{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KGINJC3CUXJ7N24WGEDAZ5FLH2","short_pith_number":"pith:KGINJC3C","canonical_record":{"source":{"id":"2209.14863","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-09-29T15:29:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1ede5c83aa681bf76d72dc29ce267d04536e8cd2dc94262e247b23a6bb8e0e5a","abstract_canon_sha256":"151afac87c87573a35a8bb06ffa94cbb8658ef21f62f62b68f4f81f05142a934"},"schema_version":"1.0"},"canonical_sha256":"5190d48b62a5d3f6eb9631060cf4ab3e93d6b8660557b06a8c46208b1d01e2ed","source":{"kind":"arxiv","id":"2209.14863","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14863","created_at":"2026-07-05T05:51:41Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14863v2","created_at":"2026-07-05T05:51:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14863","created_at":"2026-07-05T05:51:41Z"},{"alias_kind":"pith_short_12","alias_value":"KGINJC3CUXJ7","created_at":"2026-07-05T05:51:41Z"},{"alias_kind":"pith_short_16","alias_value":"KGINJC3CUXJ7N24W","created_at":"2026-07-05T05:51:41Z"},{"alias_kind":"pith_short_8","alias_value":"KGINJC3C","created_at":"2026-07-05T05:51:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KGINJC3CUXJ7N24WGEDAZ5FLH2","target":"record","payload":{"canonical_record":{"source":{"id":"2209.14863","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-09-29T15:29:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1ede5c83aa681bf76d72dc29ce267d04536e8cd2dc94262e247b23a6bb8e0e5a","abstract_canon_sha256":"151afac87c87573a35a8bb06ffa94cbb8658ef21f62f62b68f4f81f05142a934"},"schema_version":"1.0"},"canonical_sha256":"5190d48b62a5d3f6eb9631060cf4ab3e93d6b8660557b06a8c46208b1d01e2ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:41.978744Z","signature_b64":"brhkRL2Z67eUWqvYvqk5VEzB3ve/OpXCYHrQb9zM2nDbFZSCFeNFWVpf5h2iFNDQWej3pAmZyrWeFzINURRwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5190d48b62a5d3f6eb9631060cf4ab3e93d6b8660557b06a8c46208b1d01e2ed","last_reissued_at":"2026-07-05T05:51:41.978300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:41.978300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.14863","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":"2026-07-05T05:51:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8bBx8C9zUK7IobycZKI68eKHQQ/b2wttRA68/Zpv4IdjZjVaFjVFM4HntyIODs4xwYmxjbyQVe363+EkwC2aCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:03:21.144703Z"},"content_sha256":"75047ae95378dd247b5f6d48ccb10239548bfd0fe51677a23adf2719664a2049","schema_version":"1.0","event_id":"sha256:75047ae95378dd247b5f6d48ccb10239548bfd0fe51677a23adf2719664a2049"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KGINJC3CUXJ7N24WGEDAZ5FLH2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Networks Efficiently Learn Low-Dimensional Representations with SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alireza Mousavi-Hosseini, Ioannis Mitliagkas, Manuela Girotti, Murat A. Erdogdu, Sejun Park","submitted_at":"2022-09-29T15:29:10Z","abstract_excerpt":"We study the problem of training a two-layer neural network (NN) of arbitrary width using stochastic gradient descent (SGD) where the input $\\boldsymbol{x}\\in \\mathbb{R}^d$ is Gaussian and the target $y \\in \\mathbb{R}$ follows a multiple-index model, i.e., $y=g(\\langle\\boldsymbol{u_1},\\boldsymbol{x}\\rangle,...,\\langle\\boldsymbol{u_k},\\boldsymbol{x}\\rangle)$ with a noisy link function $g$. We prove that the first-layer weights of the NN converge to the $k$-dimensional principal subspace spanned by the vectors $\\boldsymbol{u_1},...,\\boldsymbol{u_k}$ of the true model, when online SGD with weight"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14863","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.14863/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T05:51:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ojGR5nX0hheV9cWXgiP7xNBo1ZWK8vd4L5nIfIirbHvu78cS/SrzAS/PAnUE8ve3oIwHlXiAz5mL8jq3DIYwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:03:21.145305Z"},"content_sha256":"b68401d49be01641653e7b30b23c3916e2a3dc4460d8120430fbaa3c412035aa","schema_version":"1.0","event_id":"sha256:b68401d49be01641653e7b30b23c3916e2a3dc4460d8120430fbaa3c412035aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KGINJC3CUXJ7N24WGEDAZ5FLH2/bundle.json","state_url":"https://pith.science/pith/KGINJC3CUXJ7N24WGEDAZ5FLH2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KGINJC3CUXJ7N24WGEDAZ5FLH2/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":"2026-08-09T04:03:21Z","links":{"resolver":"https://pith.science/pith/KGINJC3CUXJ7N24WGEDAZ5FLH2","bundle":"https://pith.science/pith/KGINJC3CUXJ7N24WGEDAZ5FLH2/bundle.json","state":"https://pith.science/pith/KGINJC3CUXJ7N24WGEDAZ5FLH2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KGINJC3CUXJ7N24WGEDAZ5FLH2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KGINJC3CUXJ7N24WGEDAZ5FLH2","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":"151afac87c87573a35a8bb06ffa94cbb8658ef21f62f62b68f4f81f05142a934","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-09-29T15:29:10Z","title_canon_sha256":"1ede5c83aa681bf76d72dc29ce267d04536e8cd2dc94262e247b23a6bb8e0e5a"},"schema_version":"1.0","source":{"id":"2209.14863","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14863","created_at":"2026-07-05T05:51:41Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14863v2","created_at":"2026-07-05T05:51:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14863","created_at":"2026-07-05T05:51:41Z"},{"alias_kind":"pith_short_12","alias_value":"KGINJC3CUXJ7","created_at":"2026-07-05T05:51:41Z"},{"alias_kind":"pith_short_16","alias_value":"KGINJC3CUXJ7N24W","created_at":"2026-07-05T05:51:41Z"},{"alias_kind":"pith_short_8","alias_value":"KGINJC3C","created_at":"2026-07-05T05:51:41Z"}],"graph_snapshots":[{"event_id":"sha256:b68401d49be01641653e7b30b23c3916e2a3dc4460d8120430fbaa3c412035aa","target":"graph","created_at":"2026-07-05T05:51:41Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2209.14863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of training a two-layer neural network (NN) of arbitrary width using stochastic gradient descent (SGD) where the input $\\boldsymbol{x}\\in \\mathbb{R}^d$ is Gaussian and the target $y \\in \\mathbb{R}$ follows a multiple-index model, i.e., $y=g(\\langle\\boldsymbol{u_1},\\boldsymbol{x}\\rangle,...,\\langle\\boldsymbol{u_k},\\boldsymbol{x}\\rangle)$ with a noisy link function $g$. We prove that the first-layer weights of the NN converge to the $k$-dimensional principal subspace spanned by the vectors $\\boldsymbol{u_1},...,\\boldsymbol{u_k}$ of the true model, when online SGD with weight","authors_text":"Alireza Mousavi-Hosseini, Ioannis Mitliagkas, Manuela Girotti, Murat A. Erdogdu, Sejun Park","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-09-29T15:29:10Z","title":"Neural Networks Efficiently Learn Low-Dimensional Representations with SGD"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14863","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":"sha256:75047ae95378dd247b5f6d48ccb10239548bfd0fe51677a23adf2719664a2049","target":"record","created_at":"2026-07-05T05:51:41Z","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":"151afac87c87573a35a8bb06ffa94cbb8658ef21f62f62b68f4f81f05142a934","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-09-29T15:29:10Z","title_canon_sha256":"1ede5c83aa681bf76d72dc29ce267d04536e8cd2dc94262e247b23a6bb8e0e5a"},"schema_version":"1.0","source":{"id":"2209.14863","kind":"arxiv","version":2}},"canonical_sha256":"5190d48b62a5d3f6eb9631060cf4ab3e93d6b8660557b06a8c46208b1d01e2ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5190d48b62a5d3f6eb9631060cf4ab3e93d6b8660557b06a8c46208b1d01e2ed","first_computed_at":"2026-07-05T05:51:41.978300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:51:41.978300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"brhkRL2Z67eUWqvYvqk5VEzB3ve/OpXCYHrQb9zM2nDbFZSCFeNFWVpf5h2iFNDQWej3pAmZyrWeFzINURRwCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:51:41.978744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14863","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75047ae95378dd247b5f6d48ccb10239548bfd0fe51677a23adf2719664a2049","sha256:b68401d49be01641653e7b30b23c3916e2a3dc4460d8120430fbaa3c412035aa"],"state_sha256":"0ee953abf82285e53d2fc417775062513c2d7829799b18e7d7d42690a7ef891d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k0JKbc884s8vaKeBC8+UXQygfiX8veOULq5rmAYCXMW7B672YxG5WYMJh/9zDHxZ0lOgfGVH7V2SxHhhEjfoCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:03:21.149535Z","bundle_sha256":"f38c50e860ac578412beef5fadd3a0b9b25e6df1273246d2f5dd3170d97f5c52"}}