{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LPZ2QAYGXGGDBZQTFLOMLJGDZR","short_pith_number":"pith:LPZ2QAYG","canonical_record":{"source":{"id":"1810.04207","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CC","submitted_at":"2018-10-09T18:42:22Z","cross_cats_sorted":[],"title_canon_sha256":"aba69ee4d8992d203940736c7618d1668ebb491e3e0ca4deae9a7f73bc3ebab6","abstract_canon_sha256":"1ad9cafe2211ddcb0fe204bf3db77388187dcca080aa56541978132be1082ea5"},"schema_version":"1.0"},"canonical_sha256":"5bf3a80306b98c30e6132adcc5a4c3cc6d10952d59a0c484433c68d50bbf2a72","source":{"kind":"arxiv","id":"1810.04207","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04207","created_at":"2026-05-18T00:03:14Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04207v2","created_at":"2026-05-18T00:03:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04207","created_at":"2026-05-18T00:03:14Z"},{"alias_kind":"pith_short_12","alias_value":"LPZ2QAYGXGGD","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LPZ2QAYGXGGDBZQT","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LPZ2QAYG","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LPZ2QAYGXGGDBZQTFLOMLJGDZR","target":"record","payload":{"canonical_record":{"source":{"id":"1810.04207","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CC","submitted_at":"2018-10-09T18:42:22Z","cross_cats_sorted":[],"title_canon_sha256":"aba69ee4d8992d203940736c7618d1668ebb491e3e0ca4deae9a7f73bc3ebab6","abstract_canon_sha256":"1ad9cafe2211ddcb0fe204bf3db77388187dcca080aa56541978132be1082ea5"},"schema_version":"1.0"},"canonical_sha256":"5bf3a80306b98c30e6132adcc5a4c3cc6d10952d59a0c484433c68d50bbf2a72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:14.437045Z","signature_b64":"IELUp++O28tK2pvNpBlv+YGj28GPxdQDQll1AjI39PDm4mOtdg3CDv0Jj0Y+rxYV4w1xqLUT4XfXwTbaTpoyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bf3a80306b98c30e6132adcc5a4c3cc6d10952d59a0c484433c68d50bbf2a72","last_reissued_at":"2026-05-18T00:03:14.436471Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:14.436471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.04207","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":"2026-05-18T00:03:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j+zoQoZl6DhnLFnoWuve4GX2+Cm0Qx9c2dV2MwHXLfeUm+LjThHdffRpSmWmv3+saRAJZF9KQbH/qQsMc2ojCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T10:39:23.758105Z"},"content_sha256":"75edd5cb4970c68d38e021b2cec65dd7a58e501be7db5293fd08a9f7d16887da","schema_version":"1.0","event_id":"sha256:75edd5cb4970c68d38e021b2cec65dd7a58e501be7db5293fd08a9f7d16887da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LPZ2QAYGXGGDBZQTFLOMLJGDZR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Computational Complexity of Training ReLU(s)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CC","authors_text":"Daniel Reichman, Pasin Manurangsi","submitted_at":"2018-10-09T18:42:22Z","abstract_excerpt":"We consider the computational complexity of training depth-2 neural networks composed of rectified linear units (ReLUs). We show that, even for the case of a single ReLU, finding a set of weights that minimizes the squared error (even approximately) for a given training set is NP-hard. We also show that for a simple network consisting of two ReLUs, the error minimization problem is NP-hard, even in the realizable case. We complement these hardness results by showing that, when the weights and samples belong to the unit ball, one can (agnostically) properly and reliably learn depth-2 ReLUs with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04207","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":"2026-05-18T00:03:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cpHtWCQrj5/Mb2KOCImIt8Sx6iVapI2T8lNz1V0TELVntkTxdjdhx3klZ//2+/gF6/423yBgfm2YvaoPcO6lDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T10:39:23.758801Z"},"content_sha256":"f75d9aa4a6550a7eca7f1ab56a32f271e6ab8f9a86f2e4f1b0fd919837970884","schema_version":"1.0","event_id":"sha256:f75d9aa4a6550a7eca7f1ab56a32f271e6ab8f9a86f2e4f1b0fd919837970884"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LPZ2QAYGXGGDBZQTFLOMLJGDZR/bundle.json","state_url":"https://pith.science/pith/LPZ2QAYGXGGDBZQTFLOMLJGDZR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LPZ2QAYGXGGDBZQTFLOMLJGDZR/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":"2026-05-30T10:39:23Z","links":{"resolver":"https://pith.science/pith/LPZ2QAYGXGGDBZQTFLOMLJGDZR","bundle":"https://pith.science/pith/LPZ2QAYGXGGDBZQTFLOMLJGDZR/bundle.json","state":"https://pith.science/pith/LPZ2QAYGXGGDBZQTFLOMLJGDZR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LPZ2QAYGXGGDBZQTFLOMLJGDZR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LPZ2QAYGXGGDBZQTFLOMLJGDZR","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":"1ad9cafe2211ddcb0fe204bf3db77388187dcca080aa56541978132be1082ea5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CC","submitted_at":"2018-10-09T18:42:22Z","title_canon_sha256":"aba69ee4d8992d203940736c7618d1668ebb491e3e0ca4deae9a7f73bc3ebab6"},"schema_version":"1.0","source":{"id":"1810.04207","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04207","created_at":"2026-05-18T00:03:14Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04207v2","created_at":"2026-05-18T00:03:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04207","created_at":"2026-05-18T00:03:14Z"},{"alias_kind":"pith_short_12","alias_value":"LPZ2QAYGXGGD","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LPZ2QAYGXGGDBZQT","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LPZ2QAYG","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:f75d9aa4a6550a7eca7f1ab56a32f271e6ab8f9a86f2e4f1b0fd919837970884","target":"graph","created_at":"2026-05-18T00:03:14Z","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 consider the computational complexity of training depth-2 neural networks composed of rectified linear units (ReLUs). We show that, even for the case of a single ReLU, finding a set of weights that minimizes the squared error (even approximately) for a given training set is NP-hard. We also show that for a simple network consisting of two ReLUs, the error minimization problem is NP-hard, even in the realizable case. We complement these hardness results by showing that, when the weights and samples belong to the unit ball, one can (agnostically) properly and reliably learn depth-2 ReLUs with","authors_text":"Daniel Reichman, Pasin Manurangsi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CC","submitted_at":"2018-10-09T18:42:22Z","title":"The Computational Complexity of Training ReLU(s)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04207","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":"sha256:75edd5cb4970c68d38e021b2cec65dd7a58e501be7db5293fd08a9f7d16887da","target":"record","created_at":"2026-05-18T00:03:14Z","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":"1ad9cafe2211ddcb0fe204bf3db77388187dcca080aa56541978132be1082ea5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CC","submitted_at":"2018-10-09T18:42:22Z","title_canon_sha256":"aba69ee4d8992d203940736c7618d1668ebb491e3e0ca4deae9a7f73bc3ebab6"},"schema_version":"1.0","source":{"id":"1810.04207","kind":"arxiv","version":2}},"canonical_sha256":"5bf3a80306b98c30e6132adcc5a4c3cc6d10952d59a0c484433c68d50bbf2a72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bf3a80306b98c30e6132adcc5a4c3cc6d10952d59a0c484433c68d50bbf2a72","first_computed_at":"2026-05-18T00:03:14.436471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:14.436471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IELUp++O28tK2pvNpBlv+YGj28GPxdQDQll1AjI39PDm4mOtdg3CDv0Jj0Y+rxYV4w1xqLUT4XfXwTbaTpoyCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:14.437045Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.04207","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75edd5cb4970c68d38e021b2cec65dd7a58e501be7db5293fd08a9f7d16887da","sha256:f75d9aa4a6550a7eca7f1ab56a32f271e6ab8f9a86f2e4f1b0fd919837970884"],"state_sha256":"f1b53e3861230539186072d53364aecedb5a9bf50e16f004ab4073297c9bbcda"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a31Z6XMwHfJrkkuRBwGUxaPzZJZ/XvfdoTqKI51yR/WFSi0bxexws5loUWOAYQRGGPju654q7jTlPXjVSNXWBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T10:39:23.762982Z","bundle_sha256":"890c2760bc676f5457bbeb55ae2ff802dc9aaafa2c1e8d86142a692d52c41e65"}}