{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6EVA74DGCGA2X4F6HBQXZSS6R5","short_pith_number":"pith:6EVA74DG","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"},"canonical_sha256":"f12a0ff0661181abf0be38617cca5e8f51fcded29aeae2c68fb4034011eb9538","source":{"kind":"arxiv","id":"2412.18296","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18296","created_at":"2026-07-05T11:06:26Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18296v2","created_at":"2026-07-05T11:06:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18296","created_at":"2026-07-05T11:06:26Z"},{"alias_kind":"pith_short_12","alias_value":"6EVA74DGCGA2","created_at":"2026-07-05T11:06:26Z"},{"alias_kind":"pith_short_16","alias_value":"6EVA74DGCGA2X4F6","created_at":"2026-07-05T11:06:26Z"},{"alias_kind":"pith_short_8","alias_value":"6EVA74DG","created_at":"2026-07-05T11:06:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6EVA74DGCGA2X4F6HBQXZSS6R5","target":"record","payload":{"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"},"canonical_sha256":"f12a0ff0661181abf0be38617cca5e8f51fcded29aeae2c68fb4034011eb9538","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"},"source_kind":"arxiv","source_id":"2412.18296","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:06:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RPynNd1RuaYBR8J5VT90+R8Gd83WOlciEDR2lL5OkybOs6Ld8xQyu/Mb8Tc/GHI/vhahcJSZhUnzC2PIZ7MHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:55:09.145080Z"},"content_sha256":"b72e948d8108541393b8d72c637afb2429a44198d0c73c22498db8293d555ba2","schema_version":"1.0","event_id":"sha256:b72e948d8108541393b8d72c637afb2429a44198d0c73c22498db8293d555ba2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6EVA74DGCGA2X4F6HBQXZSS6R5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:06:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CzWhzEcRF97sZc2Eg/2KLSB4O7JMMcWwUwvrrAriOVSeUL4EbU+fXc79jdv0tHBAof1wta4YzWhsMBeALT70DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:55:09.146044Z"},"content_sha256":"6ff940df7492ae8b18dd6ae1ef6c338d2dd4a7757e372e6d34460cb8d3de0836","schema_version":"1.0","event_id":"sha256:6ff940df7492ae8b18dd6ae1ef6c338d2dd4a7757e372e6d34460cb8d3de0836"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5/bundle.json","state_url":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EVA74DGCGA2X4F6HBQXZSS6R5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T18:55:09Z","links":{"resolver":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5","bundle":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5/bundle.json","state":"https://pith.science/pith/6EVA74DGCGA2X4F6HBQXZSS6R5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EVA74DGCGA2X4F6HBQXZSS6R5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6EVA74DGCGA2X4F6HBQXZSS6R5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a571b49c5b159ffd60224d52078bf23ef6d381459a4c7f812f89896e52ceddc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-24T09:04:06Z","title_canon_sha256":"5abd21e975ec4ad064765e125785ad6b568e7a85a83f587b0296925a744a15ad"},"schema_version":"1.0","source":{"id":"2412.18296","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18296","created_at":"2026-07-05T11:06:26Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18296v2","created_at":"2026-07-05T11:06:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18296","created_at":"2026-07-05T11:06:26Z"},{"alias_kind":"pith_short_12","alias_value":"6EVA74DGCGA2","created_at":"2026-07-05T11:06:26Z"},{"alias_kind":"pith_short_16","alias_value":"6EVA74DGCGA2X4F6","created_at":"2026-07-05T11:06:26Z"},{"alias_kind":"pith_short_8","alias_value":"6EVA74DG","created_at":"2026-07-05T11:06:26Z"}],"graph_snapshots":[{"event_id":"sha256:6ff940df7492ae8b18dd6ae1ef6c338d2dd4a7757e372e6d34460cb8d3de0836","target":"graph","created_at":"2026-07-05T11:06:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.18296/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Qi Liu, Wanjing Ma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-24T09:04:06Z","title":"Navigating Data Corruption in Machine Learning: Balancing Quality, Quantity, and Imputation Strategies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18296","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b72e948d8108541393b8d72c637afb2429a44198d0c73c22498db8293d555ba2","target":"record","created_at":"2026-07-05T11:06:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a571b49c5b159ffd60224d52078bf23ef6d381459a4c7f812f89896e52ceddc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-24T09:04:06Z","title_canon_sha256":"5abd21e975ec4ad064765e125785ad6b568e7a85a83f587b0296925a744a15ad"},"schema_version":"1.0","source":{"id":"2412.18296","kind":"arxiv","version":2}},"canonical_sha256":"f12a0ff0661181abf0be38617cca5e8f51fcded29aeae2c68fb4034011eb9538","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f12a0ff0661181abf0be38617cca5e8f51fcded29aeae2c68fb4034011eb9538","first_computed_at":"2026-07-05T11:06:26.379941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:26.379941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fiLS08SGC/bknTACxuczCIrEJi5qEyf48u7GQNZApLaGTXND7clqQ0onFfBhxHrA9Y2ogNYK3k0sDk5AyzbnAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:26.380537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18296","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b72e948d8108541393b8d72c637afb2429a44198d0c73c22498db8293d555ba2","sha256:6ff940df7492ae8b18dd6ae1ef6c338d2dd4a7757e372e6d34460cb8d3de0836"],"state_sha256":"7d526805bba232975e599e2e9cf98b97c3f1accd681772e3725d7b41740826eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dMUruv4c+0P+mBLzoerteMugiVa/g6TnhSigJLBPp+vBmXjZHyB+Uy6kGgwSbf14wKfVH0rNTp5+eRQ+Of6UDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:55:09.152077Z","bundle_sha256":"9a4fd5cf669e5e6ebc969eb1affb4cf980b722929cb85518df8db44396a35b51"}}