{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5RXQV7TDHQBIVSDG3RB7LLYOSX","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":"425804e4dc117198dd981b67d8ee870f4d2b45d2b6a5f020aa9f2face3cc7f92","cross_cats_sorted":["math.OC","math.PR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-02T16:24:46Z","title_canon_sha256":"dbf3d1fa4af9223a28839b12ccea21b0784671e3bbd92a18e2d361a7b2db5066"},"schema_version":"1.0","source":{"id":"2510.02174","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.02174","created_at":"2026-05-28T01:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"2510.02174v3","created_at":"2026-05-28T01:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.02174","created_at":"2026-05-28T01:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"5RXQV7TDHQBI","created_at":"2026-05-28T01:04:31Z"},{"alias_kind":"pith_short_16","alias_value":"5RXQV7TDHQBIVSDG","created_at":"2026-05-28T01:04:31Z"},{"alias_kind":"pith_short_8","alias_value":"5RXQV7TD","created_at":"2026-05-28T01:04:31Z"}],"graph_snapshots":[{"event_id":"sha256:c57b5e2e64ed35bfa97a1efcce3dffee6a69ffb848aab3340595f8ac76758d02","target":"graph","created_at":"2026-05-28T01:04:31Z","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/2510.02174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Flatness of the loss landscape has been widely studied as an important perspective for understanding the behavior and generalization of deep learning algorithms. Motivated by this view, we propose Flatness-Aware Stochastic Gradient Langevin Dynamics (fSGLD), a first-order optimization method that biases learning its dynamics toward flat basins while retaining the computational and memory efficiency of SGD and SGLD. We provide a non-asymptotic theoretical analysis showing that fSGLD targets a flatness-biased Gibbs distribution under a theoretically prescribed coupling between the noise scale $\\","authors_text":"Dong-Young Lim, Jaehyeon An, Sotirios Sabanis, Stefano Bruno, Youngsik Hwang","cross_cats":["math.OC","math.PR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-02T16:24:46Z","title":"Flatness-Aware Stochastic Gradient Langevin Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.02174","kind":"arxiv","version":3},"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":"sha256:29b172e79d1a0f3ad3cab3a74182d8ae9d588672def3114d225e0a219925888d","target":"record","created_at":"2026-05-28T01:04:31Z","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":"425804e4dc117198dd981b67d8ee870f4d2b45d2b6a5f020aa9f2face3cc7f92","cross_cats_sorted":["math.OC","math.PR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-02T16:24:46Z","title_canon_sha256":"dbf3d1fa4af9223a28839b12ccea21b0784671e3bbd92a18e2d361a7b2db5066"},"schema_version":"1.0","source":{"id":"2510.02174","kind":"arxiv","version":3}},"canonical_sha256":"ec6f0afe633c028ac866dc43f5af0e95eb3fe170e78e8509effb23692808d5be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec6f0afe633c028ac866dc43f5af0e95eb3fe170e78e8509effb23692808d5be","first_computed_at":"2026-05-28T01:04:31.052460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:31.052460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LB6oBqULRnJGryd8ssqQOPYOfbnbSXfvBWs4bZw3pEXULV/bDAPJRKoY8dKIrptkSh0aeAz1fmzdxoU+FiiYAw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:31.053016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.02174","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29b172e79d1a0f3ad3cab3a74182d8ae9d588672def3114d225e0a219925888d","sha256:c57b5e2e64ed35bfa97a1efcce3dffee6a69ffb848aab3340595f8ac76758d02"],"state_sha256":"5270fe67c2a61ce8e9ed33722960aa4d59d9ca9ee6499799a15caf2358ddca2e"}