{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VSHF63RMNVV4YB75VCTLGOLS3N","short_pith_number":"pith:VSHF63RM","schema_version":"1.0","canonical_sha256":"ac8e5f6e2c6d6bcc07fda8a6b33972db6ac7596223bfa9e9d70abaac2604743b","source":{"kind":"arxiv","id":"1802.05846","version":1},"attestation_state":"computed","paper":{"title":"Train on Validation: Squeezing the Data Lemon","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Guy Tennenholtz, Shie Mannor, Tom Zahavy","submitted_at":"2018-02-16T06:50:19Z","abstract_excerpt":"Model selection on validation data is an essential step in machine learning. While the mixing of data between training and validation is considered taboo, practitioners often violate it to increase performance. Here, we offer a simple, practical method for using the validation set for training, which allows for a continuous, controlled trade-off between performance and overfitting of model selection. We define the notion of on-average-validation-stable algorithms as one in which using small portions of validation data for training does not overfit the model selection process. We then prove tha"},"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":"1802.05846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-16T06:50:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a0a89df8d4f8127ab3a309e41613d7ed2ca72d44dcd95e27c00020c87f82c18f","abstract_canon_sha256":"f5ca1ee11b4e5b37186ac6b0d381b3738161c5444340e030960619908b4842ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:10.811775Z","signature_b64":"TGRZltwIqAuM+xgc01KaLIzM1k5s2NXqa39xTzb22p7tvit28b9X8mkk8DKgWkiwhR6uMbeeniw4hqygsXUVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac8e5f6e2c6d6bcc07fda8a6b33972db6ac7596223bfa9e9d70abaac2604743b","last_reissued_at":"2026-05-18T00:23:10.811095Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:10.811095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Train on Validation: Squeezing the Data Lemon","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Guy Tennenholtz, Shie Mannor, Tom Zahavy","submitted_at":"2018-02-16T06:50:19Z","abstract_excerpt":"Model selection on validation data is an essential step in machine learning. While the mixing of data between training and validation is considered taboo, practitioners often violate it to increase performance. Here, we offer a simple, practical method for using the validation set for training, which allows for a continuous, controlled trade-off between performance and overfitting of model selection. We define the notion of on-average-validation-stable algorithms as one in which using small portions of validation data for training does not overfit the model selection process. We then prove tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05846","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":""},"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":"1802.05846","created_at":"2026-05-18T00:23:10.811218+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.05846v1","created_at":"2026-05-18T00:23:10.811218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05846","created_at":"2026-05-18T00:23:10.811218+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSHF63RMNVV4","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSHF63RMNVV4YB75","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSHF63RM","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VSHF63RMNVV4YB75VCTLGOLS3N","json":"https://pith.science/pith/VSHF63RMNVV4YB75VCTLGOLS3N.json","graph_json":"https://pith.science/api/pith-number/VSHF63RMNVV4YB75VCTLGOLS3N/graph.json","events_json":"https://pith.science/api/pith-number/VSHF63RMNVV4YB75VCTLGOLS3N/events.json","paper":"https://pith.science/paper/VSHF63RM"},"agent_actions":{"view_html":"https://pith.science/pith/VSHF63RMNVV4YB75VCTLGOLS3N","download_json":"https://pith.science/pith/VSHF63RMNVV4YB75VCTLGOLS3N.json","view_paper":"https://pith.science/paper/VSHF63RM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.05846&json=true","fetch_graph":"https://pith.science/api/pith-number/VSHF63RMNVV4YB75VCTLGOLS3N/graph.json","fetch_events":"https://pith.science/api/pith-number/VSHF63RMNVV4YB75VCTLGOLS3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSHF63RMNVV4YB75VCTLGOLS3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSHF63RMNVV4YB75VCTLGOLS3N/action/storage_attestation","attest_author":"https://pith.science/pith/VSHF63RMNVV4YB75VCTLGOLS3N/action/author_attestation","sign_citation":"https://pith.science/pith/VSHF63RMNVV4YB75VCTLGOLS3N/action/citation_signature","submit_replication":"https://pith.science/pith/VSHF63RMNVV4YB75VCTLGOLS3N/action/replication_record"}},"created_at":"2026-05-18T00:23:10.811218+00:00","updated_at":"2026-05-18T00:23:10.811218+00:00"}