{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XNOGIXDGRKHUJD5HDMN7WE4WZ5","short_pith_number":"pith:XNOGIXDG","schema_version":"1.0","canonical_sha256":"bb5c645c668a8f448fa71b1bfb1396cf50bef0d612a6b0036d493995148b022e","source":{"kind":"arxiv","id":"2003.10523","version":1},"attestation_state":"computed","paper":{"title":"Neural Networks and Polynomial Regression. Demystifying the Overparametrization Phenomena","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"David Gamarnik, Eren C. K{\\i}z{\\i}lda\\u{g}, Ilias Zadik, Matt Emschwiller","submitted_at":"2020-03-23T20:09:31Z","abstract_excerpt":"In the context of neural network models, overparametrization refers to the phenomena whereby these models appear to generalize well on the unseen data, even though the number of parameters significantly exceeds the sample sizes, and the model perfectly fits the in-training data. A conventional explanation of this phenomena is based on self-regularization properties of algorithms used to train the data. In this paper we prove a series of results which provide a somewhat diverging explanation. Adopting a teacher/student model where the teacher network is used to generate the predictions and stud"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2003.10523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-23T20:09:31Z","cross_cats_sorted":["cs.LG","cs.NE","math.ST","stat.TH"],"title_canon_sha256":"07118539126a3e171683008cc1c2fff8bae19ce613a3b67f190b2d77af91d602","abstract_canon_sha256":"d43dd7e947037b5de053429b9d2ee83e28d7746ae6ac3af1bde7c88d8dd83919"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:17.933418Z","signature_b64":"fwIVDKlCOykVvqREmWduhH4p0tz21Con2O57czpt9GgYQH0bzo68F5T37aXN3ba9wEBvCKMiqBibs2DCEzdEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb5c645c668a8f448fa71b1bfb1396cf50bef0d612a6b0036d493995148b022e","last_reissued_at":"2026-07-05T00:50:17.932996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:17.932996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Networks and Polynomial Regression. Demystifying the Overparametrization Phenomena","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"David Gamarnik, Eren C. K{\\i}z{\\i}lda\\u{g}, Ilias Zadik, Matt Emschwiller","submitted_at":"2020-03-23T20:09:31Z","abstract_excerpt":"In the context of neural network models, overparametrization refers to the phenomena whereby these models appear to generalize well on the unseen data, even though the number of parameters significantly exceeds the sample sizes, and the model perfectly fits the in-training data. A conventional explanation of this phenomena is based on self-regularization properties of algorithms used to train the data. In this paper we prove a series of results which provide a somewhat diverging explanation. Adopting a teacher/student model where the teacher network is used to generate the predictions and stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.10523","kind":"arxiv","version":1},"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/2003.10523/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2003.10523","created_at":"2026-07-05T00:50:17.933058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.10523v1","created_at":"2026-07-05T00:50:17.933058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10523","created_at":"2026-07-05T00:50:17.933058+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNOGIXDGRKHU","created_at":"2026-07-05T00:50:17.933058+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNOGIXDGRKHUJD5H","created_at":"2026-07-05T00:50:17.933058+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNOGIXDG","created_at":"2026-07-05T00:50:17.933058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05134","citing_title":"Information-Theoretic Guarantees for Recovering Low-Rank Tensors from Symmetric Rank-One Measurements","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNOGIXDGRKHUJD5HDMN7WE4WZ5","json":"https://pith.science/pith/XNOGIXDGRKHUJD5HDMN7WE4WZ5.json","graph_json":"https://pith.science/api/pith-number/XNOGIXDGRKHUJD5HDMN7WE4WZ5/graph.json","events_json":"https://pith.science/api/pith-number/XNOGIXDGRKHUJD5HDMN7WE4WZ5/events.json","paper":"https://pith.science/paper/XNOGIXDG"},"agent_actions":{"view_html":"https://pith.science/pith/XNOGIXDGRKHUJD5HDMN7WE4WZ5","download_json":"https://pith.science/pith/XNOGIXDGRKHUJD5HDMN7WE4WZ5.json","view_paper":"https://pith.science/paper/XNOGIXDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.10523&json=true","fetch_graph":"https://pith.science/api/pith-number/XNOGIXDGRKHUJD5HDMN7WE4WZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/XNOGIXDGRKHUJD5HDMN7WE4WZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNOGIXDGRKHUJD5HDMN7WE4WZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNOGIXDGRKHUJD5HDMN7WE4WZ5/action/storage_attestation","attest_author":"https://pith.science/pith/XNOGIXDGRKHUJD5HDMN7WE4WZ5/action/author_attestation","sign_citation":"https://pith.science/pith/XNOGIXDGRKHUJD5HDMN7WE4WZ5/action/citation_signature","submit_replication":"https://pith.science/pith/XNOGIXDGRKHUJD5HDMN7WE4WZ5/action/replication_record"}},"created_at":"2026-07-05T00:50:17.933058+00:00","updated_at":"2026-07-05T00:50:17.933058+00:00"}