{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:D5YDHQYOXGZ3HPVP6JNCLJCZI4","short_pith_number":"pith:D5YDHQYO","canonical_record":{"source":{"id":"2606.06722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T21:14:07Z","cross_cats_sorted":[],"title_canon_sha256":"ca452dc856988e66a1dba73993c4d2fb6cb204fcb4e3c87ea8ebf105da0f4241","abstract_canon_sha256":"89c04e0746d44c5846e69001e226ca800f86e7b37405b2995efad0f613afc9d3"},"schema_version":"1.0"},"canonical_sha256":"1f7033c30eb9b3b3beaff25a25a45947002fdc515cc5ad66f18c02f9dbbcd88f","source":{"kind":"arxiv","id":"2606.06722","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06722","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06722v1","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06722","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"D5YDHQYOXGZ3","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"D5YDHQYOXGZ3HPVP","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"D5YDHQYO","created_at":"2026-06-08T01:04:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:D5YDHQYOXGZ3HPVP6JNCLJCZI4","target":"record","payload":{"canonical_record":{"source":{"id":"2606.06722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T21:14:07Z","cross_cats_sorted":[],"title_canon_sha256":"ca452dc856988e66a1dba73993c4d2fb6cb204fcb4e3c87ea8ebf105da0f4241","abstract_canon_sha256":"89c04e0746d44c5846e69001e226ca800f86e7b37405b2995efad0f613afc9d3"},"schema_version":"1.0"},"canonical_sha256":"1f7033c30eb9b3b3beaff25a25a45947002fdc515cc5ad66f18c02f9dbbcd88f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:24.617147Z","signature_b64":"h4SVsBSP3Id/XvkGVSjrj0fRkKV0Ch66jT0+8vUy4P8BE/NtUdXIHTLIhcxrmiZ9UmLmQfjElzhx59TZFA5BCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f7033c30eb9b3b3beaff25a25a45947002fdc515cc5ad66f18c02f9dbbcd88f","last_reissued_at":"2026-06-08T01:04:24.616287Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:24.616287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.06722","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":"2026-06-08T01:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DbMEvwkCV1uua+MPQUqsqtFYBDeHjT/rdWW95RcklYGeUIAlplYdyyIqef+ow7IJdg3hcZ3gfg38n1lWwJvWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T01:55:33.600138Z"},"content_sha256":"7c617e6fe9ac40623f3fca93cfc7dd426935e21a8a430bc92d9251fa51d4800c","schema_version":"1.0","event_id":"sha256:7c617e6fe9ac40623f3fca93cfc7dd426935e21a8a430bc92d9251fa51d4800c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:D5YDHQYOXGZ3HPVP6JNCLJCZI4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flatland: The Adventures of Gradient Descent with Large Step Sizes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Curtis Fox, Holger Rauhut, Leonardo Galli, Mark Schmidt, Wiebke Bartolomaeus","submitted_at":"2026-06-04T21:14:07Z","abstract_excerpt":"The training of neural networks often entails objective functions that are not globally $L$-smooth. For these functions, it is both theoretically and practically difficult to reply to the question: what is the largest possible step size that ensures the convergence of gradient descent (GD)? We address this longstanding open question in deep learning by providing a unifying definition of \"large\" step sizes that requires only local Lipschitz (or even H\\\"older) continuity of the gradient. We design first-order adaptive methods that provably yield large step sizes and show that they operate at the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06722","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/2606.06722/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":"2026-06-08T01:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bvj2bzajHG6tAJrI/SpW4EsFPmUw5gMgOvA4FmmyFNXTeCJlNCf6EVJs5cFjmLAcafic2dMl5Ds93srPZk1AAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T01:55:33.600528Z"},"content_sha256":"4fcb45861522044361bb9f0f01ad5934fe3a7288c8c9b81b6c3aa36c1fbfcbee","schema_version":"1.0","event_id":"sha256:4fcb45861522044361bb9f0f01ad5934fe3a7288c8c9b81b6c3aa36c1fbfcbee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D5YDHQYOXGZ3HPVP6JNCLJCZI4/bundle.json","state_url":"https://pith.science/pith/D5YDHQYOXGZ3HPVP6JNCLJCZI4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D5YDHQYOXGZ3HPVP6JNCLJCZI4/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":"2026-07-03T01:55:33Z","links":{"resolver":"https://pith.science/pith/D5YDHQYOXGZ3HPVP6JNCLJCZI4","bundle":"https://pith.science/pith/D5YDHQYOXGZ3HPVP6JNCLJCZI4/bundle.json","state":"https://pith.science/pith/D5YDHQYOXGZ3HPVP6JNCLJCZI4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D5YDHQYOXGZ3HPVP6JNCLJCZI4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D5YDHQYOXGZ3HPVP6JNCLJCZI4","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":"89c04e0746d44c5846e69001e226ca800f86e7b37405b2995efad0f613afc9d3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T21:14:07Z","title_canon_sha256":"ca452dc856988e66a1dba73993c4d2fb6cb204fcb4e3c87ea8ebf105da0f4241"},"schema_version":"1.0","source":{"id":"2606.06722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06722","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06722v1","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06722","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"D5YDHQYOXGZ3","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"D5YDHQYOXGZ3HPVP","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"D5YDHQYO","created_at":"2026-06-08T01:04:24Z"}],"graph_snapshots":[{"event_id":"sha256:4fcb45861522044361bb9f0f01ad5934fe3a7288c8c9b81b6c3aa36c1fbfcbee","target":"graph","created_at":"2026-06-08T01:04:24Z","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/2606.06722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The training of neural networks often entails objective functions that are not globally $L$-smooth. For these functions, it is both theoretically and practically difficult to reply to the question: what is the largest possible step size that ensures the convergence of gradient descent (GD)? We address this longstanding open question in deep learning by providing a unifying definition of \"large\" step sizes that requires only local Lipschitz (or even H\\\"older) continuity of the gradient. We design first-order adaptive methods that provably yield large step sizes and show that they operate at the","authors_text":"Curtis Fox, Holger Rauhut, Leonardo Galli, Mark Schmidt, Wiebke Bartolomaeus","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T21:14:07Z","title":"Flatland: The Adventures of Gradient Descent with Large Step Sizes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06722","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":"sha256:7c617e6fe9ac40623f3fca93cfc7dd426935e21a8a430bc92d9251fa51d4800c","target":"record","created_at":"2026-06-08T01:04:24Z","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":"89c04e0746d44c5846e69001e226ca800f86e7b37405b2995efad0f613afc9d3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T21:14:07Z","title_canon_sha256":"ca452dc856988e66a1dba73993c4d2fb6cb204fcb4e3c87ea8ebf105da0f4241"},"schema_version":"1.0","source":{"id":"2606.06722","kind":"arxiv","version":1}},"canonical_sha256":"1f7033c30eb9b3b3beaff25a25a45947002fdc515cc5ad66f18c02f9dbbcd88f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f7033c30eb9b3b3beaff25a25a45947002fdc515cc5ad66f18c02f9dbbcd88f","first_computed_at":"2026-06-08T01:04:24.616287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:24.616287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h4SVsBSP3Id/XvkGVSjrj0fRkKV0Ch66jT0+8vUy4P8BE/NtUdXIHTLIhcxrmiZ9UmLmQfjElzhx59TZFA5BCg==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:24.617147Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c617e6fe9ac40623f3fca93cfc7dd426935e21a8a430bc92d9251fa51d4800c","sha256:4fcb45861522044361bb9f0f01ad5934fe3a7288c8c9b81b6c3aa36c1fbfcbee"],"state_sha256":"6fe212e7371776665d01a1728b52259bb7b9510aff90b19a6242e36dc8604937"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ct4UXJNQ5ufQZy8QYqz4fi/N4XLgyS3rVXiGudUQT5ZREOSmOUWiI/df93ySt4v0ydDfayZb1V8J+4QZPseBBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T01:55:33.602698Z","bundle_sha256":"40ee9a623a015851414067c67f3ad1ff624932ae0d5e2290b615b5d13d503146"}}