{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:ISLLBZE2ZNTCW5YQSTOJO6I27A","short_pith_number":"pith:ISLLBZE2","schema_version":"1.0","canonical_sha256":"4496b0e49acb662b771094dc97791af814dd9c18930688f62394f004d2d175d0","source":{"kind":"arxiv","id":"1511.07069","version":2},"attestation_state":"computed","paper":{"title":"Auxiliary Image Regularization for Deep CNNs with Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiashi Feng, Samaneh Azadi, Stefanie Jegelka, Trevor Darrell","submitted_at":"2015-11-22T20:59:19Z","abstract_excerpt":"Precisely-labeled data sets with sufficient amount of samples are very important for training deep convolutional neural networks (CNNs). However, many of the available real-world data sets contain erroneously labeled samples and those errors substantially hinder the learning of very accurate CNN models. In this work, we consider the problem of training a deep CNN model for image classification with mislabeled training samples - an issue that is common in real image data sets with tags supplied by amateur users. To solve this problem, we propose an auxiliary image regularization technique, opti"},"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":"1511.07069","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-22T20:59:19Z","cross_cats_sorted":[],"title_canon_sha256":"70041bea7ebaa645ffaf78ca14a084357373f58b437241c4137a62e87d9b0e6f","abstract_canon_sha256":"0803ae16d70139db869b98359cabbcafb2a912b43d73e587fc165fa3a52c3567"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:43.991548Z","signature_b64":"3RhS8ycA745xh0xmgA/z6CjrQBOGPwxNbS1y3uES4NItLJnTrYGowQe62My3NKcVHctG6IYVvopWMFb+Fx8DBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4496b0e49acb662b771094dc97791af814dd9c18930688f62394f004d2d175d0","last_reissued_at":"2026-05-18T01:19:43.991032Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:43.991032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auxiliary Image Regularization for Deep CNNs with Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiashi Feng, Samaneh Azadi, Stefanie Jegelka, Trevor Darrell","submitted_at":"2015-11-22T20:59:19Z","abstract_excerpt":"Precisely-labeled data sets with sufficient amount of samples are very important for training deep convolutional neural networks (CNNs). However, many of the available real-world data sets contain erroneously labeled samples and those errors substantially hinder the learning of very accurate CNN models. In this work, we consider the problem of training a deep CNN model for image classification with mislabeled training samples - an issue that is common in real image data sets with tags supplied by amateur users. To solve this problem, we propose an auxiliary image regularization technique, opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07069","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":""},"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":"1511.07069","created_at":"2026-05-18T01:19:43.991116+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.07069v2","created_at":"2026-05-18T01:19:43.991116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07069","created_at":"2026-05-18T01:19:43.991116+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISLLBZE2ZNTC","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISLLBZE2ZNTCW5YQ","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISLLBZE2","created_at":"2026-05-18T12:29:25.134429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07471","citing_title":"Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ISLLBZE2ZNTCW5YQSTOJO6I27A","json":"https://pith.science/pith/ISLLBZE2ZNTCW5YQSTOJO6I27A.json","graph_json":"https://pith.science/api/pith-number/ISLLBZE2ZNTCW5YQSTOJO6I27A/graph.json","events_json":"https://pith.science/api/pith-number/ISLLBZE2ZNTCW5YQSTOJO6I27A/events.json","paper":"https://pith.science/paper/ISLLBZE2"},"agent_actions":{"view_html":"https://pith.science/pith/ISLLBZE2ZNTCW5YQSTOJO6I27A","download_json":"https://pith.science/pith/ISLLBZE2ZNTCW5YQSTOJO6I27A.json","view_paper":"https://pith.science/paper/ISLLBZE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.07069&json=true","fetch_graph":"https://pith.science/api/pith-number/ISLLBZE2ZNTCW5YQSTOJO6I27A/graph.json","fetch_events":"https://pith.science/api/pith-number/ISLLBZE2ZNTCW5YQSTOJO6I27A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISLLBZE2ZNTCW5YQSTOJO6I27A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISLLBZE2ZNTCW5YQSTOJO6I27A/action/storage_attestation","attest_author":"https://pith.science/pith/ISLLBZE2ZNTCW5YQSTOJO6I27A/action/author_attestation","sign_citation":"https://pith.science/pith/ISLLBZE2ZNTCW5YQSTOJO6I27A/action/citation_signature","submit_replication":"https://pith.science/pith/ISLLBZE2ZNTCW5YQSTOJO6I27A/action/replication_record"}},"created_at":"2026-05-18T01:19:43.991116+00:00","updated_at":"2026-05-18T01:19:43.991116+00:00"}