{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ECMTFQ2TX5BKNLXPMBFDUQVJET","short_pith_number":"pith:ECMTFQ2T","canonical_record":{"source":{"id":"2606.21683","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-19T18:43:41Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"68b9c6d7dd7981763df24d73bb3be4243f517c937b2f84aab4f42f7889a263c9","abstract_canon_sha256":"1dc435d6410f39f4ca19f37717a2b006f53c94ea9532f04fe066ebf1c5a20b97"},"schema_version":"1.0"},"canonical_sha256":"209932c353bf42a6aeef604a3a42a924cd1c70a4d28c77d11bd7c4734d392895","source":{"kind":"arxiv","id":"2606.21683","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21683","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21683v1","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21683","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"ECMTFQ2TX5BK","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"ECMTFQ2TX5BKNLXP","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"ECMTFQ2T","created_at":"2026-06-23T01:13:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ECMTFQ2TX5BKNLXPMBFDUQVJET","target":"record","payload":{"canonical_record":{"source":{"id":"2606.21683","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-19T18:43:41Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"68b9c6d7dd7981763df24d73bb3be4243f517c937b2f84aab4f42f7889a263c9","abstract_canon_sha256":"1dc435d6410f39f4ca19f37717a2b006f53c94ea9532f04fe066ebf1c5a20b97"},"schema_version":"1.0"},"canonical_sha256":"209932c353bf42a6aeef604a3a42a924cd1c70a4d28c77d11bd7c4734d392895","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:18.824216Z","signature_b64":"P+IVeYm+/TiFDLxYWv05uSLlHIFVWLBCi9N56mO1iTgefzMJlOYhOt83ZqZLG8hJM3mPs/kstvmYBGN9RMgNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"209932c353bf42a6aeef604a3a42a924cd1c70a4d28c77d11bd7c4734d392895","last_reissued_at":"2026-06-23T01:13:18.823741Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:18.823741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.21683","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":"2026-06-23T01:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GNY0QYvCHdHv4mdED0cJhDt+t3/dJ5Hj66v/k7Qsl+HrWq0yjkPjTKGMW8qYVTUS4t46XLVEMAGCfmTg3qCBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:44:28.569045Z"},"content_sha256":"eea66fd8b70087a5663c2a852c95a24b7cf0b365bc3f0f6503ffdc5d5f30464c","schema_version":"1.0","event_id":"sha256:eea66fd8b70087a5663c2a852c95a24b7cf0b365bc3f0f6503ffdc5d5f30464c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ECMTFQ2TX5BKNLXPMBFDUQVJET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finite-Sample Performance of Gradient Descent in Logistic Regression with Gaussian Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Arya Mazumdar, Junren Chen","submitted_at":"2026-06-19T18:43:41Z","abstract_excerpt":"We consider the parameter estimation problem in logistic regression with Gaussian design: the estimation of a fixed unknown parameter $\\theta^*\\in \\mathbb{R}^d$ ($\\|\\theta^*\\|_2\\ge 1$) from $n$ i.i.d. samples $\\{(x_i,y_i)\\}_{i=1}^n$, where $x_i\\sim N(0,I_d)$ and $y_i|x_i \\sim {\\rm Bernoulli}(1/(1+\\exp(-x_i^\\top \\theta^*)))$. Our main aim is to characterize the finite-sample estimation performance and convergence behavior of gradient descent (GD) on the maximum likelihood objective (i.e., the logistic loss). Under small $O(1)$ stepsize and $0$ initialization, we show that GD linearly converges "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21683","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/2606.21683/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":"2026-06-23T01:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZWrmOxLyP8k1GHkDC0XCRQLChLrAbSvgdmmZ6SfQnYEF0U7Pclx5qHTuBjOvX+fKPNjzIxOPJXQGO5sS03ZRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:44:28.569447Z"},"content_sha256":"b6ecaa2c1270d827711020ba4689f037db1d6bc2d865de12e6da4d74fe9ca8c5","schema_version":"1.0","event_id":"sha256:b6ecaa2c1270d827711020ba4689f037db1d6bc2d865de12e6da4d74fe9ca8c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ECMTFQ2TX5BKNLXPMBFDUQVJET/bundle.json","state_url":"https://pith.science/pith/ECMTFQ2TX5BKNLXPMBFDUQVJET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ECMTFQ2TX5BKNLXPMBFDUQVJET/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":"2026-06-28T15:44:28Z","links":{"resolver":"https://pith.science/pith/ECMTFQ2TX5BKNLXPMBFDUQVJET","bundle":"https://pith.science/pith/ECMTFQ2TX5BKNLXPMBFDUQVJET/bundle.json","state":"https://pith.science/pith/ECMTFQ2TX5BKNLXPMBFDUQVJET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ECMTFQ2TX5BKNLXPMBFDUQVJET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ECMTFQ2TX5BKNLXPMBFDUQVJET","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":"1dc435d6410f39f4ca19f37717a2b006f53c94ea9532f04fe066ebf1c5a20b97","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-19T18:43:41Z","title_canon_sha256":"68b9c6d7dd7981763df24d73bb3be4243f517c937b2f84aab4f42f7889a263c9"},"schema_version":"1.0","source":{"id":"2606.21683","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21683","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21683v1","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21683","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"ECMTFQ2TX5BK","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"ECMTFQ2TX5BKNLXP","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"ECMTFQ2T","created_at":"2026-06-23T01:13:18Z"}],"graph_snapshots":[{"event_id":"sha256:b6ecaa2c1270d827711020ba4689f037db1d6bc2d865de12e6da4d74fe9ca8c5","target":"graph","created_at":"2026-06-23T01:13:18Z","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/2606.21683/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the parameter estimation problem in logistic regression with Gaussian design: the estimation of a fixed unknown parameter $\\theta^*\\in \\mathbb{R}^d$ ($\\|\\theta^*\\|_2\\ge 1$) from $n$ i.i.d. samples $\\{(x_i,y_i)\\}_{i=1}^n$, where $x_i\\sim N(0,I_d)$ and $y_i|x_i \\sim {\\rm Bernoulli}(1/(1+\\exp(-x_i^\\top \\theta^*)))$. Our main aim is to characterize the finite-sample estimation performance and convergence behavior of gradient descent (GD) on the maximum likelihood objective (i.e., the logistic loss). Under small $O(1)$ stepsize and $0$ initialization, we show that GD linearly converges ","authors_text":"Arya Mazumdar, Junren Chen","cross_cats":["cs.IT","cs.LG","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-19T18:43:41Z","title":"Finite-Sample Performance of Gradient Descent in Logistic Regression with Gaussian Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21683","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:eea66fd8b70087a5663c2a852c95a24b7cf0b365bc3f0f6503ffdc5d5f30464c","target":"record","created_at":"2026-06-23T01:13:18Z","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":"1dc435d6410f39f4ca19f37717a2b006f53c94ea9532f04fe066ebf1c5a20b97","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-19T18:43:41Z","title_canon_sha256":"68b9c6d7dd7981763df24d73bb3be4243f517c937b2f84aab4f42f7889a263c9"},"schema_version":"1.0","source":{"id":"2606.21683","kind":"arxiv","version":1}},"canonical_sha256":"209932c353bf42a6aeef604a3a42a924cd1c70a4d28c77d11bd7c4734d392895","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"209932c353bf42a6aeef604a3a42a924cd1c70a4d28c77d11bd7c4734d392895","first_computed_at":"2026-06-23T01:13:18.823741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:13:18.823741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P+IVeYm+/TiFDLxYWv05uSLlHIFVWLBCi9N56mO1iTgefzMJlOYhOt83ZqZLG8hJM3mPs/kstvmYBGN9RMgNAg==","signature_status":"signed_v1","signed_at":"2026-06-23T01:13:18.824216Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21683","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eea66fd8b70087a5663c2a852c95a24b7cf0b365bc3f0f6503ffdc5d5f30464c","sha256:b6ecaa2c1270d827711020ba4689f037db1d6bc2d865de12e6da4d74fe9ca8c5"],"state_sha256":"06113db8f3d2f26feea38f7a703fd259f6c84c56447d3a9227e22d19ff8751dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5U3qRSbwDvvbDh4rv/uFOC7sI+V4K8FO2c/agj5cT1C5QO5t7obue2iKUBxYH64gvf3LTFmnhaGr45tnq35dDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T15:44:28.572418Z","bundle_sha256":"ffdd243cb1339c4da3fded358a61d55f25f0f1af3acf9d28aab58c62491d42a3"}}