{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CRUEX253DTADFJA3ULITKQGSQ6","short_pith_number":"pith:CRUEX253","schema_version":"1.0","canonical_sha256":"14684bebbb1cc032a41ba2d13540d287a8b52922b00c6e68bd34960af0807982","source":{"kind":"arxiv","id":"2003.11818","version":1},"attestation_state":"computed","paper":{"title":"Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chao Zhang, Han Wu, Jianyuan Guo, Kai Han, Xinghao Chen, Yunhe Wang, Zhaohui Yang","submitted_at":"2020-03-26T10:20:52Z","abstract_excerpt":"Neural Architecture Search (NAS) has achieved great success in image classification task. Some recent works have managed to explore the automatic design of efficient backbone or feature fusion layer for object detection. However, these methods focus on searching only one certain component of object detector while leaving others manually designed. We identify the inconsistency between searched component and manually designed ones would withhold the detector of stronger performance. To this end, we propose a hierarchical trinity search framework to simultaneously discover efficient architectures"},"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":"2003.11818","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-26T10:20:52Z","cross_cats_sorted":[],"title_canon_sha256":"682df140ce36884952d9a59de98d36bb25ce46837dcd7dea2b4f64e55224a8d9","abstract_canon_sha256":"67cb5d24a027c161458b37f180fbcc44f90f2ba54922b6d56f0d0666273b6a1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:47.807303Z","signature_b64":"iaEKpxTUOc46X9cK+YEQx9YjhdiwRgsyt/huXBfpqJLNFNf+LMNxZ5AtZT44sq5ceiAvnXFrZ9v+i9Qrr4b+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14684bebbb1cc032a41ba2d13540d287a8b52922b00c6e68bd34960af0807982","last_reissued_at":"2026-07-05T00:50:47.806876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:47.806876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chao Zhang, Han Wu, Jianyuan Guo, Kai Han, Xinghao Chen, Yunhe Wang, Zhaohui Yang","submitted_at":"2020-03-26T10:20:52Z","abstract_excerpt":"Neural Architecture Search (NAS) has achieved great success in image classification task. Some recent works have managed to explore the automatic design of efficient backbone or feature fusion layer for object detection. However, these methods focus on searching only one certain component of object detector while leaving others manually designed. We identify the inconsistency between searched component and manually designed ones would withhold the detector of stronger performance. To this end, we propose a hierarchical trinity search framework to simultaneously discover efficient architectures"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.11818","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/2003.11818/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":"2003.11818","created_at":"2026-07-05T00:50:47.806934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.11818v1","created_at":"2026-07-05T00:50:47.806934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.11818","created_at":"2026-07-05T00:50:47.806934+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRUEX253DTAD","created_at":"2026-07-05T00:50:47.806934+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRUEX253DTADFJA3","created_at":"2026-07-05T00:50:47.806934+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRUEX253","created_at":"2026-07-05T00:50:47.806934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08339","citing_title":"SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learning","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CRUEX253DTADFJA3ULITKQGSQ6","json":"https://pith.science/pith/CRUEX253DTADFJA3ULITKQGSQ6.json","graph_json":"https://pith.science/api/pith-number/CRUEX253DTADFJA3ULITKQGSQ6/graph.json","events_json":"https://pith.science/api/pith-number/CRUEX253DTADFJA3ULITKQGSQ6/events.json","paper":"https://pith.science/paper/CRUEX253"},"agent_actions":{"view_html":"https://pith.science/pith/CRUEX253DTADFJA3ULITKQGSQ6","download_json":"https://pith.science/pith/CRUEX253DTADFJA3ULITKQGSQ6.json","view_paper":"https://pith.science/paper/CRUEX253","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.11818&json=true","fetch_graph":"https://pith.science/api/pith-number/CRUEX253DTADFJA3ULITKQGSQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/CRUEX253DTADFJA3ULITKQGSQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRUEX253DTADFJA3ULITKQGSQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRUEX253DTADFJA3ULITKQGSQ6/action/storage_attestation","attest_author":"https://pith.science/pith/CRUEX253DTADFJA3ULITKQGSQ6/action/author_attestation","sign_citation":"https://pith.science/pith/CRUEX253DTADFJA3ULITKQGSQ6/action/citation_signature","submit_replication":"https://pith.science/pith/CRUEX253DTADFJA3ULITKQGSQ6/action/replication_record"}},"created_at":"2026-07-05T00:50:47.806934+00:00","updated_at":"2026-07-05T00:50:47.806934+00:00"}