{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:W57HJLWLANS5HTWEAWECGCBNKP","short_pith_number":"pith:W57HJLWL","canonical_record":{"source":{"id":"1810.03592","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-10-08T17:36:18Z","cross_cats_sorted":[],"title_canon_sha256":"c9413ba72d127356d6cc7a023b96a64a7cdfafeb3c80e4cc42c21f572a3297e3","abstract_canon_sha256":"f2cef88d41fad5efb088ddb416592cc3b564820e032d2ce51c15714353dee31b"},"schema_version":"1.0"},"canonical_sha256":"b77e74aecb0365d3cec4058823082d53ee16cdd041887889b9dd192ca026637d","source":{"kind":"arxiv","id":"1810.03592","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03592","created_at":"2026-05-17T23:45:26Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03592v2","created_at":"2026-05-17T23:45:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03592","created_at":"2026-05-17T23:45:26Z"},{"alias_kind":"pith_short_12","alias_value":"W57HJLWLANS5","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"W57HJLWLANS5HTWE","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"W57HJLWL","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:W57HJLWLANS5HTWEAWECGCBNKP","target":"record","payload":{"canonical_record":{"source":{"id":"1810.03592","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-10-08T17:36:18Z","cross_cats_sorted":[],"title_canon_sha256":"c9413ba72d127356d6cc7a023b96a64a7cdfafeb3c80e4cc42c21f572a3297e3","abstract_canon_sha256":"f2cef88d41fad5efb088ddb416592cc3b564820e032d2ce51c15714353dee31b"},"schema_version":"1.0"},"canonical_sha256":"b77e74aecb0365d3cec4058823082d53ee16cdd041887889b9dd192ca026637d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:26.041247Z","signature_b64":"3GZP4Lk80KuPEjh/TGUtoYmuhD2XXbA23lIoheqB76TwmZw6OkKpvKjIHld5wzIOl9As6gl15rxFbB8jJEnCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b77e74aecb0365d3cec4058823082d53ee16cdd041887889b9dd192ca026637d","last_reissued_at":"2026-05-17T23:45:26.040667Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:26.040667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.03592","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FqI3CrHkQfzhardmrtAwHFuMF+fX2WoXX4EehimsZO/3IKJbgR++7rCVIr3ihs7t7lWFpJUVfDVAnGXAT8/YDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:21:38.429619Z"},"content_sha256":"3c229cfdae4f493dd08aa3001420645b5169b142e50df02c43a6a700ac7ff97a","schema_version":"1.0","event_id":"sha256:3c229cfdae4f493dd08aa3001420645b5169b142e50df02c43a6a700ac7ff97a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:W57HJLWLANS5HTWEAWECGCBNKP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Approximation Algorithm for training One-Node ReLU Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Guanyi Wang, Santanu S. Dey, Yao Xie","submitted_at":"2018-10-08T17:36:18Z","abstract_excerpt":"Training a one-node neural network with ReLU activation function (One-Node-ReLU) is a fundamental optimization problem in deep learning. In this paper, we begin with proving the NP-hardness of training One-Node-ReLU. We then present an approximation algorithm to solve One-Node-ReLU whose running time is $\\mathcal{O}(n^k)$ where $n$ is the number of samples, $k$ is a predefined integral constant. Except $k$, this algorithm does not require pre-processing or tuning of parameters. We analyze the performance of this algorithm under various regimes. First, given any arbitrary set of training sample"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03592","kind":"arxiv","version":2},"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":"2026-05-17T23:45:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WhGMGwoS3sm0EcNih6tCw1r+6GcB1KHIvaoyiEMnWy0VEijvVEmanykuFYdBXoXPPVNjfNwq43GHvl5fC+6VDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:21:38.429980Z"},"content_sha256":"dbb11ebe809d02249198cbcaeb4b62d059250ae6d6fe70a8c1f85def89864e46","schema_version":"1.0","event_id":"sha256:dbb11ebe809d02249198cbcaeb4b62d059250ae6d6fe70a8c1f85def89864e46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W57HJLWLANS5HTWEAWECGCBNKP/bundle.json","state_url":"https://pith.science/pith/W57HJLWLANS5HTWEAWECGCBNKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W57HJLWLANS5HTWEAWECGCBNKP/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":"2026-06-04T20:21:38Z","links":{"resolver":"https://pith.science/pith/W57HJLWLANS5HTWEAWECGCBNKP","bundle":"https://pith.science/pith/W57HJLWLANS5HTWEAWECGCBNKP/bundle.json","state":"https://pith.science/pith/W57HJLWLANS5HTWEAWECGCBNKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W57HJLWLANS5HTWEAWECGCBNKP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:W57HJLWLANS5HTWEAWECGCBNKP","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":"f2cef88d41fad5efb088ddb416592cc3b564820e032d2ce51c15714353dee31b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-10-08T17:36:18Z","title_canon_sha256":"c9413ba72d127356d6cc7a023b96a64a7cdfafeb3c80e4cc42c21f572a3297e3"},"schema_version":"1.0","source":{"id":"1810.03592","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03592","created_at":"2026-05-17T23:45:26Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03592v2","created_at":"2026-05-17T23:45:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03592","created_at":"2026-05-17T23:45:26Z"},{"alias_kind":"pith_short_12","alias_value":"W57HJLWLANS5","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"W57HJLWLANS5HTWE","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"W57HJLWL","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:dbb11ebe809d02249198cbcaeb4b62d059250ae6d6fe70a8c1f85def89864e46","target":"graph","created_at":"2026-05-17T23:45:26Z","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":"Training a one-node neural network with ReLU activation function (One-Node-ReLU) is a fundamental optimization problem in deep learning. In this paper, we begin with proving the NP-hardness of training One-Node-ReLU. We then present an approximation algorithm to solve One-Node-ReLU whose running time is $\\mathcal{O}(n^k)$ where $n$ is the number of samples, $k$ is a predefined integral constant. Except $k$, this algorithm does not require pre-processing or tuning of parameters. We analyze the performance of this algorithm under various regimes. First, given any arbitrary set of training sample","authors_text":"Guanyi Wang, Santanu S. Dey, Yao Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-10-08T17:36:18Z","title":"An Approximation Algorithm for training One-Node ReLU Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03592","kind":"arxiv","version":2},"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":"sha256:3c229cfdae4f493dd08aa3001420645b5169b142e50df02c43a6a700ac7ff97a","target":"record","created_at":"2026-05-17T23:45:26Z","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":"f2cef88d41fad5efb088ddb416592cc3b564820e032d2ce51c15714353dee31b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-10-08T17:36:18Z","title_canon_sha256":"c9413ba72d127356d6cc7a023b96a64a7cdfafeb3c80e4cc42c21f572a3297e3"},"schema_version":"1.0","source":{"id":"1810.03592","kind":"arxiv","version":2}},"canonical_sha256":"b77e74aecb0365d3cec4058823082d53ee16cdd041887889b9dd192ca026637d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b77e74aecb0365d3cec4058823082d53ee16cdd041887889b9dd192ca026637d","first_computed_at":"2026-05-17T23:45:26.040667Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:26.040667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3GZP4Lk80KuPEjh/TGUtoYmuhD2XXbA23lIoheqB76TwmZw6OkKpvKjIHld5wzIOl9As6gl15rxFbB8jJEnCDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:26.041247Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.03592","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c229cfdae4f493dd08aa3001420645b5169b142e50df02c43a6a700ac7ff97a","sha256:dbb11ebe809d02249198cbcaeb4b62d059250ae6d6fe70a8c1f85def89864e46"],"state_sha256":"f2e0df2b6c63bb910d8bea8ad2429bdccda655faf2ec05fbee35c61d2ca1e1d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XXvwCtsJOMTyKhffpbLUBlzH5zmWODmyv0YchKDbxReMAehxVlMbJ2GT0WFMAw69eWf0P58EMmxab4jUQRtEBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T20:21:38.431984Z","bundle_sha256":"333f4b32f0e57306c3c9c38b94e3084a240dfdfa63bff83006e28a151893ae87"}}