c6331682157197acdd769a9e5583be45c578bd2a49b9d2c64a93d35e","schema_version":"1.0","event_id":"sha256:3f8cbea9c6331682157197acdd769a9e5583be45c578bd2a49b9d2c64a93d35e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DFGECB5MPDNXH724JUV56NOGRL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Demystifying Deep Learning: A Geometric Approach to Iterative Projections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashkan Panahi, Hamid Krim, Liyi Dai","submitted_at":"2018-03-22T15:49:32Z","abstract_excerpt":"Parametric approaches to Learning, such as deep learning (DL), are highly popular in nonlinear regression, in spite of their extremely difficult training with their increasing complexity (e.g. number of layers in DL). In this paper, we present an alternative semi-parametric framework which foregoes the ordinarily required feedback, by introducing the novel idea of geometric regularization. We show that certain deep learning techniques such as residual network (ResNet) architecture are closely related to our approach. Hence, our technique can be used to analyze these types of deep learning. Mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08416","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":"2026-05-18T00:20:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jtVPMo+j3i3IFaIJq1n9icu0i8ciTl0P81v5DK5vuuGK9Bp8FskH3cytndTz/PK3yNj455fDSAIBSw+DQ7T3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:24:22.479138Z"},"content_sha256":"555e246fedf489c3b6f5f3cb7a271c82b823dc8bd8be3b0057daacdc396757ff","schema_version":"1.0","event_id":"sha256:555e246fedf489c3b6f5f3cb7a271c82b823dc8bd8be3b0057daacdc396757ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DFGECB5MPDNXH724JUV56NOGRL/bundle.json","state_url":"https://pith.science/pith/DFGECB5MPDNXH724JUV56NOGRL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DFGECB5MPDNXH724JUV56NOGRL/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":"2026-05-25T20:24:22Z","links":{"resolver":"https://pith.science/pith/DFGECB5MPDNXH724JUV56NOGRL","bundle":"https://pith.science/pith/DFGECB5MPDNXH724JUV56NOGRL/bundle.json","state":"https://pith.science/pith/DFGECB5MPDNXH724JUV56NOGRL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DFGECB5MPDNXH724JUV56NOGRL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DFGECB5MPDNXH724JUV56NOGRL","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":"de8a75d21505aaacf345cfba8b766a4522ab22af1e00881e53e03234826a1a4e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-22T15:49:32Z","title_canon_sha256":"5f87e8a46d83fdfae578467b32b3cad0410f559209cc6398a3fa8260cc8cfb5f"},"schema_version":"1.0","source":{"id":"1803.08416","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.08416","created_at":"2026-05-18T00:20:22Z"},{"alias_kind":"arxiv_version","alias_value":"1803.08416v1","created_at":"2026-05-18T00:20:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08416","created_at":"2026-05-18T00:20:22Z"},{"alias_kind":"pith_short_12","alias_value":"DFGECB5MPDNX","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DFGECB5MPDNXH724","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DFGECB5M","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:555e246fedf489c3b6f5f3cb7a271c82b823dc8bd8be3b0057daacdc396757ff","target":"graph","created_at":"2026-05-18T00:20:22Z","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":"Parametric approaches to Learning, such as deep learning (DL), are highly popular in nonlinear regression, in spite of their extremely difficult training with their increasing complexity (e.g. number of layers in DL). In this paper, we present an alternative semi-parametric framework which foregoes the ordinarily required feedback, by introducing the novel idea of geometric regularization. We show that certain deep learning techniques such as residual network (ResNet) architecture are closely related to our approach. Hence, our technique can be used to analyze these types of deep learning. Mor","authors_text":"Ashkan Panahi, Hamid Krim, Liyi Dai","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-22T15:49:32Z","title":"Demystifying Deep Learning: A Geometric Approach to Iterative Projections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08416","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":"sha256:3f8cbea9c6331682157197acdd769a9e5583be45c578bd2a49b9d2c64a93d35e","target":"record","created_at":"2026-05-18T00:20:22Z","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":"de8a75d21505aaacf345cfba8b766a4522ab22af1e00881e53e03234826a1a4e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-22T15:49:32Z","title_canon_sha256":"5f87e8a46d83fdfae578467b32b3cad0410f559209cc6398a3fa8260cc8cfb5f"},"schema_version":"1.0","source":{"id":"1803.08416","kind":"arxiv","version":1}},"canonical_sha256":"194c4107ac78db73ff5c4d2bdf35c68ac8703945e6601569717e74eeb7991e9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"194c4107ac78db73ff5c4d2bdf35c68ac8703945e6601569717e74eeb7991e9e","first_computed_at":"2026-05-18T00:20:22.888985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:22.888985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+RNEUDoKdq+RygcPa3r6hjmBpI0WhRn/Gxw/9qoKnA1xXmE1tYl89nzR6TOjwTBgqsJ9R2uYKB2nLSGT2NLyCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:22.889441Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.08416","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f8cbea9c6331682157197acdd769a9e5583be45c578bd2a49b9d2c64a93d35e","sha256:555e246fedf489c3b6f5f3cb7a271c82b823dc8bd8be3b0057daacdc396757ff"],"state_sha256":"05794da42d95d61e96e8962710a4776d34c89ab1e0eac81c8a541f62de08b247"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lLZG0PK1NAloGcI0YKhF1+4q3LMYEsbrwYBcjEwSzi1Y2jAIxuZmbHmeo3WrlaBhb0NGvpEw0EnBR6JcogYTDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:24:22.482948Z","bundle_sha256":"72562dfc906d99526d664efcaaa13d61f60f844fb4a7b6ff553ed1ce209ff25c"}}