{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CJ4IXANORGA5K5IU27GOYWSYWT","short_pith_number":"pith:CJ4IXANO","schema_version":"1.0","canonical_sha256":"12788b81ae8981d57514d7ccec5a58b4f078e49d01f1077a58e62c4e31e98421","source":{"kind":"arxiv","id":"2007.01016","version":1},"attestation_state":"computed","paper":{"title":"A Novel DNN Training Framework via Data Sampling and Multi-Task Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.NE","authors_text":"A. K. Qin, Boyu Zhang, Hong Pan, Timos Sellis","submitted_at":"2020-07-02T10:58:57Z","abstract_excerpt":"Conventional DNN training paradigms typically rely on one training set and one validation set, obtained by partitioning an annotated dataset used for training, namely gross training set, in a certain way. The training set is used for training the model while the validation set is used to estimate the generalization performance of the trained model as the training proceeds to avoid over-fitting. There exist two major issues in this paradigm. Firstly, the validation set may hardly guarantee an unbiased estimate of generalization performance due to potential mismatching with test data. Secondly, "},"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":"2007.01016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2020-07-02T10:58:57Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"bcf13048cb76f87b63f5038a6610451536731dc153fdcf8d1cd93e18e8a3bc89","abstract_canon_sha256":"4c9df70261aeba81629063f11e5f98943e6244618f6e179930c264c51daa1e39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:43.951296Z","signature_b64":"o2giZjnlBflvmPqaTorSXvolcORF+vVa3/dK1XW8HJ9SlIczvSmUPLbljdPrDAT1uCP2PO/SR/c0eKATYMOjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12788b81ae8981d57514d7ccec5a58b4f078e49d01f1077a58e62c4e31e98421","last_reissued_at":"2026-07-05T01:15:43.950873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:43.950873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Novel DNN Training Framework via Data Sampling and Multi-Task Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.NE","authors_text":"A. K. Qin, Boyu Zhang, Hong Pan, Timos Sellis","submitted_at":"2020-07-02T10:58:57Z","abstract_excerpt":"Conventional DNN training paradigms typically rely on one training set and one validation set, obtained by partitioning an annotated dataset used for training, namely gross training set, in a certain way. The training set is used for training the model while the validation set is used to estimate the generalization performance of the trained model as the training proceeds to avoid over-fitting. There exist two major issues in this paradigm. Firstly, the validation set may hardly guarantee an unbiased estimate of generalization performance due to potential mismatching with test data. Secondly, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01016","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/2007.01016/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":"2007.01016","created_at":"2026-07-05T01:15:43.950946+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.01016v1","created_at":"2026-07-05T01:15:43.950946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01016","created_at":"2026-07-05T01:15:43.950946+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJ4IXANORGA5","created_at":"2026-07-05T01:15:43.950946+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJ4IXANORGA5K5IU","created_at":"2026-07-05T01:15:43.950946+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJ4IXANO","created_at":"2026-07-05T01:15:43.950946+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/CJ4IXANORGA5K5IU27GOYWSYWT","json":"https://pith.science/pith/CJ4IXANORGA5K5IU27GOYWSYWT.json","graph_json":"https://pith.science/api/pith-number/CJ4IXANORGA5K5IU27GOYWSYWT/graph.json","events_json":"https://pith.science/api/pith-number/CJ4IXANORGA5K5IU27GOYWSYWT/events.json","paper":"https://pith.science/paper/CJ4IXANO"},"agent_actions":{"view_html":"https://pith.science/pith/CJ4IXANORGA5K5IU27GOYWSYWT","download_json":"https://pith.science/pith/CJ4IXANORGA5K5IU27GOYWSYWT.json","view_paper":"https://pith.science/paper/CJ4IXANO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.01016&json=true","fetch_graph":"https://pith.science/api/pith-number/CJ4IXANORGA5K5IU27GOYWSYWT/graph.json","fetch_events":"https://pith.science/api/pith-number/CJ4IXANORGA5K5IU27GOYWSYWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJ4IXANORGA5K5IU27GOYWSYWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJ4IXANORGA5K5IU27GOYWSYWT/action/storage_attestation","attest_author":"https://pith.science/pith/CJ4IXANORGA5K5IU27GOYWSYWT/action/author_attestation","sign_citation":"https://pith.science/pith/CJ4IXANORGA5K5IU27GOYWSYWT/action/citation_signature","submit_replication":"https://pith.science/pith/CJ4IXANORGA5K5IU27GOYWSYWT/action/replication_record"}},"created_at":"2026-07-05T01:15:43.950946+00:00","updated_at":"2026-07-05T01:15:43.950946+00:00"}