{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VDD555WUBIM6V7SEJDZMF7PBSC","short_pith_number":"pith:VDD555WU","schema_version":"1.0","canonical_sha256":"a8c7def6d40a19eafe4448f2c2fde19095493d6693e7ca989d766122eeb56fac","source":{"kind":"arxiv","id":"2401.10525","version":1},"attestation_state":"computed","paper":{"title":"Focaler-IoU: More Focused Intersection over Union Loss","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Shuaijie Zhang","submitted_at":"2024-01-19T07:01:07Z","abstract_excerpt":"Bounding box regression plays a crucial role in the field of object detection, and the positioning accuracy of object detection largely depends on the loss function of bounding box regression. Existing researchs improve regression performance by utilizing the geometric relationship between bounding boxes, while ignoring the impact of difficult and easy sample distribution on bounding box regression. In this article, we analyzed the impact of difficult and easy sample distribution on regression results, and then proposed Focaler-IoU, which can improve detector performance in different detection"},"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":"2401.10525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T07:01:07Z","cross_cats_sorted":[],"title_canon_sha256":"bd15a8e44706f4a12487be05ee11ae54bedeb0097f1fb90debe09428d78f44fe","abstract_canon_sha256":"76c7b645e9996d1f478c9bfbb9fccee1a65d050ae2df25d4a5988bf3d9d9ab66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:27.660207Z","signature_b64":"YYJ3oAUVU0rTXPwuzjAlR2Z53nPvhUeW4V6Cb+6f3HK4tw0q5bV8YfJ364lKaUVD7J9BoF7I9p/F7mEoK/IFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8c7def6d40a19eafe4448f2c2fde19095493d6693e7ca989d766122eeb56fac","last_reissued_at":"2026-07-05T07:35:27.659732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:27.659732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Focaler-IoU: More Focused Intersection over Union Loss","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Shuaijie Zhang","submitted_at":"2024-01-19T07:01:07Z","abstract_excerpt":"Bounding box regression plays a crucial role in the field of object detection, and the positioning accuracy of object detection largely depends on the loss function of bounding box regression. Existing researchs improve regression performance by utilizing the geometric relationship between bounding boxes, while ignoring the impact of difficult and easy sample distribution on bounding box regression. In this article, we analyzed the impact of difficult and easy sample distribution on regression results, and then proposed Focaler-IoU, which can improve detector performance in different detection"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10525","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/2401.10525/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":"2401.10525","created_at":"2026-07-05T07:35:27.659784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10525v1","created_at":"2026-07-05T07:35:27.659784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10525","created_at":"2026-07-05T07:35:27.659784+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDD555WUBIM6","created_at":"2026-07-05T07:35:27.659784+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDD555WUBIM6V7SE","created_at":"2026-07-05T07:35:27.659784+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDD555WU","created_at":"2026-07-05T07:35:27.659784+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14343","citing_title":"Inter-Class Relational Loss for Small Object Detection: A Case Study on License Plates","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VDD555WUBIM6V7SEJDZMF7PBSC","json":"https://pith.science/pith/VDD555WUBIM6V7SEJDZMF7PBSC.json","graph_json":"https://pith.science/api/pith-number/VDD555WUBIM6V7SEJDZMF7PBSC/graph.json","events_json":"https://pith.science/api/pith-number/VDD555WUBIM6V7SEJDZMF7PBSC/events.json","paper":"https://pith.science/paper/VDD555WU"},"agent_actions":{"view_html":"https://pith.science/pith/VDD555WUBIM6V7SEJDZMF7PBSC","download_json":"https://pith.science/pith/VDD555WUBIM6V7SEJDZMF7PBSC.json","view_paper":"https://pith.science/paper/VDD555WU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10525&json=true","fetch_graph":"https://pith.science/api/pith-number/VDD555WUBIM6V7SEJDZMF7PBSC/graph.json","fetch_events":"https://pith.science/api/pith-number/VDD555WUBIM6V7SEJDZMF7PBSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDD555WUBIM6V7SEJDZMF7PBSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDD555WUBIM6V7SEJDZMF7PBSC/action/storage_attestation","attest_author":"https://pith.science/pith/VDD555WUBIM6V7SEJDZMF7PBSC/action/author_attestation","sign_citation":"https://pith.science/pith/VDD555WUBIM6V7SEJDZMF7PBSC/action/citation_signature","submit_replication":"https://pith.science/pith/VDD555WUBIM6V7SEJDZMF7PBSC/action/replication_record"}},"created_at":"2026-07-05T07:35:27.659784+00:00","updated_at":"2026-07-05T07:35:27.659784+00:00"}