{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YDUXOHGHNTHCRCUGXSY5TJBCPV","short_pith_number":"pith:YDUXOHGH","schema_version":"1.0","canonical_sha256":"c0e9771cc76cce288a86bcb1d9a4227d49ad99470b74a92eacdeca9c5d687169","source":{"kind":"arxiv","id":"2103.15383","version":2},"attestation_state":"computed","paper":{"title":"Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiali Deng, Minghui Liu, Ming Liu, Qifeng Weng, Tianshu Xie, Xiaomin Wang, Xuan Cheng","submitted_at":"2021-03-29T07:21:06Z","abstract_excerpt":"In this paper, we propose Selective Output Smoothing Regularization, a novel regularization method for training the Convolutional Neural Networks (CNNs). Inspired by the diverse effects on training from different samples, Selective Output Smoothing Regularization improves the performance by encouraging the model to produce equal logits on incorrect classes when dealing with samples that the model classifies correctly and over-confidently. This plug-and-play regularization method can be conveniently incorporated into almost any CNN-based project without extra hassle. Extensive experiments have "},"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":"2103.15383","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-29T07:21:06Z","cross_cats_sorted":[],"title_canon_sha256":"cb1fc364d7905bd1ec0460b94a8aa6481c82c4a1614bccdf59b31c7ded58303a","abstract_canon_sha256":"ef17faadd09ad47a97e97ab8cee9c35f99964e1d3df0b515117d3a85c35c97e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:13.732649Z","signature_b64":"/CgGN5bNQVHk/Cn9bsEiZEeayngfmJyGa742r2PlHk3x2DUPjyQ+w4kiTXE4l6x5+fKJKJO27UhW8B1eGHSmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0e9771cc76cce288a86bcb1d9a4227d49ad99470b74a92eacdeca9c5d687169","last_reissued_at":"2026-07-05T04:09:13.732117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:13.732117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiali Deng, Minghui Liu, Ming Liu, Qifeng Weng, Tianshu Xie, Xiaomin Wang, Xuan Cheng","submitted_at":"2021-03-29T07:21:06Z","abstract_excerpt":"In this paper, we propose Selective Output Smoothing Regularization, a novel regularization method for training the Convolutional Neural Networks (CNNs). Inspired by the diverse effects on training from different samples, Selective Output Smoothing Regularization improves the performance by encouraging the model to produce equal logits on incorrect classes when dealing with samples that the model classifies correctly and over-confidently. This plug-and-play regularization method can be conveniently incorporated into almost any CNN-based project without extra hassle. Extensive experiments have "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15383","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/2103.15383/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":"2103.15383","created_at":"2026-07-05T04:09:13.732186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.15383v2","created_at":"2026-07-05T04:09:13.732186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15383","created_at":"2026-07-05T04:09:13.732186+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDUXOHGHNTHC","created_at":"2026-07-05T04:09:13.732186+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDUXOHGHNTHCRCUG","created_at":"2026-07-05T04:09:13.732186+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDUXOHGH","created_at":"2026-07-05T04:09:13.732186+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/YDUXOHGHNTHCRCUGXSY5TJBCPV","json":"https://pith.science/pith/YDUXOHGHNTHCRCUGXSY5TJBCPV.json","graph_json":"https://pith.science/api/pith-number/YDUXOHGHNTHCRCUGXSY5TJBCPV/graph.json","events_json":"https://pith.science/api/pith-number/YDUXOHGHNTHCRCUGXSY5TJBCPV/events.json","paper":"https://pith.science/paper/YDUXOHGH"},"agent_actions":{"view_html":"https://pith.science/pith/YDUXOHGHNTHCRCUGXSY5TJBCPV","download_json":"https://pith.science/pith/YDUXOHGHNTHCRCUGXSY5TJBCPV.json","view_paper":"https://pith.science/paper/YDUXOHGH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.15383&json=true","fetch_graph":"https://pith.science/api/pith-number/YDUXOHGHNTHCRCUGXSY5TJBCPV/graph.json","fetch_events":"https://pith.science/api/pith-number/YDUXOHGHNTHCRCUGXSY5TJBCPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDUXOHGHNTHCRCUGXSY5TJBCPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDUXOHGHNTHCRCUGXSY5TJBCPV/action/storage_attestation","attest_author":"https://pith.science/pith/YDUXOHGHNTHCRCUGXSY5TJBCPV/action/author_attestation","sign_citation":"https://pith.science/pith/YDUXOHGHNTHCRCUGXSY5TJBCPV/action/citation_signature","submit_replication":"https://pith.science/pith/YDUXOHGHNTHCRCUGXSY5TJBCPV/action/replication_record"}},"created_at":"2026-07-05T04:09:13.732186+00:00","updated_at":"2026-07-05T04:09:13.732186+00:00"}