{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3HFPCFOGED5B6AIQPM45BHRGB2","short_pith_number":"pith:3HFPCFOG","canonical_record":{"source":{"id":"1709.06010","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-09-18T15:36:06Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"e4c916eb8c270254536ac07a3c0f49d1e1acad884dea317bae209d2b6a555a91","abstract_canon_sha256":"6765efde577dba114a7f295815ba0528e787871b5fe6ffc65ab8e2122d2429d9"},"schema_version":"1.0"},"canonical_sha256":"d9caf115c620fa1f01107b39d09e260e9c3ccbdcf821e7444c7f4e0b46a4afd1","source":{"kind":"arxiv","id":"1709.06010","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06010","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06010v4","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06010","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"3HFPCFOGED5B","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3HFPCFOGED5B6AIQ","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3HFPCFOG","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3HFPCFOGED5B6AIQPM45BHRGB2","target":"record","payload":{"canonical_record":{"source":{"id":"1709.06010","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-09-18T15:36:06Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"e4c916eb8c270254536ac07a3c0f49d1e1acad884dea317bae209d2b6a555a91","abstract_canon_sha256":"6765efde577dba114a7f295815ba0528e787871b5fe6ffc65ab8e2122d2429d9"},"schema_version":"1.0"},"canonical_sha256":"d9caf115c620fa1f01107b39d09e260e9c3ccbdcf821e7444c7f4e0b46a4afd1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:54.456524Z","signature_b64":"A0GHQKmV1pL2xUUvf3uSiFsIpN89xMVq2dE7ypHn3vBmwtIzzGbU5R7rViSn8/ISdiAvbl89vUPvHPAn14fxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9caf115c620fa1f01107b39d09e260e9c3ccbdcf821e7444c7f4e0b46a4afd1","last_reissued_at":"2026-05-18T00:17:54.456001Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:54.456001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.06010","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d6X5xn3JIMoKOXnfW5WCnz2HhTB22BF9EQHwIkX3KDGf4zz0RTYTbra1A9HUEDthb6oXK7yTkOYhMvNMPDnJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T18:57:47.110903Z"},"content_sha256":"db77fa34622ed5334e40f454eae31baa339ae78896daae3fc0addc98a5a6a2af","schema_version":"1.0","event_id":"sha256:db77fa34622ed5334e40f454eae31baa339ae78896daae3fc0addc98a5a6a2af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3HFPCFOGED5B6AIQPM45BHRGB2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Neural Networks with Two Nonlinear Layers in Polynomial Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"Adam Klivans, Surbhi Goel","submitted_at":"2017-09-18T15:36:06Z","abstract_excerpt":"We give a polynomial-time algorithm for learning neural networks with one layer of sigmoids feeding into any Lipschitz, monotone activation function (e.g., sigmoid or ReLU). We make no assumptions on the structure of the network, and the algorithm succeeds with respect to {\\em any} distribution on the unit ball in $n$ dimensions (hidden weight vectors also have unit norm). This is the first assumption-free, provably efficient algorithm for learning neural networks with two nonlinear layers.\n  Our algorithm-- {\\em Alphatron}-- is a simple, iterative update rule that combines isotonic regression"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06010","kind":"arxiv","version":4},"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":"2026-05-18T00:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1wZnWUsVvhHH1IUMTOvsa5Yr8NDDQB6m1BRiQeipPqW8RtQy0/fk3110R2E47UdLoDs0AT9SsRtBT7J9Ne+7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T18:57:47.111252Z"},"content_sha256":"abc708723a69e2799c4434b5b8e61ce65555d8e07536450753079dd69bef5891","schema_version":"1.0","event_id":"sha256:abc708723a69e2799c4434b5b8e61ce65555d8e07536450753079dd69bef5891"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3HFPCFOGED5B6AIQPM45BHRGB2/bundle.json","state_url":"https://pith.science/pith/3HFPCFOGED5B6AIQPM45BHRGB2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3HFPCFOGED5B6AIQPM45BHRGB2/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":"2026-05-19T18:57:47Z","links":{"resolver":"https://pith.science/pith/3HFPCFOGED5B6AIQPM45BHRGB2","bundle":"https://pith.science/pith/3HFPCFOGED5B6AIQPM45BHRGB2/bundle.json","state":"https://pith.science/pith/3HFPCFOGED5B6AIQPM45BHRGB2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3HFPCFOGED5B6AIQPM45BHRGB2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3HFPCFOGED5B6AIQPM45BHRGB2","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":"6765efde577dba114a7f295815ba0528e787871b5fe6ffc65ab8e2122d2429d9","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-09-18T15:36:06Z","title_canon_sha256":"e4c916eb8c270254536ac07a3c0f49d1e1acad884dea317bae209d2b6a555a91"},"schema_version":"1.0","source":{"id":"1709.06010","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06010","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06010v4","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06010","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"3HFPCFOGED5B","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3HFPCFOGED5B6AIQ","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3HFPCFOG","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:abc708723a69e2799c4434b5b8e61ce65555d8e07536450753079dd69bef5891","target":"graph","created_at":"2026-05-18T00:17:54Z","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 polynomial-time algorithm for learning neural networks with one layer of sigmoids feeding into any Lipschitz, monotone activation function (e.g., sigmoid or ReLU). We make no assumptions on the structure of the network, and the algorithm succeeds with respect to {\\em any} distribution on the unit ball in $n$ dimensions (hidden weight vectors also have unit norm). This is the first assumption-free, provably efficient algorithm for learning neural networks with two nonlinear layers.\n  Our algorithm-- {\\em Alphatron}-- is a simple, iterative update rule that combines isotonic regression","authors_text":"Adam Klivans, Surbhi Goel","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-09-18T15:36:06Z","title":"Learning Neural Networks with Two Nonlinear Layers in Polynomial Time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06010","kind":"arxiv","version":4},"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:db77fa34622ed5334e40f454eae31baa339ae78896daae3fc0addc98a5a6a2af","target":"record","created_at":"2026-05-18T00:17:54Z","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":"6765efde577dba114a7f295815ba0528e787871b5fe6ffc65ab8e2122d2429d9","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-09-18T15:36:06Z","title_canon_sha256":"e4c916eb8c270254536ac07a3c0f49d1e1acad884dea317bae209d2b6a555a91"},"schema_version":"1.0","source":{"id":"1709.06010","kind":"arxiv","version":4}},"canonical_sha256":"d9caf115c620fa1f01107b39d09e260e9c3ccbdcf821e7444c7f4e0b46a4afd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9caf115c620fa1f01107b39d09e260e9c3ccbdcf821e7444c7f4e0b46a4afd1","first_computed_at":"2026-05-18T00:17:54.456001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:54.456001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A0GHQKmV1pL2xUUvf3uSiFsIpN89xMVq2dE7ypHn3vBmwtIzzGbU5R7rViSn8/ISdiAvbl89vUPvHPAn14fxAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:54.456524Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.06010","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db77fa34622ed5334e40f454eae31baa339ae78896daae3fc0addc98a5a6a2af","sha256:abc708723a69e2799c4434b5b8e61ce65555d8e07536450753079dd69bef5891"],"state_sha256":"182f632dae95207515041ddb8bb1383d32656c4d834becd2e6eb85f1e8e7ec50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"slElWcWPvAUvl69vlQ6jQ6AX4gHpbd6A7Rc0Evtqd6RHqwdgcbGNTPHpbcGbjPi1hix61pulCOSnAM/QTabFDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T18:57:47.113352Z","bundle_sha256":"cfe1305b7450f1cd1a0a001b1c9a40242d9e0d44d8db9a40578f70a5559c00cf"}}