{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PHSYUZK7CO4K6HK357AV4LH7AC","short_pith_number":"pith:PHSYUZK7","canonical_record":{"source":{"id":"2607.04233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-07-05T11:11:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"130785652380491a4776f21dca065fb3adf506559ec37da768d8862bc9eb650c","abstract_canon_sha256":"1cf9937d03a161b4ff722bb1510815e260b0aad3fc741ec926faa6ce6c6240f6"},"schema_version":"1.0"},"canonical_sha256":"79e58a655f13b8af1d5befc15e2cff008a40e5fb0ca678ad533419f8219fea2e","source":{"kind":"arxiv","id":"2607.04233","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04233","created_at":"2026-07-07T02:19:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04233v1","created_at":"2026-07-07T02:19:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04233","created_at":"2026-07-07T02:19:04Z"},{"alias_kind":"pith_short_12","alias_value":"PHSYUZK7CO4K","created_at":"2026-07-07T02:19:04Z"},{"alias_kind":"pith_short_16","alias_value":"PHSYUZK7CO4K6HK3","created_at":"2026-07-07T02:19:04Z"},{"alias_kind":"pith_short_8","alias_value":"PHSYUZK7","created_at":"2026-07-07T02:19:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PHSYUZK7CO4K6HK357AV4LH7AC","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-07-05T11:11:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"130785652380491a4776f21dca065fb3adf506559ec37da768d8862bc9eb650c","abstract_canon_sha256":"1cf9937d03a161b4ff722bb1510815e260b0aad3fc741ec926faa6ce6c6240f6"},"schema_version":"1.0"},"canonical_sha256":"79e58a655f13b8af1d5befc15e2cff008a40e5fb0ca678ad533419f8219fea2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:04.502683Z","signature_b64":"3CHaC5hexT5yRW9tznBJ802PSzVNm7u8Po4r/OOtGdC3El8ddyQIAd/5TpzHoh5OPhvPKxb0p0A9EbzpwWOZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79e58a655f13b8af1d5befc15e2cff008a40e5fb0ca678ad533419f8219fea2e","last_reissued_at":"2026-07-07T02:19:04.501932Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:04.501932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04233","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":"2026-07-07T02:19:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7s7B8bd2Op6Y5gsCytZ+pVcB4xYm/ImTl6zZogL0TQnQ+9j/sU1oU21Jn006qQsCPRDmFwq92Be8DOnEBuDiBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T17:58:08.879154Z"},"content_sha256":"d8fe6b741b41a3eec5738c21dd925d58c8ae2029194e44a6f6fa0f09b12c64c2","schema_version":"1.0","event_id":"sha256:d8fe6b741b41a3eec5738c21dd925d58c8ae2029194e44a6f6fa0f09b12c64c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PHSYUZK7CO4K6HK357AV4LH7AC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified convergence analysis for gradient descent optimization methods in the training of deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Arnulf Jentzen, Shokhrukh Ibragimov","submitted_at":"2026-07-05T11:11:40Z","abstract_excerpt":"Gradient based optimization methods are nowadays the methods of choice for training deep neural networks (DNNs) in artificial intelligence (AI) systems. In practically relevant DNN training problems, one does usually not apply the standard gradient descent (GD) optimization method but instead one employs suitable sophisticated GD optimization methods, which incorporate adaptivity and/or acceleration techniques, such as the famous Adam optimizer. It is a key contribution of this work to provide a general unified convergence analysis for GD optimization methods in the training of DNNs with analy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04233","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/2607.04233/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":"2026-07-07T02:19:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w9bY9Tv1JEjvBPzkGH8GmyArHEunJX0wzRNyZjW+2GvWZyLaxFrOattaSqQvPJilko2lpNZyFpjh1ZemRu/jBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T17:58:08.879544Z"},"content_sha256":"248a87570dffbe5554edf849b3a48e1ac3bfc6069a037f1dc5524a090ba50a5e","schema_version":"1.0","event_id":"sha256:248a87570dffbe5554edf849b3a48e1ac3bfc6069a037f1dc5524a090ba50a5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PHSYUZK7CO4K6HK357AV4LH7AC/bundle.json","state_url":"https://pith.science/pith/PHSYUZK7CO4K6HK357AV4LH7AC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PHSYUZK7CO4K6HK357AV4LH7AC/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":"2026-07-25T17:58:08Z","links":{"resolver":"https://pith.science/pith/PHSYUZK7CO4K6HK357AV4LH7AC","bundle":"https://pith.science/pith/PHSYUZK7CO4K6HK357AV4LH7AC/bundle.json","state":"https://pith.science/pith/PHSYUZK7CO4K6HK357AV4LH7AC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PHSYUZK7CO4K6HK357AV4LH7AC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PHSYUZK7CO4K6HK357AV4LH7AC","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":"1cf9937d03a161b4ff722bb1510815e260b0aad3fc741ec926faa6ce6c6240f6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-07-05T11:11:40Z","title_canon_sha256":"130785652380491a4776f21dca065fb3adf506559ec37da768d8862bc9eb650c"},"schema_version":"1.0","source":{"id":"2607.04233","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04233","created_at":"2026-07-07T02:19:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04233v1","created_at":"2026-07-07T02:19:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04233","created_at":"2026-07-07T02:19:04Z"},{"alias_kind":"pith_short_12","alias_value":"PHSYUZK7CO4K","created_at":"2026-07-07T02:19:04Z"},{"alias_kind":"pith_short_16","alias_value":"PHSYUZK7CO4K6HK3","created_at":"2026-07-07T02:19:04Z"},{"alias_kind":"pith_short_8","alias_value":"PHSYUZK7","created_at":"2026-07-07T02:19:04Z"}],"graph_snapshots":[{"event_id":"sha256:248a87570dffbe5554edf849b3a48e1ac3bfc6069a037f1dc5524a090ba50a5e","target":"graph","created_at":"2026-07-07T02:19:04Z","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/2607.04233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gradient based optimization methods are nowadays the methods of choice for training deep neural networks (DNNs) in artificial intelligence (AI) systems. In practically relevant DNN training problems, one does usually not apply the standard gradient descent (GD) optimization method but instead one employs suitable sophisticated GD optimization methods, which incorporate adaptivity and/or acceleration techniques, such as the famous Adam optimizer. It is a key contribution of this work to provide a general unified convergence analysis for GD optimization methods in the training of DNNs with analy","authors_text":"Arnulf Jentzen, Shokhrukh Ibragimov","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-07-05T11:11:40Z","title":"Unified convergence analysis for gradient descent optimization methods in the training of deep neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04233","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:d8fe6b741b41a3eec5738c21dd925d58c8ae2029194e44a6f6fa0f09b12c64c2","target":"record","created_at":"2026-07-07T02:19:04Z","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":"1cf9937d03a161b4ff722bb1510815e260b0aad3fc741ec926faa6ce6c6240f6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-07-05T11:11:40Z","title_canon_sha256":"130785652380491a4776f21dca065fb3adf506559ec37da768d8862bc9eb650c"},"schema_version":"1.0","source":{"id":"2607.04233","kind":"arxiv","version":1}},"canonical_sha256":"79e58a655f13b8af1d5befc15e2cff008a40e5fb0ca678ad533419f8219fea2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79e58a655f13b8af1d5befc15e2cff008a40e5fb0ca678ad533419f8219fea2e","first_computed_at":"2026-07-07T02:19:04.501932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:04.501932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3CHaC5hexT5yRW9tznBJ802PSzVNm7u8Po4r/OOtGdC3El8ddyQIAd/5TpzHoh5OPhvPKxb0p0A9EbzpwWOZDA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:04.502683Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04233","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8fe6b741b41a3eec5738c21dd925d58c8ae2029194e44a6f6fa0f09b12c64c2","sha256:248a87570dffbe5554edf849b3a48e1ac3bfc6069a037f1dc5524a090ba50a5e"],"state_sha256":"d4356346b6a49e151e7240184e435fd457a89a9c3d050ff44ccf1bd811b73124"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qDHIN9dfNSDJwNEfPO8QYN/GcXOuHVOsooRVOfQxQsHeRdwvMKknDcwgUnIryiNZKGN9DigIwz2AePNIwO3BDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T17:58:08.881675Z","bundle_sha256":"4d40d9234a5e4883e46253adc1a4e70f1eb9ec4eb34eacaebc979ae4670be83e"}}