{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4MWX6KMQ6DHZVEYVPG3OILIVFE","short_pith_number":"pith:4MWX6KMQ","canonical_record":{"source":{"id":"1901.00035","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-31T20:21:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c1c1f27ba54b65f3e95d092910e236c16a7f34ae30c3bd304b854987752074fa","abstract_canon_sha256":"9f3c7ab4600149722ec05a245b49a08fda8daca4d9d09b3f2d600e49946f5bbd"},"schema_version":"1.0"},"canonical_sha256":"e32d7f2990f0cf9a931579b6e42d152939fd1c982f905d63485a37c4fc472736","source":{"kind":"arxiv","id":"1901.00035","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.00035","created_at":"2026-05-17T23:57:07Z"},{"alias_kind":"arxiv_version","alias_value":"1901.00035v1","created_at":"2026-05-17T23:57:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.00035","created_at":"2026-05-17T23:57:07Z"},{"alias_kind":"pith_short_12","alias_value":"4MWX6KMQ6DHZ","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4MWX6KMQ6DHZVEYV","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4MWX6KMQ","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4MWX6KMQ6DHZVEYVPG3OILIVFE","target":"record","payload":{"canonical_record":{"source":{"id":"1901.00035","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-31T20:21:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c1c1f27ba54b65f3e95d092910e236c16a7f34ae30c3bd304b854987752074fa","abstract_canon_sha256":"9f3c7ab4600149722ec05a245b49a08fda8daca4d9d09b3f2d600e49946f5bbd"},"schema_version":"1.0"},"canonical_sha256":"e32d7f2990f0cf9a931579b6e42d152939fd1c982f905d63485a37c4fc472736","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:07.057450Z","signature_b64":"33ht/b7xrjM9zXpfMcm74LCW5VpgJBRLdIslVUPMsgTfM67XoVpkNH4vxycbr4f+EZOYBpGub0iufs5uQQ+/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e32d7f2990f0cf9a931579b6e42d152939fd1c982f905d63485a37c4fc472736","last_reissued_at":"2026-05-17T23:57:07.056783Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:07.056783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.00035","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":"2026-05-17T23:57:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kUMibCWpy7FtsJqshzFb0536UvseCUjtBmJ0ZVCVnlaD0/borgx52LcTRjMdIaWqaqSqwczNxDoCAvYPK2gwCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:53:21.046678Z"},"content_sha256":"97bafbe75eb734ee052e9ab21171e2e73888434753baef98d04e156428ffc57f","schema_version":"1.0","event_id":"sha256:97bafbe75eb734ee052e9ab21171e2e73888434753baef98d04e156428ffc57f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4MWX6KMQ6DHZVEYVPG3OILIVFE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convex Relaxations of Convolutional Neural Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Burak Bartan, Mert Pilanci","submitted_at":"2018-12-31T20:21:48Z","abstract_excerpt":"We propose convex relaxations for convolutional neural nets with one hidden layer where the output weights are fixed. For convex activation functions such as rectified linear units, the relaxations are convex second order cone programs which can be solved very efficiently. We prove that the relaxation recovers the global minimum under a planted model assumption, given sufficiently many training samples from a Gaussian distribution. We also identify a phase transition phenomenon in recovering the global minimum for the relaxation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.00035","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":"2026-05-17T23:57:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9q8UUQMHZGe0ZesJB8MeM6/sgAqT9uM3Eec1jAtl1QQ7rJI5986yaN8pjBdycf1FvM0aMkw7rymc8cQVTBfADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:53:21.047021Z"},"content_sha256":"d343e77ef614fba9760669994ab66e812fcfec91cd96c2a60d91135441d8f9f3","schema_version":"1.0","event_id":"sha256:d343e77ef614fba9760669994ab66e812fcfec91cd96c2a60d91135441d8f9f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4MWX6KMQ6DHZVEYVPG3OILIVFE/bundle.json","state_url":"https://pith.science/pith/4MWX6KMQ6DHZVEYVPG3OILIVFE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4MWX6KMQ6DHZVEYVPG3OILIVFE/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":"2026-05-27T20:53:21Z","links":{"resolver":"https://pith.science/pith/4MWX6KMQ6DHZVEYVPG3OILIVFE","bundle":"https://pith.science/pith/4MWX6KMQ6DHZVEYVPG3OILIVFE/bundle.json","state":"https://pith.science/pith/4MWX6KMQ6DHZVEYVPG3OILIVFE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4MWX6KMQ6DHZVEYVPG3OILIVFE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4MWX6KMQ6DHZVEYVPG3OILIVFE","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":"9f3c7ab4600149722ec05a245b49a08fda8daca4d9d09b3f2d600e49946f5bbd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-31T20:21:48Z","title_canon_sha256":"c1c1f27ba54b65f3e95d092910e236c16a7f34ae30c3bd304b854987752074fa"},"schema_version":"1.0","source":{"id":"1901.00035","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.00035","created_at":"2026-05-17T23:57:07Z"},{"alias_kind":"arxiv_version","alias_value":"1901.00035v1","created_at":"2026-05-17T23:57:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.00035","created_at":"2026-05-17T23:57:07Z"},{"alias_kind":"pith_short_12","alias_value":"4MWX6KMQ6DHZ","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4MWX6KMQ6DHZVEYV","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4MWX6KMQ","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:d343e77ef614fba9760669994ab66e812fcfec91cd96c2a60d91135441d8f9f3","target":"graph","created_at":"2026-05-17T23:57:07Z","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 convex relaxations for convolutional neural nets with one hidden layer where the output weights are fixed. For convex activation functions such as rectified linear units, the relaxations are convex second order cone programs which can be solved very efficiently. We prove that the relaxation recovers the global minimum under a planted model assumption, given sufficiently many training samples from a Gaussian distribution. We also identify a phase transition phenomenon in recovering the global minimum for the relaxation.","authors_text":"Burak Bartan, Mert Pilanci","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-31T20:21:48Z","title":"Convex Relaxations of Convolutional Neural Nets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.00035","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":"sha256:97bafbe75eb734ee052e9ab21171e2e73888434753baef98d04e156428ffc57f","target":"record","created_at":"2026-05-17T23:57:07Z","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":"9f3c7ab4600149722ec05a245b49a08fda8daca4d9d09b3f2d600e49946f5bbd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-31T20:21:48Z","title_canon_sha256":"c1c1f27ba54b65f3e95d092910e236c16a7f34ae30c3bd304b854987752074fa"},"schema_version":"1.0","source":{"id":"1901.00035","kind":"arxiv","version":1}},"canonical_sha256":"e32d7f2990f0cf9a931579b6e42d152939fd1c982f905d63485a37c4fc472736","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e32d7f2990f0cf9a931579b6e42d152939fd1c982f905d63485a37c4fc472736","first_computed_at":"2026-05-17T23:57:07.056783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:07.056783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"33ht/b7xrjM9zXpfMcm74LCW5VpgJBRLdIslVUPMsgTfM67XoVpkNH4vxycbr4f+EZOYBpGub0iufs5uQQ+/BA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:07.057450Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.00035","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97bafbe75eb734ee052e9ab21171e2e73888434753baef98d04e156428ffc57f","sha256:d343e77ef614fba9760669994ab66e812fcfec91cd96c2a60d91135441d8f9f3"],"state_sha256":"4dc389af0d4b29b7ed7eb9c79d5adfdaa3461433cce9a34816072656c8f0df92"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3MzI/lcc3bPOkjpdNuW/Efc/PyFXMi6Ef9GLtBZrVdx45Xgq/OYpcjBohCOGJJcLWgVN9NggfLQKq9t7TRmsDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T20:53:21.049209Z","bundle_sha256":"afec25f0e054359c5c8d25b41e3d3a23e71487ab09d50bbfbf9b791bb97a0c90"}}