{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HPX4RAAQHBDGQL2SORQ6UHDSNU","short_pith_number":"pith:HPX4RAAQ","schema_version":"1.0","canonical_sha256":"3befc880103846682f527461ea1c726d3fc7625716df95af3d5a5d8b3fe0a821","source":{"kind":"arxiv","id":"2009.12583","version":1},"attestation_state":"computed","paper":{"title":"Small Data, Big Decisions: Model Selection in the Small-Data Regime","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Francesco Visin, Jorg Bornschein, Simon Osindero","submitted_at":"2020-09-26T12:52:56Z","abstract_excerpt":"Highly overparametrized neural networks can display curiously strong generalization performance - a phenomenon that has recently garnered a wealth of theoretical and empirical research in order to better understand it. In contrast to most previous work, which typically considers the performance as a function of the model size, in this paper we empirically study the generalization performance as the size of the training set varies over multiple orders of magnitude. These systematic experiments lead to some interesting and potentially very useful observations; perhaps most notably that training "},"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":"2009.12583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T12:52:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d405e145d3c533c4d70abe31c4ea98e635780c332a8556ab3dad09ce894c5230","abstract_canon_sha256":"0e981228afe2bbe4bf41437692176a544bb632279d811ac8cb4bb87c69acc761"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:06.539372Z","signature_b64":"QQE30w3RgTRa1zdc0ft5sDERpGOLbyvE0hRtyWgnDu4pXK1XJ8TznseGSzPYHX/Zr5fviCxenyewh1lc6w+KAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3befc880103846682f527461ea1c726d3fc7625716df95af3d5a5d8b3fe0a821","last_reissued_at":"2026-07-05T01:38:06.538956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:06.538956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Small Data, Big Decisions: Model Selection in the Small-Data Regime","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Francesco Visin, Jorg Bornschein, Simon Osindero","submitted_at":"2020-09-26T12:52:56Z","abstract_excerpt":"Highly overparametrized neural networks can display curiously strong generalization performance - a phenomenon that has recently garnered a wealth of theoretical and empirical research in order to better understand it. In contrast to most previous work, which typically considers the performance as a function of the model size, in this paper we empirically study the generalization performance as the size of the training set varies over multiple orders of magnitude. These systematic experiments lead to some interesting and potentially very useful observations; perhaps most notably that training "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12583","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/2009.12583/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":"2009.12583","created_at":"2026-07-05T01:38:06.539018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.12583v1","created_at":"2026-07-05T01:38:06.539018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12583","created_at":"2026-07-05T01:38:06.539018+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPX4RAAQHBDG","created_at":"2026-07-05T01:38:06.539018+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPX4RAAQHBDGQL2S","created_at":"2026-07-05T01:38:06.539018+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPX4RAAQ","created_at":"2026-07-05T01:38:06.539018+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11773","citing_title":"Small Data Explainer -- The impact of small data methods in everyday life","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPX4RAAQHBDGQL2SORQ6UHDSNU","json":"https://pith.science/pith/HPX4RAAQHBDGQL2SORQ6UHDSNU.json","graph_json":"https://pith.science/api/pith-number/HPX4RAAQHBDGQL2SORQ6UHDSNU/graph.json","events_json":"https://pith.science/api/pith-number/HPX4RAAQHBDGQL2SORQ6UHDSNU/events.json","paper":"https://pith.science/paper/HPX4RAAQ"},"agent_actions":{"view_html":"https://pith.science/pith/HPX4RAAQHBDGQL2SORQ6UHDSNU","download_json":"https://pith.science/pith/HPX4RAAQHBDGQL2SORQ6UHDSNU.json","view_paper":"https://pith.science/paper/HPX4RAAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.12583&json=true","fetch_graph":"https://pith.science/api/pith-number/HPX4RAAQHBDGQL2SORQ6UHDSNU/graph.json","fetch_events":"https://pith.science/api/pith-number/HPX4RAAQHBDGQL2SORQ6UHDSNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPX4RAAQHBDGQL2SORQ6UHDSNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPX4RAAQHBDGQL2SORQ6UHDSNU/action/storage_attestation","attest_author":"https://pith.science/pith/HPX4RAAQHBDGQL2SORQ6UHDSNU/action/author_attestation","sign_citation":"https://pith.science/pith/HPX4RAAQHBDGQL2SORQ6UHDSNU/action/citation_signature","submit_replication":"https://pith.science/pith/HPX4RAAQHBDGQL2SORQ6UHDSNU/action/replication_record"}},"created_at":"2026-07-05T01:38:06.539018+00:00","updated_at":"2026-07-05T01:38:06.539018+00:00"}