{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NR3NTRYEN2PVEZY4B6KDRFHEP6","short_pith_number":"pith:NR3NTRYE","schema_version":"1.0","canonical_sha256":"6c76d9c7046e9f52671c0f943894e47f87f145ad0da2703458d048f393591d51","source":{"kind":"arxiv","id":"2312.06645","version":1},"attestation_state":"computed","paper":{"title":"Beyond Classification: Definition and Density-based Estimation of Calibration in Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksei Tiulpin, Matthew B. Blaschko, Teodora Popordanoska","submitted_at":"2023-12-11T18:57:05Z","abstract_excerpt":"Despite their impressive predictive performance in various computer vision tasks, deep neural networks (DNNs) tend to make overly confident predictions, which hinders their widespread use in safety-critical applications. While there have been recent attempts to calibrate DNNs, most of these efforts have primarily been focused on classification tasks, thus neglecting DNN-based object detectors. Although several recent works addressed calibration for object detection and proposed differentiable penalties, none of them are consistent estimators of established concepts in calibration. In this work"},"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":"2312.06645","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T18:57:05Z","cross_cats_sorted":[],"title_canon_sha256":"45a8e90059d8e0947080e2326805cc89ee6a1d67c36723034c26685167e557f3","abstract_canon_sha256":"7f1aba0e6c71d18c2ac08c4ebe095de72c4936b56acfa5092d96964942f2d343"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:48.281829Z","signature_b64":"ntkpgmOX/fHRKk7A4zY1tD/+tIEIMGA8+Oy55aLFVZG0MWNF/m/rbZ4z52dwxz3+hxYkXszVqQXmtHfei5UjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c76d9c7046e9f52671c0f943894e47f87f145ad0da2703458d048f393591d51","last_reissued_at":"2026-07-05T07:22:48.281433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:48.281433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Classification: Definition and Density-based Estimation of Calibration in Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksei Tiulpin, Matthew B. Blaschko, Teodora Popordanoska","submitted_at":"2023-12-11T18:57:05Z","abstract_excerpt":"Despite their impressive predictive performance in various computer vision tasks, deep neural networks (DNNs) tend to make overly confident predictions, which hinders their widespread use in safety-critical applications. While there have been recent attempts to calibrate DNNs, most of these efforts have primarily been focused on classification tasks, thus neglecting DNN-based object detectors. Although several recent works addressed calibration for object detection and proposed differentiable penalties, none of them are consistent estimators of established concepts in calibration. In this work"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06645","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/2312.06645/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":"2312.06645","created_at":"2026-07-05T07:22:48.281490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06645v1","created_at":"2026-07-05T07:22:48.281490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06645","created_at":"2026-07-05T07:22:48.281490+00:00"},{"alias_kind":"pith_short_12","alias_value":"NR3NTRYEN2PV","created_at":"2026-07-05T07:22:48.281490+00:00"},{"alias_kind":"pith_short_16","alias_value":"NR3NTRYEN2PVEZY4","created_at":"2026-07-05T07:22:48.281490+00:00"},{"alias_kind":"pith_short_8","alias_value":"NR3NTRYE","created_at":"2026-07-05T07:22:48.281490+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/NR3NTRYEN2PVEZY4B6KDRFHEP6","json":"https://pith.science/pith/NR3NTRYEN2PVEZY4B6KDRFHEP6.json","graph_json":"https://pith.science/api/pith-number/NR3NTRYEN2PVEZY4B6KDRFHEP6/graph.json","events_json":"https://pith.science/api/pith-number/NR3NTRYEN2PVEZY4B6KDRFHEP6/events.json","paper":"https://pith.science/paper/NR3NTRYE"},"agent_actions":{"view_html":"https://pith.science/pith/NR3NTRYEN2PVEZY4B6KDRFHEP6","download_json":"https://pith.science/pith/NR3NTRYEN2PVEZY4B6KDRFHEP6.json","view_paper":"https://pith.science/paper/NR3NTRYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06645&json=true","fetch_graph":"https://pith.science/api/pith-number/NR3NTRYEN2PVEZY4B6KDRFHEP6/graph.json","fetch_events":"https://pith.science/api/pith-number/NR3NTRYEN2PVEZY4B6KDRFHEP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NR3NTRYEN2PVEZY4B6KDRFHEP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NR3NTRYEN2PVEZY4B6KDRFHEP6/action/storage_attestation","attest_author":"https://pith.science/pith/NR3NTRYEN2PVEZY4B6KDRFHEP6/action/author_attestation","sign_citation":"https://pith.science/pith/NR3NTRYEN2PVEZY4B6KDRFHEP6/action/citation_signature","submit_replication":"https://pith.science/pith/NR3NTRYEN2PVEZY4B6KDRFHEP6/action/replication_record"}},"created_at":"2026-07-05T07:22:48.281490+00:00","updated_at":"2026-07-05T07:22:48.281490+00:00"}