{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LFQAFOV4KPJ36VXX357HPB73OK","short_pith_number":"pith:LFQAFOV4","schema_version":"1.0","canonical_sha256":"596002babc53d3bf56f7df7e7787fb72aa043cc6cbfc21e46b61e0b21d01a791","source":{"kind":"arxiv","id":"2205.07116","version":1},"attestation_state":"computed","paper":{"title":"Practical Insights of Repairing Model Problems on Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Akihito Yoshii, Fuyuki Ishikawa, Susumu Tokumoto","submitted_at":"2022-05-14T19:28:55Z","abstract_excerpt":"Additional training of a deep learning model can cause negative effects on the results, turning an initially positive sample into a negative one (degradation). Such degradation is possible in real-world use cases due to the diversity of sample characteristics. That is, a set of samples is a mixture of critical ones which should not be missed and less important ones. Therefore, we cannot understand the performance by accuracy alone. While existing research aims to prevent a model degradation, insights into the related methods are needed to grasp their benefits and limitations. In this talk, we "},"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":"2205.07116","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-14T19:28:55Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"6a4f77a4974c826b4e3961ce628f5e84044a7dd8d4cf01380272b5a6a9a9adbd","abstract_canon_sha256":"f55bd28b072e00d9700c49261b61de4515112baa9d15209ef1f9ffd22c9bd218"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:26.310675Z","signature_b64":"L16/9qR+Gaewwb08Ac9n/zXVrthduJdp86QjQ6SwhUKGMV4vK3+KOmH7PNGZQ8Rc3mtJIlsAuUHuUHmNoAgoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"596002babc53d3bf56f7df7e7787fb72aa043cc6cbfc21e46b61e0b21d01a791","last_reissued_at":"2026-07-05T04:24:26.310324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:26.310324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Practical Insights of Repairing Model Problems on Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Akihito Yoshii, Fuyuki Ishikawa, Susumu Tokumoto","submitted_at":"2022-05-14T19:28:55Z","abstract_excerpt":"Additional training of a deep learning model can cause negative effects on the results, turning an initially positive sample into a negative one (degradation). Such degradation is possible in real-world use cases due to the diversity of sample characteristics. That is, a set of samples is a mixture of critical ones which should not be missed and less important ones. Therefore, we cannot understand the performance by accuracy alone. While existing research aims to prevent a model degradation, insights into the related methods are needed to grasp their benefits and limitations. In this talk, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07116","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/2205.07116/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":"2205.07116","created_at":"2026-07-05T04:24:26.310382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.07116v1","created_at":"2026-07-05T04:24:26.310382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07116","created_at":"2026-07-05T04:24:26.310382+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFQAFOV4KPJ3","created_at":"2026-07-05T04:24:26.310382+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFQAFOV4KPJ36VXX","created_at":"2026-07-05T04:24:26.310382+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFQAFOV4","created_at":"2026-07-05T04:24:26.310382+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/LFQAFOV4KPJ36VXX357HPB73OK","json":"https://pith.science/pith/LFQAFOV4KPJ36VXX357HPB73OK.json","graph_json":"https://pith.science/api/pith-number/LFQAFOV4KPJ36VXX357HPB73OK/graph.json","events_json":"https://pith.science/api/pith-number/LFQAFOV4KPJ36VXX357HPB73OK/events.json","paper":"https://pith.science/paper/LFQAFOV4"},"agent_actions":{"view_html":"https://pith.science/pith/LFQAFOV4KPJ36VXX357HPB73OK","download_json":"https://pith.science/pith/LFQAFOV4KPJ36VXX357HPB73OK.json","view_paper":"https://pith.science/paper/LFQAFOV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.07116&json=true","fetch_graph":"https://pith.science/api/pith-number/LFQAFOV4KPJ36VXX357HPB73OK/graph.json","fetch_events":"https://pith.science/api/pith-number/LFQAFOV4KPJ36VXX357HPB73OK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFQAFOV4KPJ36VXX357HPB73OK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFQAFOV4KPJ36VXX357HPB73OK/action/storage_attestation","attest_author":"https://pith.science/pith/LFQAFOV4KPJ36VXX357HPB73OK/action/author_attestation","sign_citation":"https://pith.science/pith/LFQAFOV4KPJ36VXX357HPB73OK/action/citation_signature","submit_replication":"https://pith.science/pith/LFQAFOV4KPJ36VXX357HPB73OK/action/replication_record"}},"created_at":"2026-07-05T04:24:26.310382+00:00","updated_at":"2026-07-05T04:24:26.310382+00:00"}