{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LXKEDAV4N664P6AODK7W3BTD56","short_pith_number":"pith:LXKEDAV4","schema_version":"1.0","canonical_sha256":"5dd44182bc6fbdc7f80e1abf6d8663ef97f82c967a7335e2079686aecc85224d","source":{"kind":"arxiv","id":"2009.13592","version":4},"attestation_state":"computed","paper":{"title":"A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baris Can Cam, Emre Akbas, Kemal Oksuz, Sinan Kalkan","submitted_at":"2020-09-28T19:24:51Z","abstract_excerpt":"We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection. aLRP extends the Localisation-Recall-Precision (LRP) performance metric (Oksuz et al., 2018) inspired from how Average Precision (AP) Loss extends precision to a ranking-based loss function for classification (Chen et al., 2020). aLRP has the following distinct advantages: (i) aLRP is the first ranking-based loss function for both classification and localisation tasks. (ii) Thanks to using ranking for both task"},"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":"2009.13592","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-09-28T19:24:51Z","cross_cats_sorted":[],"title_canon_sha256":"d299104c0a27c4da2e19a91b0c4f876267a70d837c3863566bce3425c25628bb","abstract_canon_sha256":"65f932e50fd83f3240dda63982b1c9251f81f8620f10953b741bfa8366ae3afe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:09.028617Z","signature_b64":"LpKkyP0U3dE8yiclBkv+ZEjb/Mk1xIgULf1YSYwTlHf6k+t56Kse32J+IN4Uli0QFEZj09pomgI05qStp0oZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dd44182bc6fbdc7f80e1abf6d8663ef97f82c967a7335e2079686aecc85224d","last_reissued_at":"2026-07-05T02:05:09.028214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:09.028214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baris Can Cam, Emre Akbas, Kemal Oksuz, Sinan Kalkan","submitted_at":"2020-09-28T19:24:51Z","abstract_excerpt":"We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection. aLRP extends the Localisation-Recall-Precision (LRP) performance metric (Oksuz et al., 2018) inspired from how Average Precision (AP) Loss extends precision to a ranking-based loss function for classification (Chen et al., 2020). aLRP has the following distinct advantages: (i) aLRP is the first ranking-based loss function for both classification and localisation tasks. (ii) Thanks to using ranking for both task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13592","kind":"arxiv","version":4},"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/2009.13592/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":"2009.13592","created_at":"2026-07-05T02:05:09.028267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.13592v4","created_at":"2026-07-05T02:05:09.028267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13592","created_at":"2026-07-05T02:05:09.028267+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXKEDAV4N664","created_at":"2026-07-05T02:05:09.028267+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXKEDAV4N664P6AO","created_at":"2026-07-05T02:05:09.028267+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXKEDAV4","created_at":"2026-07-05T02:05:09.028267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05741","citing_title":"Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LXKEDAV4N664P6AODK7W3BTD56","json":"https://pith.science/pith/LXKEDAV4N664P6AODK7W3BTD56.json","graph_json":"https://pith.science/api/pith-number/LXKEDAV4N664P6AODK7W3BTD56/graph.json","events_json":"https://pith.science/api/pith-number/LXKEDAV4N664P6AODK7W3BTD56/events.json","paper":"https://pith.science/paper/LXKEDAV4"},"agent_actions":{"view_html":"https://pith.science/pith/LXKEDAV4N664P6AODK7W3BTD56","download_json":"https://pith.science/pith/LXKEDAV4N664P6AODK7W3BTD56.json","view_paper":"https://pith.science/paper/LXKEDAV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.13592&json=true","fetch_graph":"https://pith.science/api/pith-number/LXKEDAV4N664P6AODK7W3BTD56/graph.json","fetch_events":"https://pith.science/api/pith-number/LXKEDAV4N664P6AODK7W3BTD56/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXKEDAV4N664P6AODK7W3BTD56/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXKEDAV4N664P6AODK7W3BTD56/action/storage_attestation","attest_author":"https://pith.science/pith/LXKEDAV4N664P6AODK7W3BTD56/action/author_attestation","sign_citation":"https://pith.science/pith/LXKEDAV4N664P6AODK7W3BTD56/action/citation_signature","submit_replication":"https://pith.science/pith/LXKEDAV4N664P6AODK7W3BTD56/action/replication_record"}},"created_at":"2026-07-05T02:05:09.028267+00:00","updated_at":"2026-07-05T02:05:09.028267+00:00"}