{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QDAM4ZQRSK4FYU3LPGW5URRWMQ","short_pith_number":"pith:QDAM4ZQR","canonical_record":{"source":{"id":"1810.06793","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T02:26:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5ccbbfda014085ef9e26a4ace59cf485a2e46785aaf85ff50ec3057b39ee210e","abstract_canon_sha256":"b37056319747682a8921943f1d3e7957a2eee7357dc5eeaf32b316db6029f8ae"},"schema_version":"1.0"},"canonical_sha256":"80c0ce661192b85c536b79adda4636642ec93a95147dcb6941fa4d626fa3eaf6","source":{"kind":"arxiv","id":"1810.06793","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06793","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06793v2","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06793","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"QDAM4ZQRSK4F","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QDAM4ZQRSK4FYU3L","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QDAM4ZQR","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QDAM4ZQRSK4FYU3LPGW5URRWMQ","target":"record","payload":{"canonical_record":{"source":{"id":"1810.06793","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T02:26:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5ccbbfda014085ef9e26a4ace59cf485a2e46785aaf85ff50ec3057b39ee210e","abstract_canon_sha256":"b37056319747682a8921943f1d3e7957a2eee7357dc5eeaf32b316db6029f8ae"},"schema_version":"1.0"},"canonical_sha256":"80c0ce661192b85c536b79adda4636642ec93a95147dcb6941fa4d626fa3eaf6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:53.594477Z","signature_b64":"SLBIj0FergX19a+kERnUG7ytDnk6Mg6JGTetcrJjIWq4VopIgiZ182fSDS8rCK4sAaAtW2r+w/AYIIV575iKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80c0ce661192b85c536b79adda4636642ec93a95147dcb6941fa4d626fa3eaf6","last_reissued_at":"2026-05-17T23:54:53.593791Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:53.593791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.06793","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":"2026-05-17T23:54:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EuZEM/+hPMMq/eNuQGwpQV3jwkKJ+VYu2UjAI6NLe3q65YvcHXM+2jpbEqJRt4xj3xbDwdFzlm/XW2LC6pYkAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:21:55.186747Z"},"content_sha256":"43db00ed353e04ea5438757c8717a78a604f71f6dbe4a764420cc4f7ca8ee831","schema_version":"1.0","event_id":"sha256:43db00ed353e04ea5438757c8717a78a604f71f6dbe4a764420cc4f7ca8ee831"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QDAM4ZQRSK4FYU3LPGW5URRWMQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Two-layer Neural Networks with Symmetric Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Rohith Kuditipudi, Rong Ge, Xiang Wang, Zhize Li","submitted_at":"2018-10-16T02:26:55Z","abstract_excerpt":"We give a new algorithm for learning a two-layer neural network under a general class of input distributions. Assuming there is a ground-truth two-layer network $$ y = A \\sigma(Wx) + \\xi, $$ where $A,W$ are weight matrices, $\\xi$ represents noise, and the number of neurons in the hidden layer is no larger than the input or output, our algorithm is guaranteed to recover the parameters $A,W$ of the ground-truth network. The only requirement on the input $x$ is that it is symmetric, which still allows highly complicated and structured input.\n  Our algorithm is based on the method-of-moments frame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06793","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":"2026-05-17T23:54:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UkqQwreKs7lCFCM8lrvwCWcBfyHPH/nCvpR5vI2UidYtwAf2quDvNixzOM1sRdS5ZZV7U5TsE/UcCnAoTqWAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:21:55.187421Z"},"content_sha256":"e6a2586dc22c6cccc196e52c22880391c0e28c7a8a3e2042968ff3ece305b133","schema_version":"1.0","event_id":"sha256:e6a2586dc22c6cccc196e52c22880391c0e28c7a8a3e2042968ff3ece305b133"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QDAM4ZQRSK4FYU3LPGW5URRWMQ/bundle.json","state_url":"https://pith.science/pith/QDAM4ZQRSK4FYU3LPGW5URRWMQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QDAM4ZQRSK4FYU3LPGW5URRWMQ/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":"2026-05-27T23:21:55Z","links":{"resolver":"https://pith.science/pith/QDAM4ZQRSK4FYU3LPGW5URRWMQ","bundle":"https://pith.science/pith/QDAM4ZQRSK4FYU3LPGW5URRWMQ/bundle.json","state":"https://pith.science/pith/QDAM4ZQRSK4FYU3LPGW5URRWMQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QDAM4ZQRSK4FYU3LPGW5URRWMQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QDAM4ZQRSK4FYU3LPGW5URRWMQ","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":"b37056319747682a8921943f1d3e7957a2eee7357dc5eeaf32b316db6029f8ae","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T02:26:55Z","title_canon_sha256":"5ccbbfda014085ef9e26a4ace59cf485a2e46785aaf85ff50ec3057b39ee210e"},"schema_version":"1.0","source":{"id":"1810.06793","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06793","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06793v2","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06793","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"QDAM4ZQRSK4F","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QDAM4ZQRSK4FYU3L","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QDAM4ZQR","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:e6a2586dc22c6cccc196e52c22880391c0e28c7a8a3e2042968ff3ece305b133","target":"graph","created_at":"2026-05-17T23:54:53Z","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 give a new algorithm for learning a two-layer neural network under a general class of input distributions. Assuming there is a ground-truth two-layer network $$ y = A \\sigma(Wx) + \\xi, $$ where $A,W$ are weight matrices, $\\xi$ represents noise, and the number of neurons in the hidden layer is no larger than the input or output, our algorithm is guaranteed to recover the parameters $A,W$ of the ground-truth network. The only requirement on the input $x$ is that it is symmetric, which still allows highly complicated and structured input.\n  Our algorithm is based on the method-of-moments frame","authors_text":"Rohith Kuditipudi, Rong Ge, Xiang Wang, Zhize Li","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T02:26:55Z","title":"Learning Two-layer Neural Networks with Symmetric Inputs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06793","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":"sha256:43db00ed353e04ea5438757c8717a78a604f71f6dbe4a764420cc4f7ca8ee831","target":"record","created_at":"2026-05-17T23:54:53Z","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":"b37056319747682a8921943f1d3e7957a2eee7357dc5eeaf32b316db6029f8ae","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T02:26:55Z","title_canon_sha256":"5ccbbfda014085ef9e26a4ace59cf485a2e46785aaf85ff50ec3057b39ee210e"},"schema_version":"1.0","source":{"id":"1810.06793","kind":"arxiv","version":2}},"canonical_sha256":"80c0ce661192b85c536b79adda4636642ec93a95147dcb6941fa4d626fa3eaf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80c0ce661192b85c536b79adda4636642ec93a95147dcb6941fa4d626fa3eaf6","first_computed_at":"2026-05-17T23:54:53.593791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:53.593791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SLBIj0FergX19a+kERnUG7ytDnk6Mg6JGTetcrJjIWq4VopIgiZ182fSDS8rCK4sAaAtW2r+w/AYIIV575iKAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:53.594477Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.06793","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43db00ed353e04ea5438757c8717a78a604f71f6dbe4a764420cc4f7ca8ee831","sha256:e6a2586dc22c6cccc196e52c22880391c0e28c7a8a3e2042968ff3ece305b133"],"state_sha256":"3e2ea28ea3a27ac6cdb1990b7b58325a1e7d7796541565f34defc9501e27c186"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uz1uhm0JvpYVLim6ncYnijT3C47QJyHYfL0bbdNAGElVahqwU3jdsbPPq1gfDcbhGRm4zEMR3PykGntZByBxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T23:21:55.192628Z","bundle_sha256":"4abf83b602352769893ba2d4341bdd4cb8471b4a9219efc3fa8749b546e79879"}}