{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RSN2H7KM5KGKQIBLZ4YJNOHQ4K","short_pith_number":"pith:RSN2H7KM","canonical_record":{"source":{"id":"2312.17369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T21:28:08Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"9fc63e83f91e65904769ebce24583487537c046f2ec08a444995e34edda36dd3","abstract_canon_sha256":"67b1ed5beea94fce9a18d536e8b5e6557941e92833d1a6aa3c99f84bac9f6365"},"schema_version":"1.0"},"canonical_sha256":"8c9ba3fd4cea8ca8202bcf3096b8f0e295df6910efe418f1ade8d956f8f6b2c2","source":{"kind":"arxiv","id":"2312.17369","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.17369","created_at":"2026-07-05T07:28:50Z"},{"alias_kind":"arxiv_version","alias_value":"2312.17369v1","created_at":"2026-07-05T07:28:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17369","created_at":"2026-07-05T07:28:50Z"},{"alias_kind":"pith_short_12","alias_value":"RSN2H7KM5KGK","created_at":"2026-07-05T07:28:50Z"},{"alias_kind":"pith_short_16","alias_value":"RSN2H7KM5KGKQIBL","created_at":"2026-07-05T07:28:50Z"},{"alias_kind":"pith_short_8","alias_value":"RSN2H7KM","created_at":"2026-07-05T07:28:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RSN2H7KM5KGKQIBLZ4YJNOHQ4K","target":"record","payload":{"canonical_record":{"source":{"id":"2312.17369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T21:28:08Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"9fc63e83f91e65904769ebce24583487537c046f2ec08a444995e34edda36dd3","abstract_canon_sha256":"67b1ed5beea94fce9a18d536e8b5e6557941e92833d1a6aa3c99f84bac9f6365"},"schema_version":"1.0"},"canonical_sha256":"8c9ba3fd4cea8ca8202bcf3096b8f0e295df6910efe418f1ade8d956f8f6b2c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:50.111165Z","signature_b64":"kJKUMeUHwPN0KKIdKz5ugdVQpyziAHt+SjiN9QKGEQu9ZYGLuyOSAVPnb5ezLO0fkjsf0GuhxI0+iwvQj2CRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c9ba3fd4cea8ca8202bcf3096b8f0e295df6910efe418f1ade8d956f8f6b2c2","last_reissued_at":"2026-07-05T07:28:50.110726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:50.110726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.17369","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:28:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQ9R8m4HWVGyiXCQD+1TjghSRnUWyLYz/n+CakJYeqmYAr0F8/b7nO6BMoJalTki6Xwg/qE+Wba0kcoUxA3SAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:31:40.430752Z"},"content_sha256":"f2915725a3556092b873d291250d2a2ae3b67917c29b6a2cfa5a10859e139d9c","schema_version":"1.0","event_id":"sha256:f2915725a3556092b873d291250d2a2ae3b67917c29b6a2cfa5a10859e139d9c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RSN2H7KM5KGKQIBLZ4YJNOHQ4K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Chulu Xiang, Dmitry Kamzolov, Farshed Abdukhakimov, Martin Tak\\'a\\v{c}, Robert Gower","submitted_at":"2023-12-28T21:28:08Z","abstract_excerpt":"Adaptive optimization methods are widely recognized as among the most popular approaches for training Deep Neural Networks (DNNs). Techniques such as Adam, AdaGrad, and AdaHessian utilize a preconditioner that modifies the search direction by incorporating information about the curvature of the objective function. However, despite their adaptive characteristics, these methods still require manual fine-tuning of the step-size. This, in turn, impacts the time required to solve a particular problem. This paper presents an optimization framework named SANIA to tackle these challenges. Beyond elimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17369","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/2312.17369/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:28:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JIzb7GWrK3et0lSWPxvph2jHQY7MnJ2iQisBDlh6wlHCI8zyP1qiiYhyYcK/9S1MIgfpMCiwUxcLhgUA2e+MBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:31:40.431504Z"},"content_sha256":"078ed1c4ad60b604dc8efd93e79df95503ecacbd58ecb02bb168cc0e78ff4835","schema_version":"1.0","event_id":"sha256:078ed1c4ad60b604dc8efd93e79df95503ecacbd58ecb02bb168cc0e78ff4835"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RSN2H7KM5KGKQIBLZ4YJNOHQ4K/bundle.json","state_url":"https://pith.science/pith/RSN2H7KM5KGKQIBLZ4YJNOHQ4K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RSN2H7KM5KGKQIBLZ4YJNOHQ4K/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T15:31:40Z","links":{"resolver":"https://pith.science/pith/RSN2H7KM5KGKQIBLZ4YJNOHQ4K","bundle":"https://pith.science/pith/RSN2H7KM5KGKQIBLZ4YJNOHQ4K/bundle.json","state":"https://pith.science/pith/RSN2H7KM5KGKQIBLZ4YJNOHQ4K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RSN2H7KM5KGKQIBLZ4YJNOHQ4K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RSN2H7KM5KGKQIBLZ4YJNOHQ4K","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"67b1ed5beea94fce9a18d536e8b5e6557941e92833d1a6aa3c99f84bac9f6365","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T21:28:08Z","title_canon_sha256":"9fc63e83f91e65904769ebce24583487537c046f2ec08a444995e34edda36dd3"},"schema_version":"1.0","source":{"id":"2312.17369","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.17369","created_at":"2026-07-05T07:28:50Z"},{"alias_kind":"arxiv_version","alias_value":"2312.17369v1","created_at":"2026-07-05T07:28:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17369","created_at":"2026-07-05T07:28:50Z"},{"alias_kind":"pith_short_12","alias_value":"RSN2H7KM5KGK","created_at":"2026-07-05T07:28:50Z"},{"alias_kind":"pith_short_16","alias_value":"RSN2H7KM5KGKQIBL","created_at":"2026-07-05T07:28:50Z"},{"alias_kind":"pith_short_8","alias_value":"RSN2H7KM","created_at":"2026-07-05T07:28:50Z"}],"graph_snapshots":[{"event_id":"sha256:078ed1c4ad60b604dc8efd93e79df95503ecacbd58ecb02bb168cc0e78ff4835","target":"graph","created_at":"2026-07-05T07:28:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.17369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adaptive optimization methods are widely recognized as among the most popular approaches for training Deep Neural Networks (DNNs). Techniques such as Adam, AdaGrad, and AdaHessian utilize a preconditioner that modifies the search direction by incorporating information about the curvature of the objective function. However, despite their adaptive characteristics, these methods still require manual fine-tuning of the step-size. This, in turn, impacts the time required to solve a particular problem. This paper presents an optimization framework named SANIA to tackle these challenges. Beyond elimi","authors_text":"Chulu Xiang, Dmitry Kamzolov, Farshed Abdukhakimov, Martin Tak\\'a\\v{c}, Robert Gower","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T21:28:08Z","title":"SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17369","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f2915725a3556092b873d291250d2a2ae3b67917c29b6a2cfa5a10859e139d9c","target":"record","created_at":"2026-07-05T07:28:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"67b1ed5beea94fce9a18d536e8b5e6557941e92833d1a6aa3c99f84bac9f6365","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T21:28:08Z","title_canon_sha256":"9fc63e83f91e65904769ebce24583487537c046f2ec08a444995e34edda36dd3"},"schema_version":"1.0","source":{"id":"2312.17369","kind":"arxiv","version":1}},"canonical_sha256":"8c9ba3fd4cea8ca8202bcf3096b8f0e295df6910efe418f1ade8d956f8f6b2c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c9ba3fd4cea8ca8202bcf3096b8f0e295df6910efe418f1ade8d956f8f6b2c2","first_computed_at":"2026-07-05T07:28:50.110726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:50.110726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kJKUMeUHwPN0KKIdKz5ugdVQpyziAHt+SjiN9QKGEQu9ZYGLuyOSAVPnb5ezLO0fkjsf0GuhxI0+iwvQj2CRDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:50.111165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.17369","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2915725a3556092b873d291250d2a2ae3b67917c29b6a2cfa5a10859e139d9c","sha256:078ed1c4ad60b604dc8efd93e79df95503ecacbd58ecb02bb168cc0e78ff4835"],"state_sha256":"0e274c37b521015549913fb688961683d39c0c23acc3f3067fd8a9fb08f244fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IPSjA6Eq0NJ3PRVG6NJnyW/bptMaHWX1s5m1CzYqT4tCYH94hlvOMyx6mT/UfHRTMQElJcoXSFfHOwhi1K4rBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T15:31:40.436993Z","bundle_sha256":"7126da3ac3cf62b9db6089a7fdba20dc029b9fa970bc24e98c24482798ce0791"}}