{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TLU5LXYHMO5YRWUW6ZPELDFHBI","short_pith_number":"pith:TLU5LXYH","schema_version":"1.0","canonical_sha256":"9ae9d5df0763bb88da96f65e458ca70a2ca3abf8af163ddc9fdbe1ac2bce7112","source":{"kind":"arxiv","id":"2307.16889","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.LG","authors_text":"Changjie Fan, Haobo Wang, Haoyu Liu, Minmin Lin, Renyu Zhu, Runze Wu, Tangjie Lv","submitted_at":"2023-07-28T10:57:38Z","abstract_excerpt":"In this paper, we investigate the problem of learning with noisy labels in real-world annotation scenarios, where noise can be categorized into two types: factual noise and ambiguity noise. To better distinguish these noise types and utilize their semantics, we propose a novel sample selection-based approach for noisy label learning, called Proto-semi. Proto-semi initially divides all samples into the confident and unconfident datasets via warm-up. By leveraging the confident dataset, prototype vectors are constructed to capture class characteristics. Subsequently, the distances between the un"},"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":"2307.16889","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-28T10:57:38Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"46e9a6323c7f17b3b56835414c6f4ef713ab868e070a2e3493dd0ed7ef3c14db","abstract_canon_sha256":"c7ca2d8e5a61edee0808b10c790be3bfa69aaecf6d41388a512e6245565e5b54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:24.613440Z","signature_b64":"C09n5Zr1uAQpuT0qkryhG/IGZzf95qPePuMvXFi3fZ6m4pt2GIr12fwHvA92pYutjZ5+xOq7FdotyjdxBoCkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ae9d5df0763bb88da96f65e458ca70a2ca3abf8af163ddc9fdbe1ac2bce7112","last_reissued_at":"2026-07-05T06:43:24.612747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:24.612747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.LG","authors_text":"Changjie Fan, Haobo Wang, Haoyu Liu, Minmin Lin, Renyu Zhu, Runze Wu, Tangjie Lv","submitted_at":"2023-07-28T10:57:38Z","abstract_excerpt":"In this paper, we investigate the problem of learning with noisy labels in real-world annotation scenarios, where noise can be categorized into two types: factual noise and ambiguity noise. To better distinguish these noise types and utilize their semantics, we propose a novel sample selection-based approach for noisy label learning, called Proto-semi. Proto-semi initially divides all samples into the confident and unconfident datasets via warm-up. By leveraging the confident dataset, prototype vectors are constructed to capture class characteristics. Subsequently, the distances between the un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16889","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/2307.16889/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":"2307.16889","created_at":"2026-07-05T06:43:24.613042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.16889v2","created_at":"2026-07-05T06:43:24.613042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16889","created_at":"2026-07-05T06:43:24.613042+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLU5LXYHMO5Y","created_at":"2026-07-05T06:43:24.613042+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLU5LXYHMO5YRWUW","created_at":"2026-07-05T06:43:24.613042+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLU5LXYH","created_at":"2026-07-05T06:43:24.613042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06622","citing_title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TLU5LXYHMO5YRWUW6ZPELDFHBI","json":"https://pith.science/pith/TLU5LXYHMO5YRWUW6ZPELDFHBI.json","graph_json":"https://pith.science/api/pith-number/TLU5LXYHMO5YRWUW6ZPELDFHBI/graph.json","events_json":"https://pith.science/api/pith-number/TLU5LXYHMO5YRWUW6ZPELDFHBI/events.json","paper":"https://pith.science/paper/TLU5LXYH"},"agent_actions":{"view_html":"https://pith.science/pith/TLU5LXYHMO5YRWUW6ZPELDFHBI","download_json":"https://pith.science/pith/TLU5LXYHMO5YRWUW6ZPELDFHBI.json","view_paper":"https://pith.science/paper/TLU5LXYH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.16889&json=true","fetch_graph":"https://pith.science/api/pith-number/TLU5LXYHMO5YRWUW6ZPELDFHBI/graph.json","fetch_events":"https://pith.science/api/pith-number/TLU5LXYHMO5YRWUW6ZPELDFHBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLU5LXYHMO5YRWUW6ZPELDFHBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLU5LXYHMO5YRWUW6ZPELDFHBI/action/storage_attestation","attest_author":"https://pith.science/pith/TLU5LXYHMO5YRWUW6ZPELDFHBI/action/author_attestation","sign_citation":"https://pith.science/pith/TLU5LXYHMO5YRWUW6ZPELDFHBI/action/citation_signature","submit_replication":"https://pith.science/pith/TLU5LXYHMO5YRWUW6ZPELDFHBI/action/replication_record"}},"created_at":"2026-07-05T06:43:24.613042+00:00","updated_at":"2026-07-05T06:43:24.613042+00:00"}