{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:55OMM3SQCAG4FTWZ36GZSR64X2","short_pith_number":"pith:55OMM3SQ","canonical_record":{"source":{"id":"1811.01501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T03:33:24Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"3361e87c6725be414260dbe46980a604a672f6c6ae8ff6a9f987c05e18d65281","abstract_canon_sha256":"53bd6f7592f314f142e472056ca861f04ccaeb9a67f4d055884471cecdc46600"},"schema_version":"1.0"},"canonical_sha256":"ef5cc66e50100dc2ced9df8d9947dcbe9ae308bd6ec0ae8775d45f62c702efdf","source":{"kind":"arxiv","id":"1811.01501","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.01501","created_at":"2026-05-18T00:01:34Z"},{"alias_kind":"arxiv_version","alias_value":"1811.01501v1","created_at":"2026-05-18T00:01:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01501","created_at":"2026-05-18T00:01:34Z"},{"alias_kind":"pith_short_12","alias_value":"55OMM3SQCAG4","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"55OMM3SQCAG4FTWZ","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"55OMM3SQ","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:55OMM3SQCAG4FTWZ36GZSR64X2","target":"record","payload":{"canonical_record":{"source":{"id":"1811.01501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T03:33:24Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"3361e87c6725be414260dbe46980a604a672f6c6ae8ff6a9f987c05e18d65281","abstract_canon_sha256":"53bd6f7592f314f142e472056ca861f04ccaeb9a67f4d055884471cecdc46600"},"schema_version":"1.0"},"canonical_sha256":"ef5cc66e50100dc2ced9df8d9947dcbe9ae308bd6ec0ae8775d45f62c702efdf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:34.117590Z","signature_b64":"9jcsRZ2ky3SnJpH9BR93G1IlXpSleMIVrSTjG1/pPsmh2iMEEuLXl4k77XGprjyEYIhAHfM/gRmg1f9WiyhwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef5cc66e50100dc2ced9df8d9947dcbe9ae308bd6ec0ae8775d45f62c702efdf","last_reissued_at":"2026-05-18T00:01:34.117001Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:34.117001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.01501","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":"2026-05-18T00:01:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WtgD6kWFOUOkIu3EW364lS/xK4OyJ18XPRS7EeEIMwAFn/rF7/cSitwRA0aGvuLK6esgMXmSL/BbG+2ptNZiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:58:58.229148Z"},"content_sha256":"f57391be58e8123249598a4a057af59f7c642f97876550cf626eeca33180b2eb","schema_version":"1.0","event_id":"sha256:f57391be58e8123249598a4a057af59f7c642f97876550cf626eeca33180b2eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:55OMM3SQCAG4FTWZ36GZSR64X2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lifted Proximal Operator Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cong Fang, Jia Li, Zhouchen Lin","submitted_at":"2018-11-05T03:33:24Z","abstract_excerpt":"We propose a new optimization method for training feed-forward neural networks. By rewriting the activation function as an equivalent proximal operator, we approximate a feed-forward neural network by adding the proximal operators to the objective function as penalties, hence we call the lifted proximal operator machine (LPOM). LPOM is block multi-convex in all layer-wise weights and activations. This allows us to use block coordinate descent to update the layer-wise weights and activations in parallel. Most notably, we only use the mapping of the activation function itself, rather than its de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01501","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":"2026-05-18T00:01:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WQBCrHRVuXI81rTSR3RPeW0Hx/V1J+KzQ+Xgi/ivZ0/w0i2ri3ECyvXNZr924N8P8XCSB9eKDOoAaZqbyzJoDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:58:58.229523Z"},"content_sha256":"ed955af4f08cd3804ac60282d14d11c43ed7d96299a3384cdec8ca90f155d5c9","schema_version":"1.0","event_id":"sha256:ed955af4f08cd3804ac60282d14d11c43ed7d96299a3384cdec8ca90f155d5c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/55OMM3SQCAG4FTWZ36GZSR64X2/bundle.json","state_url":"https://pith.science/pith/55OMM3SQCAG4FTWZ36GZSR64X2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/55OMM3SQCAG4FTWZ36GZSR64X2/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":"2026-06-29T19:58:58Z","links":{"resolver":"https://pith.science/pith/55OMM3SQCAG4FTWZ36GZSR64X2","bundle":"https://pith.science/pith/55OMM3SQCAG4FTWZ36GZSR64X2/bundle.json","state":"https://pith.science/pith/55OMM3SQCAG4FTWZ36GZSR64X2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/55OMM3SQCAG4FTWZ36GZSR64X2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:55OMM3SQCAG4FTWZ36GZSR64X2","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":"53bd6f7592f314f142e472056ca861f04ccaeb9a67f4d055884471cecdc46600","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T03:33:24Z","title_canon_sha256":"3361e87c6725be414260dbe46980a604a672f6c6ae8ff6a9f987c05e18d65281"},"schema_version":"1.0","source":{"id":"1811.01501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.01501","created_at":"2026-05-18T00:01:34Z"},{"alias_kind":"arxiv_version","alias_value":"1811.01501v1","created_at":"2026-05-18T00:01:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01501","created_at":"2026-05-18T00:01:34Z"},{"alias_kind":"pith_short_12","alias_value":"55OMM3SQCAG4","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"55OMM3SQCAG4FTWZ","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"55OMM3SQ","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:ed955af4f08cd3804ac60282d14d11c43ed7d96299a3384cdec8ca90f155d5c9","target":"graph","created_at":"2026-05-18T00:01:34Z","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 propose a new optimization method for training feed-forward neural networks. By rewriting the activation function as an equivalent proximal operator, we approximate a feed-forward neural network by adding the proximal operators to the objective function as penalties, hence we call the lifted proximal operator machine (LPOM). LPOM is block multi-convex in all layer-wise weights and activations. This allows us to use block coordinate descent to update the layer-wise weights and activations in parallel. Most notably, we only use the mapping of the activation function itself, rather than its de","authors_text":"Cong Fang, Jia Li, Zhouchen Lin","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T03:33:24Z","title":"Lifted Proximal Operator Machines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01501","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:f57391be58e8123249598a4a057af59f7c642f97876550cf626eeca33180b2eb","target":"record","created_at":"2026-05-18T00:01:34Z","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":"53bd6f7592f314f142e472056ca861f04ccaeb9a67f4d055884471cecdc46600","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T03:33:24Z","title_canon_sha256":"3361e87c6725be414260dbe46980a604a672f6c6ae8ff6a9f987c05e18d65281"},"schema_version":"1.0","source":{"id":"1811.01501","kind":"arxiv","version":1}},"canonical_sha256":"ef5cc66e50100dc2ced9df8d9947dcbe9ae308bd6ec0ae8775d45f62c702efdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef5cc66e50100dc2ced9df8d9947dcbe9ae308bd6ec0ae8775d45f62c702efdf","first_computed_at":"2026-05-18T00:01:34.117001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:34.117001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9jcsRZ2ky3SnJpH9BR93G1IlXpSleMIVrSTjG1/pPsmh2iMEEuLXl4k77XGprjyEYIhAHfM/gRmg1f9WiyhwAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:34.117590Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.01501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f57391be58e8123249598a4a057af59f7c642f97876550cf626eeca33180b2eb","sha256:ed955af4f08cd3804ac60282d14d11c43ed7d96299a3384cdec8ca90f155d5c9"],"state_sha256":"efc7324c861b83baab0947846b0088240fefff70db3ee3b2ac16d571ca7cc83b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sLoPx+l0JUKsd2eUXszS5cz7tpetoUSaOV7+X1zVpwSz60rz5uYuNtNcKfsgBgkvrTbu9ZQ/omIZZoMJiWhyBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T19:58:58.231603Z","bundle_sha256":"a62285e99d92a87c40d1987e674895d5bd0ed3543d6092aa5f754a96649bbb01"}}