{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PSOC57ZBOVSJSL556CC7LDO4FR","short_pith_number":"pith:PSOC57ZB","schema_version":"1.0","canonical_sha256":"7c9c2eff217564992fbdf085f58ddc2c7a19e7a5c8552d927b673a0cda1d713c","source":{"kind":"arxiv","id":"2403.13803","version":1},"attestation_state":"computed","paper":{"title":"Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jifeng Dai, Liang Zheng, Wenhai Wang, Yang Yang, Zhe Chen","submitted_at":"2024-03-20T17:59:16Z","abstract_excerpt":"Bounding boxes uniquely characterize object detection, where a good detector gives accurate bounding boxes of categories of interest. However, in the real-world where test ground truths are not provided, it is non-trivial to find out whether bounding boxes are accurate, thus preventing us from assessing the detector generalization ability. In this work, we find under feature map dropout, good detectors tend to output bounding boxes whose locations do not change much, while bounding boxes of poor detectors will undergo noticeable position changes. We compute the box stability score (BoS score) "},"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":"2403.13803","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T17:59:16Z","cross_cats_sorted":[],"title_canon_sha256":"71b74a92840e0f265d9e451c75f61e2714060ac38a2ab0213be8a353b595d188","abstract_canon_sha256":"f222e80f13a1b0afec47c973f72a0f94c34c595ff0d60a97b9345e47699524cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:41.455662Z","signature_b64":"R4DkuypzjMwMu6WO96MgcTj2pVKbPSFJJJNaNiZbMHLzCuB4s5RXLG1XO+jlYfwYSRuUp6cRHz1qnKmQy1OnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c9c2eff217564992fbdf085f58ddc2c7a19e7a5c8552d927b673a0cda1d713c","last_reissued_at":"2026-07-05T07:58:41.455261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:41.455261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jifeng Dai, Liang Zheng, Wenhai Wang, Yang Yang, Zhe Chen","submitted_at":"2024-03-20T17:59:16Z","abstract_excerpt":"Bounding boxes uniquely characterize object detection, where a good detector gives accurate bounding boxes of categories of interest. However, in the real-world where test ground truths are not provided, it is non-trivial to find out whether bounding boxes are accurate, thus preventing us from assessing the detector generalization ability. In this work, we find under feature map dropout, good detectors tend to output bounding boxes whose locations do not change much, while bounding boxes of poor detectors will undergo noticeable position changes. We compute the box stability score (BoS score) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13803","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/2403.13803/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":"2403.13803","created_at":"2026-07-05T07:58:41.455312+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13803v1","created_at":"2026-07-05T07:58:41.455312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13803","created_at":"2026-07-05T07:58:41.455312+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSOC57ZBOVSJ","created_at":"2026-07-05T07:58:41.455312+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSOC57ZBOVSJSL55","created_at":"2026-07-05T07:58:41.455312+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSOC57ZB","created_at":"2026-07-05T07:58:41.455312+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14725","citing_title":"Evaluating and Advancing Multimodal Large Language Models in Perception Ability Lens","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PSOC57ZBOVSJSL556CC7LDO4FR","json":"https://pith.science/pith/PSOC57ZBOVSJSL556CC7LDO4FR.json","graph_json":"https://pith.science/api/pith-number/PSOC57ZBOVSJSL556CC7LDO4FR/graph.json","events_json":"https://pith.science/api/pith-number/PSOC57ZBOVSJSL556CC7LDO4FR/events.json","paper":"https://pith.science/paper/PSOC57ZB"},"agent_actions":{"view_html":"https://pith.science/pith/PSOC57ZBOVSJSL556CC7LDO4FR","download_json":"https://pith.science/pith/PSOC57ZBOVSJSL556CC7LDO4FR.json","view_paper":"https://pith.science/paper/PSOC57ZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13803&json=true","fetch_graph":"https://pith.science/api/pith-number/PSOC57ZBOVSJSL556CC7LDO4FR/graph.json","fetch_events":"https://pith.science/api/pith-number/PSOC57ZBOVSJSL556CC7LDO4FR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSOC57ZBOVSJSL556CC7LDO4FR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSOC57ZBOVSJSL556CC7LDO4FR/action/storage_attestation","attest_author":"https://pith.science/pith/PSOC57ZBOVSJSL556CC7LDO4FR/action/author_attestation","sign_citation":"https://pith.science/pith/PSOC57ZBOVSJSL556CC7LDO4FR/action/citation_signature","submit_replication":"https://pith.science/pith/PSOC57ZBOVSJSL556CC7LDO4FR/action/replication_record"}},"created_at":"2026-07-05T07:58:41.455312+00:00","updated_at":"2026-07-05T07:58:41.455312+00:00"}