{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:XSCQ2LX3XOB7N5VCRLMUU7PSH5","short_pith_number":"pith:XSCQ2LX3","canonical_record":{"source":{"id":"1710.08177","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-10-23T10:06:15Z","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"title_canon_sha256":"2278ed2f7b921c07176b58474149c187c41a18b3085ca230579c1fb06fafac45","abstract_canon_sha256":"73b39fb198e3870e940e7d6a9de9fdc40f34b49a7989e9a7730505c3a50a379a"},"schema_version":"1.0"},"canonical_sha256":"bc850d2efbbb83f6f6a28ad94a7df23f4b914741ec5331722e3d6d646d44a292","source":{"kind":"arxiv","id":"1710.08177","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.08177","created_at":"2026-05-18T00:32:16Z"},{"alias_kind":"arxiv_version","alias_value":"1710.08177v1","created_at":"2026-05-18T00:32:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.08177","created_at":"2026-05-18T00:32:16Z"},{"alias_kind":"pith_short_12","alias_value":"XSCQ2LX3XOB7","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"XSCQ2LX3XOB7N5VC","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"XSCQ2LX3","created_at":"2026-05-18T12:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:XSCQ2LX3XOB7N5VCRLMUU7PSH5","target":"record","payload":{"canonical_record":{"source":{"id":"1710.08177","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-10-23T10:06:15Z","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"title_canon_sha256":"2278ed2f7b921c07176b58474149c187c41a18b3085ca230579c1fb06fafac45","abstract_canon_sha256":"73b39fb198e3870e940e7d6a9de9fdc40f34b49a7989e9a7730505c3a50a379a"},"schema_version":"1.0"},"canonical_sha256":"bc850d2efbbb83f6f6a28ad94a7df23f4b914741ec5331722e3d6d646d44a292","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:16.995824Z","signature_b64":"wUSMbTHvWATmDe22I8gOw4FBiu1TpFEgh+p/8X+fH8u9mqg6jeYtsReSJ55GayhPDRODM4chFuPjcnLIRp/DBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc850d2efbbb83f6f6a28ad94a7df23f4b914741ec5331722e3d6d646d44a292","last_reissued_at":"2026-05-18T00:32:16.995106Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:16.995106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.08177","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":"2026-05-18T00:32:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3uTqY09+fgD6ce2lr0PVjLcz6RAV08yA9bH4u15MgVnjbaATSQO+c+AAFtjTALBig8t75KkKpyVYJXmZ5lh7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:55:56.971519Z"},"content_sha256":"dd6eb199de48cbc09f19d097e08b310d39aef02591e26a6f2cfbebe03ba509c6","schema_version":"1.0","event_id":"sha256:dd6eb199de48cbc09f19d097e08b310d39aef02591e26a6f2cfbebe03ba509c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:XSCQ2LX3XOB7N5VCRLMUU7PSH5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Progressive Learning for Systematic Design of Large Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Alireza M. Javid, Mikael Skoglund, Mostafa Sadeghi, Partha P. Mitra, Saikat Chatterjee","submitted_at":"2017-10-23T10:06:15Z","abstract_excerpt":"We develop an algorithm for systematic design of a large artificial neural network using a progression property. We find that some non-linear functions, such as the rectifier linear unit and its derivatives, hold the property. The systematic design addresses the choice of network size and regularization of parameters. The number of nodes and layers in network increases in progression with the objective of consistently reducing an appropriate cost. Each layer is optimized at a time, where appropriate parameters are learned using convex optimization. Regularization parameters for convex optimiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.08177","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":"2026-05-18T00:32:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4PuQfdAcTM76X5hByIwvUgiSq23BrBeaSHgidoCs6flVecJ9zx0aVo+JCFN8YDCzpRHIn8OtJVQ1JhVK5NMLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:55:56.971880Z"},"content_sha256":"de629d8a06e026573a309fe7a213ca99d0224fb4fdd2ac3078b071ab69a6ab53","schema_version":"1.0","event_id":"sha256:de629d8a06e026573a309fe7a213ca99d0224fb4fdd2ac3078b071ab69a6ab53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XSCQ2LX3XOB7N5VCRLMUU7PSH5/bundle.json","state_url":"https://pith.science/pith/XSCQ2LX3XOB7N5VCRLMUU7PSH5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XSCQ2LX3XOB7N5VCRLMUU7PSH5/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":"2026-05-31T09:55:56Z","links":{"resolver":"https://pith.science/pith/XSCQ2LX3XOB7N5VCRLMUU7PSH5","bundle":"https://pith.science/pith/XSCQ2LX3XOB7N5VCRLMUU7PSH5/bundle.json","state":"https://pith.science/pith/XSCQ2LX3XOB7N5VCRLMUU7PSH5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XSCQ2LX3XOB7N5VCRLMUU7PSH5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XSCQ2LX3XOB7N5VCRLMUU7PSH5","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":"73b39fb198e3870e940e7d6a9de9fdc40f34b49a7989e9a7730505c3a50a379a","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-10-23T10:06:15Z","title_canon_sha256":"2278ed2f7b921c07176b58474149c187c41a18b3085ca230579c1fb06fafac45"},"schema_version":"1.0","source":{"id":"1710.08177","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.08177","created_at":"2026-05-18T00:32:16Z"},{"alias_kind":"arxiv_version","alias_value":"1710.08177v1","created_at":"2026-05-18T00:32:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.08177","created_at":"2026-05-18T00:32:16Z"},{"alias_kind":"pith_short_12","alias_value":"XSCQ2LX3XOB7","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"XSCQ2LX3XOB7N5VC","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"XSCQ2LX3","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:de629d8a06e026573a309fe7a213ca99d0224fb4fdd2ac3078b071ab69a6ab53","target":"graph","created_at":"2026-05-18T00:32:16Z","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 develop an algorithm for systematic design of a large artificial neural network using a progression property. We find that some non-linear functions, such as the rectifier linear unit and its derivatives, hold the property. The systematic design addresses the choice of network size and regularization of parameters. The number of nodes and layers in network increases in progression with the objective of consistently reducing an appropriate cost. Each layer is optimized at a time, where appropriate parameters are learned using convex optimization. Regularization parameters for convex optimiza","authors_text":"Alireza M. Javid, Mikael Skoglund, Mostafa Sadeghi, Partha P. Mitra, Saikat Chatterjee","cross_cats":["cs.CV","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-10-23T10:06:15Z","title":"Progressive Learning for Systematic Design of Large Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.08177","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:dd6eb199de48cbc09f19d097e08b310d39aef02591e26a6f2cfbebe03ba509c6","target":"record","created_at":"2026-05-18T00:32:16Z","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":"73b39fb198e3870e940e7d6a9de9fdc40f34b49a7989e9a7730505c3a50a379a","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-10-23T10:06:15Z","title_canon_sha256":"2278ed2f7b921c07176b58474149c187c41a18b3085ca230579c1fb06fafac45"},"schema_version":"1.0","source":{"id":"1710.08177","kind":"arxiv","version":1}},"canonical_sha256":"bc850d2efbbb83f6f6a28ad94a7df23f4b914741ec5331722e3d6d646d44a292","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc850d2efbbb83f6f6a28ad94a7df23f4b914741ec5331722e3d6d646d44a292","first_computed_at":"2026-05-18T00:32:16.995106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:16.995106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wUSMbTHvWATmDe22I8gOw4FBiu1TpFEgh+p/8X+fH8u9mqg6jeYtsReSJ55GayhPDRODM4chFuPjcnLIRp/DBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:16.995824Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.08177","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd6eb199de48cbc09f19d097e08b310d39aef02591e26a6f2cfbebe03ba509c6","sha256:de629d8a06e026573a309fe7a213ca99d0224fb4fdd2ac3078b071ab69a6ab53"],"state_sha256":"4c8aba744aef90efb1e4b33d7eacc301f1f0c4fc65f91b8b172b65dd6ad7ed72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kqJhYsL9AVUabnP2Km4gEE2ZG2eIxFqWxN20LdUPzHAyHK270kWPILZu3LL5+mjxveksA4CQQaXdlnb7rnMpDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T09:55:56.974536Z","bundle_sha256":"5346ca3d9bf9bbcd62a4b625da27d38e16a625ba86a5aa957e479c34ca617a4f"}}