{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6EVA74DGCGA2X4F6HBQXZSS6R5","short_pith_number":"pith:6EVA74DG","schema_version":"1.0","canonical_sha256":"f12a0ff0661181abf0be38617cca5e8f51fcded29aeae2c68fb4034011eb9538","source":{"kind":"arxiv","id":"2412.18296","version":2},"attestation_state":"computed","paper":{"title":"Navigating Data Corruption in Machine Learning: Balancing Quality, Quantity, and Imputation Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Qi Liu, Wanjing Ma","submitted_at":"2024-12-24T09:04:06Z","abstract_excerpt":"Data corruption, including missing and noisy data, poses significant challenges in real-world machine learning. This study investigates the effects of data corruption on model performance and explores strategies to mitigate these effects through two experimental setups: supervised learning with NLP tasks (NLP-SL) and deep reinforcement learning for traffic signal optimization (Signal-RL). We analyze the relationship between data corruption levels and model performance, evaluate the effectiveness of data imputation methods, and assess the utility of enlarging datasets to address data corruption"},"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":"2412.18296","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-24T09:04:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5abd21e975ec4ad064765e125785ad6b568e7a85a83f587b0296925a744a15ad","abstract_canon_sha256":"a571b49c5b159ffd60224d52078bf23ef6d381459a4c7f812f89896e52ceddc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:26.380537Z","signature_b64":"fiLS08SGC/bknTACxuczCIrEJi5qEyf48u7GQNZApLaGTXND7clqQ0onFfBhxHrA9Y2ogNYK3k0sDk5AyzbnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f12a0ff0661181abf0be38617cca5e8f51fcded29aeae2c68fb4034011eb9538","last_reissued_at":"2026-07-05T11:06:26.379941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:26.379941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigating Data Corruption in Machine Learning: Balancing Quality, Quantity, and Imputation Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Qi Liu, Wanjing Ma","submitted_at":"2024-12-24T09:04:06Z","abstract_excerpt":"Data corruption, including missing and noisy data, poses significant challenges in real-world machine learning. This study investigates the effects of data corruption on model performance and explores strategies to mitigate these effects through two experimental setups: supervised learning with NLP tasks (NLP-SL) and deep reinforcement learning for traffic signal optimization (Signal-RL). We analyze the relationship between data corruption levels and model performance, evaluate the effectiveness of data imputation methods, and assess the utility of enlarging datasets to address data corruption"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18296","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/2412.18296/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":"2412.18296","created_at":"2026-07-05T11:06:26.380003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18296v2","created_at":"2026-07-05T11:06:26.380003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18296","created_at":"2026-07-05T11:06:26.380003+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EVA74DGCGA2","created_at":"2026-07-05T11:06:26.380003+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EVA74DGCGA2X4F6","created_at":"2026-07-05T11:06:26.380003+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EVA74DG","created_at":"2026-07-05T11:06:26.380003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00348","citing_title":"Theory Foundation of Physics-Enhanced Residual Learning","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5","json":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5.json","graph_json":"https://pith.science/api/pith-number/6EVA74DGCGA2X4F6HBQXZSS6R5/graph.json","events_json":"https://pith.science/api/pith-number/6EVA74DGCGA2X4F6HBQXZSS6R5/events.json","paper":"https://pith.science/paper/6EVA74DG"},"agent_actions":{"view_html":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5","download_json":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5.json","view_paper":"https://pith.science/paper/6EVA74DG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18296&json=true","fetch_graph":"https://pith.science/api/pith-number/6EVA74DGCGA2X4F6HBQXZSS6R5/graph.json","fetch_events":"https://pith.science/api/pith-number/6EVA74DGCGA2X4F6HBQXZSS6R5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5/action/storage_attestation","attest_author":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5/action/author_attestation","sign_citation":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5/action/citation_signature","submit_replication":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5/action/replication_record"}},"created_at":"2026-07-05T11:06:26.380003+00:00","updated_at":"2026-07-05T11:06:26.380003+00:00"}