{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TAVFBZ5NM6VK2EEMPWCGZLELTC","short_pith_number":"pith:TAVFBZ5N","canonical_record":{"source":{"id":"2504.04105","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-04-05T08:34:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"28f3e56d5b3e1a6d35992573bf616ceab2862ee7d2ee1fa6ddd03c1447face81","abstract_canon_sha256":"36b15aba65800679ee6b8fcaad36c598cb34c6f8546e68ba48d7e835703fe304"},"schema_version":"1.0"},"canonical_sha256":"982a50e7ad67aaad108c7d846cac8b98b8f25848b8cffac30a55504780e20fd4","source":{"kind":"arxiv","id":"2504.04105","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04105","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04105v2","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04105","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"pith_short_12","alias_value":"TAVFBZ5NM6VK","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"pith_short_16","alias_value":"TAVFBZ5NM6VK2EEM","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"pith_short_8","alias_value":"TAVFBZ5N","created_at":"2026-07-05T10:50:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TAVFBZ5NM6VK2EEMPWCGZLELTC","target":"record","payload":{"canonical_record":{"source":{"id":"2504.04105","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-04-05T08:34:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"28f3e56d5b3e1a6d35992573bf616ceab2862ee7d2ee1fa6ddd03c1447face81","abstract_canon_sha256":"36b15aba65800679ee6b8fcaad36c598cb34c6f8546e68ba48d7e835703fe304"},"schema_version":"1.0"},"canonical_sha256":"982a50e7ad67aaad108c7d846cac8b98b8f25848b8cffac30a55504780e20fd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:48.349907Z","signature_b64":"IplD2+2gDN41jqmqHX2xrxoacFRj2V4nt8WH7lYugvbjvS1cpYk5JTAm5asdFyaUa4JB0CufeSTtBsxDJhVhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"982a50e7ad67aaad108c7d846cac8b98b8f25848b8cffac30a55504780e20fd4","last_reissued_at":"2026-07-05T10:50:48.349378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:48.349378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.04105","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:50:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yBwZDHpsajab+meH2sfB+gy8rhU3fK8ygjbIzBu81cAzfZfKpQacG2TUML4kUFdEdc1e5BP7+dY1CFIYVclICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T03:52:49.549209Z"},"content_sha256":"f4a0e5809fc8e50799f4c288c8d79d9961fde8baec1ddec483041415773c81f1","schema_version":"1.0","event_id":"sha256:f4a0e5809fc8e50799f4c288c8d79d9961fde8baec1ddec483041415773c81f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TAVFBZ5NM6VK2EEMPWCGZLELTC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jingfeng Wu, Licong Lin, Peter L. Bartlett, Ruiqi Zhang","submitted_at":"2025-04-05T08:34:20Z","abstract_excerpt":"We study $\\textit{gradient descent}$ (GD) for logistic regression on linearly separable data with stepsizes that adapt to the current risk, scaled by a constant hyperparameter $\\eta$. We show that after at most $1/\\gamma^2$ burn-in steps, GD achieves a risk upper bounded by $\\exp(-\\Theta(\\eta))$, where $\\gamma$ is the margin of the dataset. As $\\eta$ can be arbitrarily large, GD attains an arbitrarily small risk $\\textit{immediately after the burn-in steps}$, though the risk evolution may be $\\textit{non-monotonic}$.\n  We further construct hard datasets with margin $\\gamma$, where any batch (o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04105","kind":"arxiv","version":2},"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/2504.04105/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":"2026-07-05T10:50:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Trbsyx1pw5viZEMeFHPow0g44EZfcBnpWaPrn/GtzPFPjl77TzQCosEeuPJSXEXiBIpL5dqYj9w1verFtmJFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T03:52:49.549834Z"},"content_sha256":"c7c9050dcaaaa8e93ead4ea16460e99f6b2d2f8802f125e1897753af605a3a29","schema_version":"1.0","event_id":"sha256:c7c9050dcaaaa8e93ead4ea16460e99f6b2d2f8802f125e1897753af605a3a29"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TAVFBZ5NM6VK2EEMPWCGZLELTC/bundle.json","state_url":"https://pith.science/pith/TAVFBZ5NM6VK2EEMPWCGZLELTC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TAVFBZ5NM6VK2EEMPWCGZLELTC/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":"2026-08-12T03:52:49Z","links":{"resolver":"https://pith.science/pith/TAVFBZ5NM6VK2EEMPWCGZLELTC","bundle":"https://pith.science/pith/TAVFBZ5NM6VK2EEMPWCGZLELTC/bundle.json","state":"https://pith.science/pith/TAVFBZ5NM6VK2EEMPWCGZLELTC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TAVFBZ5NM6VK2EEMPWCGZLELTC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TAVFBZ5NM6VK2EEMPWCGZLELTC","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":"36b15aba65800679ee6b8fcaad36c598cb34c6f8546e68ba48d7e835703fe304","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-04-05T08:34:20Z","title_canon_sha256":"28f3e56d5b3e1a6d35992573bf616ceab2862ee7d2ee1fa6ddd03c1447face81"},"schema_version":"1.0","source":{"id":"2504.04105","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04105","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04105v2","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04105","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"pith_short_12","alias_value":"TAVFBZ5NM6VK","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"pith_short_16","alias_value":"TAVFBZ5NM6VK2EEM","created_at":"2026-07-05T10:50:48Z"},{"alias_kind":"pith_short_8","alias_value":"TAVFBZ5N","created_at":"2026-07-05T10:50:48Z"}],"graph_snapshots":[{"event_id":"sha256:c7c9050dcaaaa8e93ead4ea16460e99f6b2d2f8802f125e1897753af605a3a29","target":"graph","created_at":"2026-07-05T10:50:48Z","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/2504.04105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study $\\textit{gradient descent}$ (GD) for logistic regression on linearly separable data with stepsizes that adapt to the current risk, scaled by a constant hyperparameter $\\eta$. We show that after at most $1/\\gamma^2$ burn-in steps, GD achieves a risk upper bounded by $\\exp(-\\Theta(\\eta))$, where $\\gamma$ is the margin of the dataset. As $\\eta$ can be arbitrarily large, GD attains an arbitrarily small risk $\\textit{immediately after the burn-in steps}$, though the risk evolution may be $\\textit{non-monotonic}$.\n  We further construct hard datasets with margin $\\gamma$, where any batch (o","authors_text":"Jingfeng Wu, Licong Lin, Peter L. Bartlett, Ruiqi Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-04-05T08:34:20Z","title":"Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04105","kind":"arxiv","version":2},"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:f4a0e5809fc8e50799f4c288c8d79d9961fde8baec1ddec483041415773c81f1","target":"record","created_at":"2026-07-05T10:50:48Z","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":"36b15aba65800679ee6b8fcaad36c598cb34c6f8546e68ba48d7e835703fe304","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-04-05T08:34:20Z","title_canon_sha256":"28f3e56d5b3e1a6d35992573bf616ceab2862ee7d2ee1fa6ddd03c1447face81"},"schema_version":"1.0","source":{"id":"2504.04105","kind":"arxiv","version":2}},"canonical_sha256":"982a50e7ad67aaad108c7d846cac8b98b8f25848b8cffac30a55504780e20fd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"982a50e7ad67aaad108c7d846cac8b98b8f25848b8cffac30a55504780e20fd4","first_computed_at":"2026-07-05T10:50:48.349378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:48.349378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IplD2+2gDN41jqmqHX2xrxoacFRj2V4nt8WH7lYugvbjvS1cpYk5JTAm5asdFyaUa4JB0CufeSTtBsxDJhVhAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:48.349907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04105","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4a0e5809fc8e50799f4c288c8d79d9961fde8baec1ddec483041415773c81f1","sha256:c7c9050dcaaaa8e93ead4ea16460e99f6b2d2f8802f125e1897753af605a3a29"],"state_sha256":"dca04b9cff5307f231f44eaf79a6f28a99e7623db982f38a28831354a4f51cf1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"78eceYkkA/T9M2lY5hIMNOZP7T/rFa34ZfRKdbkwDB7tXUc0e6RvgXj4mujyfvSRFSzGyPXxtx60QNgDgti3DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T03:52:49.555249Z","bundle_sha256":"e69fc4760935e35949ba2c63b4773024ef636dbe577b7729418e04ba34f3ba9e"}}