{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LQJK7RHEOHK5TUXW3OGMMB2XMG","short_pith_number":"pith:LQJK7RHE","schema_version":"1.0","canonical_sha256":"5c12afc4e471d5d9d2f6db8cc60757618089750fd8954b5d3d14dee462657f9f","source":{"kind":"arxiv","id":"2205.10247","version":1},"attestation_state":"computed","paper":{"title":"SADAM: Stochastic Adam, A Stochastic Operator for First-Order Gradient-based Optimizer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Wei Zhang, Yu Bao","submitted_at":"2022-05-20T15:20:19Z","abstract_excerpt":"In this work, to efficiently help escape the stationary and saddle points, we propose, analyze, and generalize a stochastic strategy performed as an operator for a first-order gradient descent algorithm in order to increase the target accuracy and reduce time consumption. Unlike existing algorithms, the proposed stochastic the strategy does not require any batches and sampling techniques, enabling efficient implementation and maintaining the initial first-order optimizer's convergence rate, but provides an incomparable improvement of target accuracy when optimizing the target functions. In sho"},"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":"2205.10247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-20T15:20:19Z","cross_cats_sorted":[],"title_canon_sha256":"94867dd227a6c4dc7ed2f52071744fa9eea7ab487c4c558f90355bb2749c2ca4","abstract_canon_sha256":"20ae351b8e3a324a39feabaae88ac3771c8c2d718a8dd11ed33396f24b703a0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:05.392567Z","signature_b64":"N8IlEI5E0wG7UALJGr3y0bY41/yfPg402ijylBRALXvhf7mpT4jni/OrmCEVfRgeqjP75kom2Ok2datYP0WBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c12afc4e471d5d9d2f6db8cc60757618089750fd8954b5d3d14dee462657f9f","last_reissued_at":"2026-07-05T04:25:05.391967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:05.391967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SADAM: Stochastic Adam, A Stochastic Operator for First-Order Gradient-based Optimizer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Wei Zhang, Yu Bao","submitted_at":"2022-05-20T15:20:19Z","abstract_excerpt":"In this work, to efficiently help escape the stationary and saddle points, we propose, analyze, and generalize a stochastic strategy performed as an operator for a first-order gradient descent algorithm in order to increase the target accuracy and reduce time consumption. Unlike existing algorithms, the proposed stochastic the strategy does not require any batches and sampling techniques, enabling efficient implementation and maintaining the initial first-order optimizer's convergence rate, but provides an incomparable improvement of target accuracy when optimizing the target functions. In sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10247","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/2205.10247/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":"2205.10247","created_at":"2026-07-05T04:25:05.392057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.10247v1","created_at":"2026-07-05T04:25:05.392057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10247","created_at":"2026-07-05T04:25:05.392057+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQJK7RHEOHK5","created_at":"2026-07-05T04:25:05.392057+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQJK7RHEOHK5TUXW","created_at":"2026-07-05T04:25:05.392057+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQJK7RHE","created_at":"2026-07-05T04:25:05.392057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11748","citing_title":"HOME-3: High-Order Momentum Estimator with Third-Power Gradient for Convex and Smooth Nonconvex Optimization","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQJK7RHEOHK5TUXW3OGMMB2XMG","json":"https://pith.science/pith/LQJK7RHEOHK5TUXW3OGMMB2XMG.json","graph_json":"https://pith.science/api/pith-number/LQJK7RHEOHK5TUXW3OGMMB2XMG/graph.json","events_json":"https://pith.science/api/pith-number/LQJK7RHEOHK5TUXW3OGMMB2XMG/events.json","paper":"https://pith.science/paper/LQJK7RHE"},"agent_actions":{"view_html":"https://pith.science/pith/LQJK7RHEOHK5TUXW3OGMMB2XMG","download_json":"https://pith.science/pith/LQJK7RHEOHK5TUXW3OGMMB2XMG.json","view_paper":"https://pith.science/paper/LQJK7RHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.10247&json=true","fetch_graph":"https://pith.science/api/pith-number/LQJK7RHEOHK5TUXW3OGMMB2XMG/graph.json","fetch_events":"https://pith.science/api/pith-number/LQJK7RHEOHK5TUXW3OGMMB2XMG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQJK7RHEOHK5TUXW3OGMMB2XMG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQJK7RHEOHK5TUXW3OGMMB2XMG/action/storage_attestation","attest_author":"https://pith.science/pith/LQJK7RHEOHK5TUXW3OGMMB2XMG/action/author_attestation","sign_citation":"https://pith.science/pith/LQJK7RHEOHK5TUXW3OGMMB2XMG/action/citation_signature","submit_replication":"https://pith.science/pith/LQJK7RHEOHK5TUXW3OGMMB2XMG/action/replication_record"}},"created_at":"2026-07-05T04:25:05.392057+00:00","updated_at":"2026-07-05T04:25:05.392057+00:00"}