{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:OIKWE6BC4YV3EFFS5SZJAQ3PC6","short_pith_number":"pith:OIKWE6BC","canonical_record":{"source":{"id":"2111.01040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-11-01T15:43:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a368f79b6ec5d10bc5e56b61a3a7da622e9c16bd8dc1bb54d81726e1f623a43","abstract_canon_sha256":"048a4f23c2dfac727bf631c290b108abac4eb9383f6226577f7f89f7e83fd6bc"},"schema_version":"1.0"},"canonical_sha256":"7215627822e62bb214b2ecb290436f178146eb921c8fc91167adab3ace4e6c86","source":{"kind":"arxiv","id":"2111.01040","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.01040","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"arxiv_version","alias_value":"2111.01040v1","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01040","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"pith_short_12","alias_value":"OIKWE6BC4YV3","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"OIKWE6BC4YV3EFFS","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"OIKWE6BC","created_at":"2026-07-05T03:27:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:OIKWE6BC4YV3EFFS5SZJAQ3PC6","target":"record","payload":{"canonical_record":{"source":{"id":"2111.01040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-11-01T15:43:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a368f79b6ec5d10bc5e56b61a3a7da622e9c16bd8dc1bb54d81726e1f623a43","abstract_canon_sha256":"048a4f23c2dfac727bf631c290b108abac4eb9383f6226577f7f89f7e83fd6bc"},"schema_version":"1.0"},"canonical_sha256":"7215627822e62bb214b2ecb290436f178146eb921c8fc91167adab3ace4e6c86","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:52.935675Z","signature_b64":"bQDTniNfLaenLPQP+cIe1i1nrt1rTCZ7avgjYqZ1TkOlz3NIgDLtILbN5naj8/m1HEMl6QIzyzGTQ8Ehwp7+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7215627822e62bb214b2ecb290436f178146eb921c8fc91167adab3ace4e6c86","last_reissued_at":"2026-07-05T03:27:52.935178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:52.935178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.01040","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":"2026-07-05T03:27:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IsmuL2gcr0tvLKRqLjmvbexVEn11nZzgYTbPb1PIsvl5+Gs8zthw0q1rEMgNuU5ZQGHuhztUamf+z7Vnbe/rAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:08:37.432932Z"},"content_sha256":"ff712af2847bbfca284eaf9f175fe5165383dbd42abe6543596a0d132b13c3b7","schema_version":"1.0","event_id":"sha256:ff712af2847bbfca284eaf9f175fe5165383dbd42abe6543596a0d132b13c3b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:OIKWE6BC4YV3EFFS5SZJAQ3PC6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"STORM+: Fully Adaptive SGD with Momentum for Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Ali Kavis, Kfir Y. Levy, Volkan Cevher","submitted_at":"2021-11-01T15:43:36Z","abstract_excerpt":"In this work we investigate stochastic non-convex optimization problems where the objective is an expectation over smooth loss functions, and the goal is to find an approximate stationary point. The most popular approach to handling such problems is variance reduction techniques, which are also known to obtain tight convergence rates, matching the lower bounds in this case. Nevertheless, these techniques require a careful maintenance of anchor points in conjunction with appropriately selected \"mega-batchsizes\". This leads to a challenging hyperparameter tuning problem, that weakens their pract"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01040","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/2111.01040/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":"2026-07-05T03:27:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wf1eGeeQFFygJv+0eTzEMl8XSXDUkL74PtuuKVlI02B3m8mewyWTSl6H5cybSOtOITOHbnfhwUJZLV3Q+kaFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:08:37.433464Z"},"content_sha256":"3563217f79ab273169d5af31411509656d488d63d697dd075500b4dfc3617266","schema_version":"1.0","event_id":"sha256:3563217f79ab273169d5af31411509656d488d63d697dd075500b4dfc3617266"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OIKWE6BC4YV3EFFS5SZJAQ3PC6/bundle.json","state_url":"https://pith.science/pith/OIKWE6BC4YV3EFFS5SZJAQ3PC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OIKWE6BC4YV3EFFS5SZJAQ3PC6/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":"2026-08-17T22:08:37Z","links":{"resolver":"https://pith.science/pith/OIKWE6BC4YV3EFFS5SZJAQ3PC6","bundle":"https://pith.science/pith/OIKWE6BC4YV3EFFS5SZJAQ3PC6/bundle.json","state":"https://pith.science/pith/OIKWE6BC4YV3EFFS5SZJAQ3PC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OIKWE6BC4YV3EFFS5SZJAQ3PC6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OIKWE6BC4YV3EFFS5SZJAQ3PC6","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":"048a4f23c2dfac727bf631c290b108abac4eb9383f6226577f7f89f7e83fd6bc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-11-01T15:43:36Z","title_canon_sha256":"4a368f79b6ec5d10bc5e56b61a3a7da622e9c16bd8dc1bb54d81726e1f623a43"},"schema_version":"1.0","source":{"id":"2111.01040","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.01040","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"arxiv_version","alias_value":"2111.01040v1","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01040","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"pith_short_12","alias_value":"OIKWE6BC4YV3","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"OIKWE6BC4YV3EFFS","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"OIKWE6BC","created_at":"2026-07-05T03:27:52Z"}],"graph_snapshots":[{"event_id":"sha256:3563217f79ab273169d5af31411509656d488d63d697dd075500b4dfc3617266","target":"graph","created_at":"2026-07-05T03:27:52Z","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/2111.01040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work we investigate stochastic non-convex optimization problems where the objective is an expectation over smooth loss functions, and the goal is to find an approximate stationary point. The most popular approach to handling such problems is variance reduction techniques, which are also known to obtain tight convergence rates, matching the lower bounds in this case. Nevertheless, these techniques require a careful maintenance of anchor points in conjunction with appropriately selected \"mega-batchsizes\". This leads to a challenging hyperparameter tuning problem, that weakens their pract","authors_text":"Ali Kavis, Kfir Y. Levy, Volkan Cevher","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-11-01T15:43:36Z","title":"STORM+: Fully Adaptive SGD with Momentum for Nonconvex Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01040","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:ff712af2847bbfca284eaf9f175fe5165383dbd42abe6543596a0d132b13c3b7","target":"record","created_at":"2026-07-05T03:27:52Z","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":"048a4f23c2dfac727bf631c290b108abac4eb9383f6226577f7f89f7e83fd6bc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-11-01T15:43:36Z","title_canon_sha256":"4a368f79b6ec5d10bc5e56b61a3a7da622e9c16bd8dc1bb54d81726e1f623a43"},"schema_version":"1.0","source":{"id":"2111.01040","kind":"arxiv","version":1}},"canonical_sha256":"7215627822e62bb214b2ecb290436f178146eb921c8fc91167adab3ace4e6c86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7215627822e62bb214b2ecb290436f178146eb921c8fc91167adab3ace4e6c86","first_computed_at":"2026-07-05T03:27:52.935178Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:52.935178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bQDTniNfLaenLPQP+cIe1i1nrt1rTCZ7avgjYqZ1TkOlz3NIgDLtILbN5naj8/m1HEMl6QIzyzGTQ8Ehwp7+Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:52.935675Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.01040","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff712af2847bbfca284eaf9f175fe5165383dbd42abe6543596a0d132b13c3b7","sha256:3563217f79ab273169d5af31411509656d488d63d697dd075500b4dfc3617266"],"state_sha256":"940db4b5a2f94df07b334e8920e060a41751beffda8a082bf9e5f98be895f6e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EUQGBsk3FdojGM0NXepJx0Iqeuxr38o/JLnB2JhhQE31u+sFiiokyZoXzgd5QfoJcDxrSmpMyv9+fJZiUb53Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:08:37.438688Z","bundle_sha256":"b496e2623480fd87b0019a03225f718e8fbce8c509d5739cc3fa3761d7a9bed9"}}