{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FDJMMTQHJJ3SC6SN75K4NJCSKU","short_pith_number":"pith:FDJMMTQH","schema_version":"1.0","canonical_sha256":"28d2c64e074a77217a4dff55c6a452550e53454e96eade1fe48e050d2da49396","source":{"kind":"arxiv","id":"2106.13731","version":2},"attestation_state":"computed","paper":{"title":"Ranger21: a synergistic deep learning optimizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Less Wright, Nestor Demeure","submitted_at":"2021-06-25T16:07:59Z","abstract_excerpt":"As optimizers are critical to the performances of neural networks, every year a large number of papers innovating on the subject are published. However, while most of these publications provide incremental improvements to existing algorithms, they tend to be presented as new optimizers rather than composable algorithms. Thus, many worthwhile improvements are rarely seen out of their initial publication. Taking advantage of this untapped potential, we introduce Ranger21, a new optimizer which combines AdamW with eight components, carefully selected after reviewing and testing ideas from the lit"},"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":"2106.13731","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-25T16:07:59Z","cross_cats_sorted":[],"title_canon_sha256":"3988a3df96c3156d8a281251d369448184a5c8764077e40cb2841fb3fc99f8d1","abstract_canon_sha256":"676baa3bb87a64bff6c949b4cfb917dbbd3f89774c677a0ca9bac284aad9d4a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:50.444116Z","signature_b64":"LlMpX6B51RGcsr/kD2ww4wq85bRsqE652vhMvGTDSQVrJ+LIRrdw+gOVtbfFu18q6l0dj5kBf4QX8TXfFarZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28d2c64e074a77217a4dff55c6a452550e53454e96eade1fe48e050d2da49396","last_reissued_at":"2026-07-05T03:03:50.443695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:50.443695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ranger21: a synergistic deep learning optimizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Less Wright, Nestor Demeure","submitted_at":"2021-06-25T16:07:59Z","abstract_excerpt":"As optimizers are critical to the performances of neural networks, every year a large number of papers innovating on the subject are published. However, while most of these publications provide incremental improvements to existing algorithms, they tend to be presented as new optimizers rather than composable algorithms. Thus, many worthwhile improvements are rarely seen out of their initial publication. Taking advantage of this untapped potential, we introduce Ranger21, a new optimizer which combines AdamW with eight components, carefully selected after reviewing and testing ideas from the lit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13731","kind":"arxiv","version":2},"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/2106.13731/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":"2106.13731","created_at":"2026-07-05T03:03:50.443751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13731v2","created_at":"2026-07-05T03:03:50.443751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13731","created_at":"2026-07-05T03:03:50.443751+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDJMMTQHJJ3S","created_at":"2026-07-05T03:03:50.443751+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDJMMTQHJJ3SC6SN","created_at":"2026-07-05T03:03:50.443751+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDJMMTQH","created_at":"2026-07-05T03:03:50.443751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20765","citing_title":"Dataset-Aware Cold-Start Active Learning for Annotation-Efficient 3D Medical Image Segmentation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2601.07447","citing_title":"PanoSAMic: Panoramic Image Segmentation from SAM Feature Encoding and Dual View Fusion","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDJMMTQHJJ3SC6SN75K4NJCSKU","json":"https://pith.science/pith/FDJMMTQHJJ3SC6SN75K4NJCSKU.json","graph_json":"https://pith.science/api/pith-number/FDJMMTQHJJ3SC6SN75K4NJCSKU/graph.json","events_json":"https://pith.science/api/pith-number/FDJMMTQHJJ3SC6SN75K4NJCSKU/events.json","paper":"https://pith.science/paper/FDJMMTQH"},"agent_actions":{"view_html":"https://pith.science/pith/FDJMMTQHJJ3SC6SN75K4NJCSKU","download_json":"https://pith.science/pith/FDJMMTQHJJ3SC6SN75K4NJCSKU.json","view_paper":"https://pith.science/paper/FDJMMTQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13731&json=true","fetch_graph":"https://pith.science/api/pith-number/FDJMMTQHJJ3SC6SN75K4NJCSKU/graph.json","fetch_events":"https://pith.science/api/pith-number/FDJMMTQHJJ3SC6SN75K4NJCSKU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDJMMTQHJJ3SC6SN75K4NJCSKU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDJMMTQHJJ3SC6SN75K4NJCSKU/action/storage_attestation","attest_author":"https://pith.science/pith/FDJMMTQHJJ3SC6SN75K4NJCSKU/action/author_attestation","sign_citation":"https://pith.science/pith/FDJMMTQHJJ3SC6SN75K4NJCSKU/action/citation_signature","submit_replication":"https://pith.science/pith/FDJMMTQHJJ3SC6SN75K4NJCSKU/action/replication_record"}},"created_at":"2026-07-05T03:03:50.443751+00:00","updated_at":"2026-07-05T03:03:50.443751+00:00"}