{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GR7EEYS33ATMHGQSPDLYIR5VZH","short_pith_number":"pith:GR7EEYS3","canonical_record":{"source":{"id":"1802.07301","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-20T19:40:32Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"91ab2c129791934e317ec60ed34f090782d5cd1cdb8748ecf01964888702f58d","abstract_canon_sha256":"29735a4aeafc83938d6b5c52c18cd125798c5bbe30422911bfff2f6cb9f05b21"},"schema_version":"1.0"},"canonical_sha256":"347e42625bd826c39a1278d78447b5c9d61779aafcbdea6d4228ea0440ffd400","source":{"kind":"arxiv","id":"1802.07301","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07301","created_at":"2026-05-18T00:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07301v3","created_at":"2026-05-18T00:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07301","created_at":"2026-05-18T00:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"GR7EEYS33ATM","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GR7EEYS33ATMHGQS","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GR7EEYS3","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GR7EEYS33ATMHGQSPDLYIR5VZH","target":"record","payload":{"canonical_record":{"source":{"id":"1802.07301","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-20T19:40:32Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"91ab2c129791934e317ec60ed34f090782d5cd1cdb8748ecf01964888702f58d","abstract_canon_sha256":"29735a4aeafc83938d6b5c52c18cd125798c5bbe30422911bfff2f6cb9f05b21"},"schema_version":"1.0"},"canonical_sha256":"347e42625bd826c39a1278d78447b5c9d61779aafcbdea6d4228ea0440ffd400","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:41.521849Z","signature_b64":"/dn8lH/FvcFsBi64WcTuxcQV2m8X4kxO7Fui9EZ6tWa77UG8JM42A5AiizG6ZRZuHOhPOkvmPsN63ggEfuEWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"347e42625bd826c39a1278d78447b5c9d61779aafcbdea6d4228ea0440ffd400","last_reissued_at":"2026-05-18T00:03:41.521455Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:41.521455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.07301","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:03:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9gJ6Nn8W6lpwwa6ChriMo5k0NnJb22qyw2kfRO93ammoj6SfqMnN896NDeM3Jk5C1FTQOH3I07AORpNbnXzBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:22:13.193984Z"},"content_sha256":"138404d4a43a41218354142f690aa75001007aaef21f793713a95f3e6fc458ed","schema_version":"1.0","event_id":"sha256:138404d4a43a41218354142f690aa75001007aaef21f793713a95f3e6fc458ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GR7EEYS33ATMHGQSPDLYIR5VZH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Montanari, Marco Mondelli","submitted_at":"2018-02-20T19:40:32Z","abstract_excerpt":"We establish connections between the problem of learning a two-layer neural network and tensor decomposition. We consider a model with feature vectors $\\boldsymbol x \\in \\mathbb R^d$, $r$ hidden units with weights $\\{\\boldsymbol w_i\\}_{1\\le i \\le r}$ and output $y\\in \\mathbb R$, i.e., $y=\\sum_{i=1}^r \\sigma( \\boldsymbol w_i^{\\mathsf T}\\boldsymbol x)$, with activation functions given by low-degree polynomials. In particular, if $\\sigma(x) = a_0+a_1x+a_3x^3$, we prove that no polynomial-time learning algorithm can outperform the trivial predictor that assigns to each example the response variabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07301","kind":"arxiv","version":3},"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":"2026-05-18T00:03:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Qap+VZC8YofrwweAXGYK2w4cVENlefKdkbwT9pLXB5IfNXV8RPSwaJwlxQUOSDrpIvJSGTYTjXZ7FF9tylGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:22:13.194662Z"},"content_sha256":"a717daafd403ed05fcde6322c2b6dbb28d0c6ed664bab132920b98c758426f4a","schema_version":"1.0","event_id":"sha256:a717daafd403ed05fcde6322c2b6dbb28d0c6ed664bab132920b98c758426f4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GR7EEYS33ATMHGQSPDLYIR5VZH/bundle.json","state_url":"https://pith.science/pith/GR7EEYS33ATMHGQSPDLYIR5VZH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GR7EEYS33ATMHGQSPDLYIR5VZH/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":"2026-05-26T07:22:13Z","links":{"resolver":"https://pith.science/pith/GR7EEYS33ATMHGQSPDLYIR5VZH","bundle":"https://pith.science/pith/GR7EEYS33ATMHGQSPDLYIR5VZH/bundle.json","state":"https://pith.science/pith/GR7EEYS33ATMHGQSPDLYIR5VZH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GR7EEYS33ATMHGQSPDLYIR5VZH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GR7EEYS33ATMHGQSPDLYIR5VZH","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":"29735a4aeafc83938d6b5c52c18cd125798c5bbe30422911bfff2f6cb9f05b21","cross_cats_sorted":["cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-20T19:40:32Z","title_canon_sha256":"91ab2c129791934e317ec60ed34f090782d5cd1cdb8748ecf01964888702f58d"},"schema_version":"1.0","source":{"id":"1802.07301","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07301","created_at":"2026-05-18T00:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07301v3","created_at":"2026-05-18T00:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07301","created_at":"2026-05-18T00:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"GR7EEYS33ATM","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GR7EEYS33ATMHGQS","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GR7EEYS3","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:a717daafd403ed05fcde6322c2b6dbb28d0c6ed664bab132920b98c758426f4a","target":"graph","created_at":"2026-05-18T00:03:41Z","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 establish connections between the problem of learning a two-layer neural network and tensor decomposition. We consider a model with feature vectors $\\boldsymbol x \\in \\mathbb R^d$, $r$ hidden units with weights $\\{\\boldsymbol w_i\\}_{1\\le i \\le r}$ and output $y\\in \\mathbb R$, i.e., $y=\\sum_{i=1}^r \\sigma( \\boldsymbol w_i^{\\mathsf T}\\boldsymbol x)$, with activation functions given by low-degree polynomials. In particular, if $\\sigma(x) = a_0+a_1x+a_3x^3$, we prove that no polynomial-time learning algorithm can outperform the trivial predictor that assigns to each example the response variabl","authors_text":"Andrea Montanari, Marco Mondelli","cross_cats":["cs.DS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-20T19:40:32Z","title":"On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07301","kind":"arxiv","version":3},"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":"sha256:138404d4a43a41218354142f690aa75001007aaef21f793713a95f3e6fc458ed","target":"record","created_at":"2026-05-18T00:03:41Z","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":"29735a4aeafc83938d6b5c52c18cd125798c5bbe30422911bfff2f6cb9f05b21","cross_cats_sorted":["cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-20T19:40:32Z","title_canon_sha256":"91ab2c129791934e317ec60ed34f090782d5cd1cdb8748ecf01964888702f58d"},"schema_version":"1.0","source":{"id":"1802.07301","kind":"arxiv","version":3}},"canonical_sha256":"347e42625bd826c39a1278d78447b5c9d61779aafcbdea6d4228ea0440ffd400","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"347e42625bd826c39a1278d78447b5c9d61779aafcbdea6d4228ea0440ffd400","first_computed_at":"2026-05-18T00:03:41.521455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:41.521455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/dn8lH/FvcFsBi64WcTuxcQV2m8X4kxO7Fui9EZ6tWa77UG8JM42A5AiizG6ZRZuHOhPOkvmPsN63ggEfuEWBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:41.521849Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.07301","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:138404d4a43a41218354142f690aa75001007aaef21f793713a95f3e6fc458ed","sha256:a717daafd403ed05fcde6322c2b6dbb28d0c6ed664bab132920b98c758426f4a"],"state_sha256":"628061240bfef63d46abb1123a9ea2fd4b19bf872365ac4d2e4a5c9c1e322030"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uFJOro54k5+7zQHvwVg0NfH49GDpC3/koShug6YtBsYm1PwgrQhBJV5d1tNPcqT4n4kzPXpaM7iGSQeBSVMwBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T07:22:13.198521Z","bundle_sha256":"b3f0aeda00fb37990dc07c7bf94d119b6b8d79a0dab00fb8bb8173ab3cb80328"}}