{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:46CAP3CWWS6RGLVFOQ5DWKYWKS","short_pith_number":"pith:46CAP3CW","schema_version":"1.0","canonical_sha256":"e78407ec56b4bd132ea5743a3b2b1654ab1bf831e208725ccc86a98de522656c","source":{"kind":"arxiv","id":"2107.00057","version":1},"attestation_state":"computed","paper":{"title":"Simple Training Strategies and Model Scaling for Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Barret Zoph, Tsung-Yi Lin, Wei-Chih Hung, Xianzhi Du","submitted_at":"2021-06-30T18:41:47Z","abstract_excerpt":"The speed-accuracy Pareto curve of object detection systems have advanced through a combination of better model architectures, training and inference methods. In this paper, we methodically evaluate a variety of these techniques to understand where most of the improvements in modern detection systems come from. We benchmark these improvements on the vanilla ResNet-FPN backbone with RetinaNet and RCNN detectors. The vanilla detectors are improved by 7.7% in accuracy while being 30% faster in speed. We further provide simple scaling strategies to generate family of models that form two Pareto cu"},"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":"2107.00057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-30T18:41:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c0c168d9938dfa977db3886fcf65c0752cec12c2dfcb94590f70ae062174a6a1","abstract_canon_sha256":"63e8ce5be40096a822b762f2551c1d0cd2ef8514a724398b4f0c69712116fe4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:19.894535Z","signature_b64":"1SPWfvhJD5FzXon9qs56nkCilOyQbweOO/caut+Ry4HDsWbX3U7J2pg9VaK449ya4zXxHciItsv0NEqIoRj8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e78407ec56b4bd132ea5743a3b2b1654ab1bf831e208725ccc86a98de522656c","last_reissued_at":"2026-07-05T02:54:19.894133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:19.894133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple Training Strategies and Model Scaling for Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Barret Zoph, Tsung-Yi Lin, Wei-Chih Hung, Xianzhi Du","submitted_at":"2021-06-30T18:41:47Z","abstract_excerpt":"The speed-accuracy Pareto curve of object detection systems have advanced through a combination of better model architectures, training and inference methods. In this paper, we methodically evaluate a variety of these techniques to understand where most of the improvements in modern detection systems come from. We benchmark these improvements on the vanilla ResNet-FPN backbone with RetinaNet and RCNN detectors. The vanilla detectors are improved by 7.7% in accuracy while being 30% faster in speed. We further provide simple scaling strategies to generate family of models that form two Pareto cu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00057","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/2107.00057/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":"2107.00057","created_at":"2026-07-05T02:54:19.894190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.00057v1","created_at":"2026-07-05T02:54:19.894190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00057","created_at":"2026-07-05T02:54:19.894190+00:00"},{"alias_kind":"pith_short_12","alias_value":"46CAP3CWWS6R","created_at":"2026-07-05T02:54:19.894190+00:00"},{"alias_kind":"pith_short_16","alias_value":"46CAP3CWWS6RGLVF","created_at":"2026-07-05T02:54:19.894190+00:00"},{"alias_kind":"pith_short_8","alias_value":"46CAP3CW","created_at":"2026-07-05T02:54:19.894190+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/46CAP3CWWS6RGLVFOQ5DWKYWKS","json":"https://pith.science/pith/46CAP3CWWS6RGLVFOQ5DWKYWKS.json","graph_json":"https://pith.science/api/pith-number/46CAP3CWWS6RGLVFOQ5DWKYWKS/graph.json","events_json":"https://pith.science/api/pith-number/46CAP3CWWS6RGLVFOQ5DWKYWKS/events.json","paper":"https://pith.science/paper/46CAP3CW"},"agent_actions":{"view_html":"https://pith.science/pith/46CAP3CWWS6RGLVFOQ5DWKYWKS","download_json":"https://pith.science/pith/46CAP3CWWS6RGLVFOQ5DWKYWKS.json","view_paper":"https://pith.science/paper/46CAP3CW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.00057&json=true","fetch_graph":"https://pith.science/api/pith-number/46CAP3CWWS6RGLVFOQ5DWKYWKS/graph.json","fetch_events":"https://pith.science/api/pith-number/46CAP3CWWS6RGLVFOQ5DWKYWKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46CAP3CWWS6RGLVFOQ5DWKYWKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46CAP3CWWS6RGLVFOQ5DWKYWKS/action/storage_attestation","attest_author":"https://pith.science/pith/46CAP3CWWS6RGLVFOQ5DWKYWKS/action/author_attestation","sign_citation":"https://pith.science/pith/46CAP3CWWS6RGLVFOQ5DWKYWKS/action/citation_signature","submit_replication":"https://pith.science/pith/46CAP3CWWS6RGLVFOQ5DWKYWKS/action/replication_record"}},"created_at":"2026-07-05T02:54:19.894190+00:00","updated_at":"2026-07-05T02:54:19.894190+00:00"}