{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YNTO5K2B7YQMGNN362AWSPJTCW","short_pith_number":"pith:YNTO5K2B","schema_version":"1.0","canonical_sha256":"c366eeab41fe20c335bbf681693d33159b00efed4ceacba914927a44f356d303","source":{"kind":"arxiv","id":"2111.13336","version":5},"attestation_state":"computed","paper":{"title":"MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Li, Ming Lin, Rong Jin, Xiuyu Sun, Zhenhong Sun, Zhiyu Tan","submitted_at":"2021-11-26T07:18:52Z","abstract_excerpt":"In object detection, the detection backbone consumes more than half of the overall inference cost. Recent researches attempt to reduce this cost by optimizing the backbone architecture with the help of Neural Architecture Search (NAS). However, existing NAS methods for object detection require hundreds to thousands of GPU hours of searching, making them impractical in fast-paced research and development. In this work, we propose a novel zero-shot NAS method to address this issue. The proposed method, named MAE-DET, automatically designs efficient detection backbones via the Maximum Entropy Pri"},"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":"2111.13336","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-26T07:18:52Z","cross_cats_sorted":[],"title_canon_sha256":"4a5df7df1ad490130c0f21983c3317308f643f3fbca51156fc22f6b4b066093a","abstract_canon_sha256":"d995ccb915481aa21ced35e890c0de09e27b262e82af5f3135ae233420bdf452"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:58.032288Z","signature_b64":"jxKkCpFz6dJGQs1/t7UaCLw3uqZ8RzR/SwxZNzRScFo+MCUw8zcZSlUn4qbEXbw/ES9aAuZtQqZX02Cf6CUFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c366eeab41fe20c335bbf681693d33159b00efed4ceacba914927a44f356d303","last_reissued_at":"2026-07-05T04:31:58.031810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:58.031810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Li, Ming Lin, Rong Jin, Xiuyu Sun, Zhenhong Sun, Zhiyu Tan","submitted_at":"2021-11-26T07:18:52Z","abstract_excerpt":"In object detection, the detection backbone consumes more than half of the overall inference cost. Recent researches attempt to reduce this cost by optimizing the backbone architecture with the help of Neural Architecture Search (NAS). However, existing NAS methods for object detection require hundreds to thousands of GPU hours of searching, making them impractical in fast-paced research and development. In this work, we propose a novel zero-shot NAS method to address this issue. The proposed method, named MAE-DET, automatically designs efficient detection backbones via the Maximum Entropy Pri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13336","kind":"arxiv","version":5},"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/2111.13336/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":"2111.13336","created_at":"2026-07-05T04:31:58.031862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13336v5","created_at":"2026-07-05T04:31:58.031862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13336","created_at":"2026-07-05T04:31:58.031862+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNTO5K2B7YQM","created_at":"2026-07-05T04:31:58.031862+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNTO5K2B7YQMGNN3","created_at":"2026-07-05T04:31:58.031862+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNTO5K2B","created_at":"2026-07-05T04:31:58.031862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.14235","citing_title":"Spiking Neural Network Architecture Search: A Survey","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2511.06443","citing_title":"How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YNTO5K2B7YQMGNN362AWSPJTCW","json":"https://pith.science/pith/YNTO5K2B7YQMGNN362AWSPJTCW.json","graph_json":"https://pith.science/api/pith-number/YNTO5K2B7YQMGNN362AWSPJTCW/graph.json","events_json":"https://pith.science/api/pith-number/YNTO5K2B7YQMGNN362AWSPJTCW/events.json","paper":"https://pith.science/paper/YNTO5K2B"},"agent_actions":{"view_html":"https://pith.science/pith/YNTO5K2B7YQMGNN362AWSPJTCW","download_json":"https://pith.science/pith/YNTO5K2B7YQMGNN362AWSPJTCW.json","view_paper":"https://pith.science/paper/YNTO5K2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13336&json=true","fetch_graph":"https://pith.science/api/pith-number/YNTO5K2B7YQMGNN362AWSPJTCW/graph.json","fetch_events":"https://pith.science/api/pith-number/YNTO5K2B7YQMGNN362AWSPJTCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNTO5K2B7YQMGNN362AWSPJTCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNTO5K2B7YQMGNN362AWSPJTCW/action/storage_attestation","attest_author":"https://pith.science/pith/YNTO5K2B7YQMGNN362AWSPJTCW/action/author_attestation","sign_citation":"https://pith.science/pith/YNTO5K2B7YQMGNN362AWSPJTCW/action/citation_signature","submit_replication":"https://pith.science/pith/YNTO5K2B7YQMGNN362AWSPJTCW/action/replication_record"}},"created_at":"2026-07-05T04:31:58.031862+00:00","updated_at":"2026-07-05T04:31:58.031862+00:00"}