{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:34UYGA4S2WT3B3FYAZS5XSS2GJ","short_pith_number":"pith:34UYGA4S","canonical_record":{"source":{"id":"2606.01827","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-01T07:42:01Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"e90b0619413e1c835139d24a73ecb8887a492e44fc3fe4fcf6e0862ecab32c8b","abstract_canon_sha256":"79714f934fcd3a743c8e1edc1616fc11e132e6723db773a25843f5cd2c6e05ef"},"schema_version":"1.0"},"canonical_sha256":"df29830392d5a7b0ecb80665dbca5a325cb6422c2d952762931f9075f34bd8e3","source":{"kind":"arxiv","id":"2606.01827","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01827","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01827v1","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01827","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"34UYGA4S2WT3","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"34UYGA4S2WT3B3FY","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"34UYGA4S","created_at":"2026-06-02T02:04:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:34UYGA4S2WT3B3FYAZS5XSS2GJ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.01827","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-01T07:42:01Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"e90b0619413e1c835139d24a73ecb8887a492e44fc3fe4fcf6e0862ecab32c8b","abstract_canon_sha256":"79714f934fcd3a743c8e1edc1616fc11e132e6723db773a25843f5cd2c6e05ef"},"schema_version":"1.0"},"canonical_sha256":"df29830392d5a7b0ecb80665dbca5a325cb6422c2d952762931f9075f34bd8e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:57.947295Z","signature_b64":"f2iJbFAcN9owrE5ky/pMVGufNWmSXCbGsbPz7k8ZSWQK3I6H3fNcMMw6NRCdwohb6eval005fj6f3D7B/XZcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df29830392d5a7b0ecb80665dbca5a325cb6422c2d952762931f9075f34bd8e3","last_reissued_at":"2026-06-02T02:04:57.946971Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:57.946971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.01827","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":"2026-06-02T02:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+f/XJ/VE2ghL3ZXYjjQAQIGgMZ63aH9in2eUgSZhXyWGas/MoGOTHlY1xoVwjbVnVqpse5NjfuW24wJ+UqRiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:41:26.342232Z"},"content_sha256":"c34c2e6faee83bbe65028f09afb75d121ac467e424166218c2bfa41944c81289","schema_version":"1.0","event_id":"sha256:c34c2e6faee83bbe65028f09afb75d121ac467e424166218c2bfa41944c81289"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:34UYGA4S2WT3B3FYAZS5XSS2GJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Dimitris Oikonomou, Nicolas Loizou","submitted_at":"2026-06-01T07:42:01Z","abstract_excerpt":"Sharpness-Aware Minimization (SAM) has established itself as a powerful and widely adopted optimizer for training machine learning models. By explicitly minimizing the sharpness of the loss landscape, SAM often improves generalization while delivering strong empirical performance. However, SAM and its variants, like most training algorithms, are sensitive to the choice of learning rate, which is typically selected through extensive hyperparameter tuning or predefined schedulers. In this work, motivated by recent advances on the effectiveness of stochastic Polyak step sizes for Stochastic Gradi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01827","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/2606.01827/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":"2026-06-02T02:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4+OOl881upSjhlUMt/2RIPGKiV1ZqSi3oMdQtxk6eEoj51Oov/YbCFFKnrUI7y5Qpx+C5dDsxsOzxiK431tLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:41:26.342627Z"},"content_sha256":"7b7b5af0fa7904360e457196d6e4999cdea5dba6e3d4dd6fbe489aab085ff337","schema_version":"1.0","event_id":"sha256:7b7b5af0fa7904360e457196d6e4999cdea5dba6e3d4dd6fbe489aab085ff337"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/34UYGA4S2WT3B3FYAZS5XSS2GJ/bundle.json","state_url":"https://pith.science/pith/34UYGA4S2WT3B3FYAZS5XSS2GJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/34UYGA4S2WT3B3FYAZS5XSS2GJ/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":"2026-07-06T10:41:26Z","links":{"resolver":"https://pith.science/pith/34UYGA4S2WT3B3FYAZS5XSS2GJ","bundle":"https://pith.science/pith/34UYGA4S2WT3B3FYAZS5XSS2GJ/bundle.json","state":"https://pith.science/pith/34UYGA4S2WT3B3FYAZS5XSS2GJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/34UYGA4S2WT3B3FYAZS5XSS2GJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:34UYGA4S2WT3B3FYAZS5XSS2GJ","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":"79714f934fcd3a743c8e1edc1616fc11e132e6723db773a25843f5cd2c6e05ef","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-01T07:42:01Z","title_canon_sha256":"e90b0619413e1c835139d24a73ecb8887a492e44fc3fe4fcf6e0862ecab32c8b"},"schema_version":"1.0","source":{"id":"2606.01827","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01827","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01827v1","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01827","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"34UYGA4S2WT3","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"34UYGA4S2WT3B3FY","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"34UYGA4S","created_at":"2026-06-02T02:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:7b7b5af0fa7904360e457196d6e4999cdea5dba6e3d4dd6fbe489aab085ff337","target":"graph","created_at":"2026-06-02T02:04:57Z","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/2606.01827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sharpness-Aware Minimization (SAM) has established itself as a powerful and widely adopted optimizer for training machine learning models. By explicitly minimizing the sharpness of the loss landscape, SAM often improves generalization while delivering strong empirical performance. However, SAM and its variants, like most training algorithms, are sensitive to the choice of learning rate, which is typically selected through extensive hyperparameter tuning or predefined schedulers. In this work, motivated by recent advances on the effectiveness of stochastic Polyak step sizes for Stochastic Gradi","authors_text":"Dimitris Oikonomou, Nicolas Loizou","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-01T07:42:01Z","title":"Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01827","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:c34c2e6faee83bbe65028f09afb75d121ac467e424166218c2bfa41944c81289","target":"record","created_at":"2026-06-02T02:04:57Z","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":"79714f934fcd3a743c8e1edc1616fc11e132e6723db773a25843f5cd2c6e05ef","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-01T07:42:01Z","title_canon_sha256":"e90b0619413e1c835139d24a73ecb8887a492e44fc3fe4fcf6e0862ecab32c8b"},"schema_version":"1.0","source":{"id":"2606.01827","kind":"arxiv","version":1}},"canonical_sha256":"df29830392d5a7b0ecb80665dbca5a325cb6422c2d952762931f9075f34bd8e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df29830392d5a7b0ecb80665dbca5a325cb6422c2d952762931f9075f34bd8e3","first_computed_at":"2026-06-02T02:04:57.946971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:57.946971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f2iJbFAcN9owrE5ky/pMVGufNWmSXCbGsbPz7k8ZSWQK3I6H3fNcMMw6NRCdwohb6eval005fj6f3D7B/XZcBQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:57.947295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01827","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c34c2e6faee83bbe65028f09afb75d121ac467e424166218c2bfa41944c81289","sha256:7b7b5af0fa7904360e457196d6e4999cdea5dba6e3d4dd6fbe489aab085ff337"],"state_sha256":"99a34f47f86312cc167176a95fd5a9248caba0c776cff80136b52b4bfd4e26e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oJIRGLZKsF8JMxGcV1VaimMh13B8SdWrNIYqMfPbYzM3+/Iugq6Y6qJKkU4Kbx7ABbFLwY9U/QEIDn3y3jstCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:41:26.344896Z","bundle_sha256":"39df769b697013dec34a37bb0f92ca6ceebd461e0e5a1ec5f9f55db5d280fc8e"}}