{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VLISBUVAFNIXCJ54AUWSYWF3BO","short_pith_number":"pith:VLISBUVA","schema_version":"1.0","canonical_sha256":"aad120d2a02b517127bc052d2c58bb0b8f4b17bc9956fdb4f4931d018ecf7d2b","source":{"kind":"arxiv","id":"2412.02313","version":1},"attestation_state":"computed","paper":{"title":"Noisy Ostracods: A Fine-Grained, Imbalanced Real-World Dataset for Benchmarking Robust Machine Learning and Label Correction Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"He Wang, Jiamian Hu, Moriaki Yasuhara, Yihua Chen, Yuanyuan Hong","submitted_at":"2024-12-03T09:30:57Z","abstract_excerpt":"We present the Noisy Ostracods, a noisy dataset for genus and species classification of crustacean ostracods with specialists' annotations. Over the 71466 specimens collected, 5.58% of them are estimated to be noisy (possibly problematic) at genus level. The dataset is created to addressing a real-world challenge: creating a clean fine-grained taxonomy dataset. The Noisy Ostracods dataset has diverse noises from multiple sources. Firstly, the noise is open-set, including new classes discovered during curation that were not part of the original annotation. The dataset has pseudo-classes, where "},"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":"2412.02313","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-03T09:30:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"17b5747cc4f7bf7ec8a5f6cc35b915b2d508b08d344ec9b1ed1d48c16ab1bee2","abstract_canon_sha256":"f04d8963875281d746f24760dbbc668ec6951babc7fec6d6d708d21cbc2b2b74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:47.995672Z","signature_b64":"5amn99yFSuZGb2Hvqn7MrqDg0EFnWSJkgRC3FvmhdkFWtIb4cZcPZxY5QeVurV9epREnwJwxdW5M2Y4bRHliAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aad120d2a02b517127bc052d2c58bb0b8f4b17bc9956fdb4f4931d018ecf7d2b","last_reissued_at":"2026-07-05T09:43:47.995227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:47.995227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noisy Ostracods: A Fine-Grained, Imbalanced Real-World Dataset for Benchmarking Robust Machine Learning and Label Correction Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"He Wang, Jiamian Hu, Moriaki Yasuhara, Yihua Chen, Yuanyuan Hong","submitted_at":"2024-12-03T09:30:57Z","abstract_excerpt":"We present the Noisy Ostracods, a noisy dataset for genus and species classification of crustacean ostracods with specialists' annotations. Over the 71466 specimens collected, 5.58% of them are estimated to be noisy (possibly problematic) at genus level. The dataset is created to addressing a real-world challenge: creating a clean fine-grained taxonomy dataset. The Noisy Ostracods dataset has diverse noises from multiple sources. Firstly, the noise is open-set, including new classes discovered during curation that were not part of the original annotation. The dataset has pseudo-classes, where "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02313","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/2412.02313/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":"2412.02313","created_at":"2026-07-05T09:43:47.995276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02313v1","created_at":"2026-07-05T09:43:47.995276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02313","created_at":"2026-07-05T09:43:47.995276+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLISBUVAFNIX","created_at":"2026-07-05T09:43:47.995276+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLISBUVAFNIXCJ54","created_at":"2026-07-05T09:43:47.995276+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLISBUVA","created_at":"2026-07-05T09:43:47.995276+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/VLISBUVAFNIXCJ54AUWSYWF3BO","json":"https://pith.science/pith/VLISBUVAFNIXCJ54AUWSYWF3BO.json","graph_json":"https://pith.science/api/pith-number/VLISBUVAFNIXCJ54AUWSYWF3BO/graph.json","events_json":"https://pith.science/api/pith-number/VLISBUVAFNIXCJ54AUWSYWF3BO/events.json","paper":"https://pith.science/paper/VLISBUVA"},"agent_actions":{"view_html":"https://pith.science/pith/VLISBUVAFNIXCJ54AUWSYWF3BO","download_json":"https://pith.science/pith/VLISBUVAFNIXCJ54AUWSYWF3BO.json","view_paper":"https://pith.science/paper/VLISBUVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02313&json=true","fetch_graph":"https://pith.science/api/pith-number/VLISBUVAFNIXCJ54AUWSYWF3BO/graph.json","fetch_events":"https://pith.science/api/pith-number/VLISBUVAFNIXCJ54AUWSYWF3BO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLISBUVAFNIXCJ54AUWSYWF3BO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLISBUVAFNIXCJ54AUWSYWF3BO/action/storage_attestation","attest_author":"https://pith.science/pith/VLISBUVAFNIXCJ54AUWSYWF3BO/action/author_attestation","sign_citation":"https://pith.science/pith/VLISBUVAFNIXCJ54AUWSYWF3BO/action/citation_signature","submit_replication":"https://pith.science/pith/VLISBUVAFNIXCJ54AUWSYWF3BO/action/replication_record"}},"created_at":"2026-07-05T09:43:47.995276+00:00","updated_at":"2026-07-05T09:43:47.995276+00:00"}