{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2FXKHS3VTCMKX3SQQ6JR6G7G6I","short_pith_number":"pith:2FXKHS3V","schema_version":"1.0","canonical_sha256":"d16ea3cb759898abee5087931f1be6f21acc21befc7308cd9ae484264e397acc","source":{"kind":"arxiv","id":"2203.17020","version":1},"attestation_state":"computed","paper":{"title":"Logit Normalization for Long-tail Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liang Zhao, Limin Wang, Yao Teng","submitted_at":"2022-03-31T13:28:51Z","abstract_excerpt":"Real-world data exhibiting skewed distributions pose a serious challenge to existing object detectors. Moreover, the samplers in detectors lead to shifted training label distributions, while the tremendous proportion of background to foreground samples severely harms foreground classification. To mitigate these issues, in this paper, we propose Logit Normalization (LogN), a simple technique to self-calibrate the classified logits of detectors in a similar way to batch normalization. In general, our LogN is training- and tuning-free (i.e. require no extra training and tuning process), model- an"},"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":"2203.17020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-31T13:28:51Z","cross_cats_sorted":[],"title_canon_sha256":"612e6c4b0ed8bf6ee0fead27a5620f9bf7138e15ec707b4f01dc6d3a3138ea0f","abstract_canon_sha256":"447309313ecdd0b3e9b66797a0591844821916460b5b74e741e86c6cf5af28fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:30.711269Z","signature_b64":"ynXCdJ+q1+cKeRplYrg+PSub/U9cdRzPPxI1MNR6J32f5970bve81iGlxpWejPLwgBc4KGEhM/Ln0e6ezpHGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d16ea3cb759898abee5087931f1be6f21acc21befc7308cd9ae484264e397acc","last_reissued_at":"2026-07-05T04:10:30.710836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:30.710836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logit Normalization for Long-tail Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liang Zhao, Limin Wang, Yao Teng","submitted_at":"2022-03-31T13:28:51Z","abstract_excerpt":"Real-world data exhibiting skewed distributions pose a serious challenge to existing object detectors. Moreover, the samplers in detectors lead to shifted training label distributions, while the tremendous proportion of background to foreground samples severely harms foreground classification. To mitigate these issues, in this paper, we propose Logit Normalization (LogN), a simple technique to self-calibrate the classified logits of detectors in a similar way to batch normalization. In general, our LogN is training- and tuning-free (i.e. require no extra training and tuning process), model- an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.17020","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/2203.17020/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":"2203.17020","created_at":"2026-07-05T04:10:30.710902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.17020v1","created_at":"2026-07-05T04:10:30.710902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.17020","created_at":"2026-07-05T04:10:30.710902+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FXKHS3VTCMK","created_at":"2026-07-05T04:10:30.710902+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FXKHS3VTCMKX3SQ","created_at":"2026-07-05T04:10:30.710902+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FXKHS3V","created_at":"2026-07-05T04:10:30.710902+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/2FXKHS3VTCMKX3SQQ6JR6G7G6I","json":"https://pith.science/pith/2FXKHS3VTCMKX3SQQ6JR6G7G6I.json","graph_json":"https://pith.science/api/pith-number/2FXKHS3VTCMKX3SQQ6JR6G7G6I/graph.json","events_json":"https://pith.science/api/pith-number/2FXKHS3VTCMKX3SQQ6JR6G7G6I/events.json","paper":"https://pith.science/paper/2FXKHS3V"},"agent_actions":{"view_html":"https://pith.science/pith/2FXKHS3VTCMKX3SQQ6JR6G7G6I","download_json":"https://pith.science/pith/2FXKHS3VTCMKX3SQQ6JR6G7G6I.json","view_paper":"https://pith.science/paper/2FXKHS3V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.17020&json=true","fetch_graph":"https://pith.science/api/pith-number/2FXKHS3VTCMKX3SQQ6JR6G7G6I/graph.json","fetch_events":"https://pith.science/api/pith-number/2FXKHS3VTCMKX3SQQ6JR6G7G6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FXKHS3VTCMKX3SQQ6JR6G7G6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FXKHS3VTCMKX3SQQ6JR6G7G6I/action/storage_attestation","attest_author":"https://pith.science/pith/2FXKHS3VTCMKX3SQQ6JR6G7G6I/action/author_attestation","sign_citation":"https://pith.science/pith/2FXKHS3VTCMKX3SQQ6JR6G7G6I/action/citation_signature","submit_replication":"https://pith.science/pith/2FXKHS3VTCMKX3SQQ6JR6G7G6I/action/replication_record"}},"created_at":"2026-07-05T04:10:30.710902+00:00","updated_at":"2026-07-05T04:10:30.710902+00:00"}