{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EAQHZPR3OWIB7TOAS5XYNBHC7Y","short_pith_number":"pith:EAQHZPR3","schema_version":"1.0","canonical_sha256":"20207cbe3b75901fcdc0976f8684e2fe133a6617304dc149bb343d73f49c31cd","source":{"kind":"arxiv","id":"1906.09756","version":1},"attestation_state":"computed","paper":{"title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Nuno Vasconcelos, Zhaowei Cai","submitted_at":"2019-06-24T07:22:28Z","abstract_excerpt":"In object detection, the intersection over union (IoU) threshold is frequently used to define positives/negatives. The threshold used to train a detector defines its \\textit{quality}. While the commonly used threshold of 0.5 leads to noisy (low-quality) detections, detection performance frequently degrades for larger thresholds. This paradox of high-quality detection has two causes: 1) overfitting, due to vanishing positive samples for large thresholds, and 2) inference-time quality mismatch between detector and test hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, c"},"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":"1906.09756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-24T07:22:28Z","cross_cats_sorted":[],"title_canon_sha256":"a78cca30d90ffaf8cabdbdd62a0c25e1b9368fcef2d4f4d608e1ab77b0ccf5d9","abstract_canon_sha256":"f2896db589f7fc2beb3c67b7b5cabb18c5b55c692f975e4c9aa27e3228a628f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:36.831267Z","signature_b64":"uYhwQIo/pY/4PtQE9ABX+C76Xr3gkobEzsqXXUs/FCDCYKoOQBSUtwy8fCmDe4Ff9iVfV9+iw78MrZoSP6INCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20207cbe3b75901fcdc0976f8684e2fe133a6617304dc149bb343d73f49c31cd","last_reissued_at":"2026-05-17T23:42:36.830652Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:36.830652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Nuno Vasconcelos, Zhaowei Cai","submitted_at":"2019-06-24T07:22:28Z","abstract_excerpt":"In object detection, the intersection over union (IoU) threshold is frequently used to define positives/negatives. The threshold used to train a detector defines its \\textit{quality}. While the commonly used threshold of 0.5 leads to noisy (low-quality) detections, detection performance frequently degrades for larger thresholds. This paradox of high-quality detection has two causes: 1) overfitting, due to vanishing positive samples for large thresholds, and 2) inference-time quality mismatch between detector and test hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09756","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":""},"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":"1906.09756","created_at":"2026-05-17T23:42:36.830764+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.09756v1","created_at":"2026-05-17T23:42:36.830764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09756","created_at":"2026-05-17T23:42:36.830764+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAQHZPR3OWIB","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAQHZPR3OWIB7TOA","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAQHZPR3","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15263","citing_title":"gen2seg: Generative Models Enable Generalizable Instance Segmentation","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EAQHZPR3OWIB7TOAS5XYNBHC7Y","json":"https://pith.science/pith/EAQHZPR3OWIB7TOAS5XYNBHC7Y.json","graph_json":"https://pith.science/api/pith-number/EAQHZPR3OWIB7TOAS5XYNBHC7Y/graph.json","events_json":"https://pith.science/api/pith-number/EAQHZPR3OWIB7TOAS5XYNBHC7Y/events.json","paper":"https://pith.science/paper/EAQHZPR3"},"agent_actions":{"view_html":"https://pith.science/pith/EAQHZPR3OWIB7TOAS5XYNBHC7Y","download_json":"https://pith.science/pith/EAQHZPR3OWIB7TOAS5XYNBHC7Y.json","view_paper":"https://pith.science/paper/EAQHZPR3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.09756&json=true","fetch_graph":"https://pith.science/api/pith-number/EAQHZPR3OWIB7TOAS5XYNBHC7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/EAQHZPR3OWIB7TOAS5XYNBHC7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAQHZPR3OWIB7TOAS5XYNBHC7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAQHZPR3OWIB7TOAS5XYNBHC7Y/action/storage_attestation","attest_author":"https://pith.science/pith/EAQHZPR3OWIB7TOAS5XYNBHC7Y/action/author_attestation","sign_citation":"https://pith.science/pith/EAQHZPR3OWIB7TOAS5XYNBHC7Y/action/citation_signature","submit_replication":"https://pith.science/pith/EAQHZPR3OWIB7TOAS5XYNBHC7Y/action/replication_record"}},"created_at":"2026-05-17T23:42:36.830764+00:00","updated_at":"2026-05-17T23:42:36.830764+00:00"}