{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PZLU33YBBJZAP3WYJIK6L2OB5F","short_pith_number":"pith:PZLU33YB","canonical_record":{"source":{"id":"1803.02865","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-07T20:30:35Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NA","math.NA","math.OC"],"title_canon_sha256":"d2aad522be117678a23dafac981996374666a1f24d1a2461b25783b2e3d917d0","abstract_canon_sha256":"31c206f18231217c9ae9b228895c1395aea4d5b06100e00f99e27078d0ab50b1"},"schema_version":"1.0"},"canonical_sha256":"7e574def010a7207eed84a15e5e9c1e95e6c17bccf49d09ef2c85b4bb02f0b95","source":{"kind":"arxiv","id":"1803.02865","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.02865","created_at":"2026-07-05T01:53:05Z"},{"alias_kind":"arxiv_version","alias_value":"1803.02865v2","created_at":"2026-07-05T01:53:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.02865","created_at":"2026-07-05T01:53:05Z"},{"alias_kind":"pith_short_12","alias_value":"PZLU33YBBJZA","created_at":"2026-07-05T01:53:05Z"},{"alias_kind":"pith_short_16","alias_value":"PZLU33YBBJZAP3WY","created_at":"2026-07-05T01:53:05Z"},{"alias_kind":"pith_short_8","alias_value":"PZLU33YB","created_at":"2026-07-05T01:53:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PZLU33YBBJZAP3WYJIK6L2OB5F","target":"record","payload":{"canonical_record":{"source":{"id":"1803.02865","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-07T20:30:35Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NA","math.NA","math.OC"],"title_canon_sha256":"d2aad522be117678a23dafac981996374666a1f24d1a2461b25783b2e3d917d0","abstract_canon_sha256":"31c206f18231217c9ae9b228895c1395aea4d5b06100e00f99e27078d0ab50b1"},"schema_version":"1.0"},"canonical_sha256":"7e574def010a7207eed84a15e5e9c1e95e6c17bccf49d09ef2c85b4bb02f0b95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:05.629600Z","signature_b64":"fHoQ1msP2FoBGR1L4SV7+20UNqflCx20OURwobqIv7s+rmIocNi0EIdiEzSLvd16c57A/gjpY1XTDbWeAFxUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e574def010a7207eed84a15e5e9c1e95e6c17bccf49d09ef2c85b4bb02f0b95","last_reissued_at":"2026-07-05T01:53:05.629167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:05.629167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.02865","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":"2026-07-05T01:53:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2J0xxaioUazGMAAF4uHwlxx+FN/WpQY4tqk2BjzXWXcl1PC+v0QNCTgccH/2r/FtdQT8BnEDbZ4PXfSlDLi7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:02:29.695250Z"},"content_sha256":"94b4627cf72a02199ad4e71c34f88d0f607fc8bd0874a91cb97c6fd78da2d8b4","schema_version":"1.0","event_id":"sha256:94b4627cf72a02199ad4e71c34f88d0f607fc8bd0874a91cb97c6fd78da2d8b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PZLU33YBBJZAP3WYJIK6L2OB5F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WNGrad: Learn the Learning Rate in Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NA","math.NA","math.OC"],"primary_cat":"stat.ML","authors_text":"L\\'eon Bottou, Rachel Ward, Xiaoxia Wu","submitted_at":"2018-03-07T20:30:35Z","abstract_excerpt":"Adjusting the learning rate schedule in stochastic gradient methods is an important unresolved problem which requires tuning in practice. If certain parameters of the loss function such as smoothness or strong convexity constants are known, theoretical learning rate schedules can be applied. However, in practice, such parameters are not known, and the loss function of interest is not convex in any case. The recently proposed batch normalization reparametrization is widely adopted in most neural network architectures today because, among other advantages, it is robust to the choice of Lipschitz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.02865","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/1803.02865/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":"2026-07-05T01:53:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yvJ1wWkGAvy4TSg0TL9ZjKogzBeQrYWeNFouWNtxjIc6A9l4k3pdXvwh4LMufi7qrVhlLh3Q2BdBBkqw5rYWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:02:29.695746Z"},"content_sha256":"bc0bf7b1c2140639691a17c9043d32e32dc4fb290efaeae0635ed31294b19af7","schema_version":"1.0","event_id":"sha256:bc0bf7b1c2140639691a17c9043d32e32dc4fb290efaeae0635ed31294b19af7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PZLU33YBBJZAP3WYJIK6L2OB5F/bundle.json","state_url":"https://pith.science/pith/PZLU33YBBJZAP3WYJIK6L2OB5F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PZLU33YBBJZAP3WYJIK6L2OB5F/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":"2026-08-09T19:02:29Z","links":{"resolver":"https://pith.science/pith/PZLU33YBBJZAP3WYJIK6L2OB5F","bundle":"https://pith.science/pith/PZLU33YBBJZAP3WYJIK6L2OB5F/bundle.json","state":"https://pith.science/pith/PZLU33YBBJZAP3WYJIK6L2OB5F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PZLU33YBBJZAP3WYJIK6L2OB5F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PZLU33YBBJZAP3WYJIK6L2OB5F","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":"31c206f18231217c9ae9b228895c1395aea4d5b06100e00f99e27078d0ab50b1","cross_cats_sorted":["cs.AI","cs.LG","cs.NA","math.NA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-07T20:30:35Z","title_canon_sha256":"d2aad522be117678a23dafac981996374666a1f24d1a2461b25783b2e3d917d0"},"schema_version":"1.0","source":{"id":"1803.02865","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.02865","created_at":"2026-07-05T01:53:05Z"},{"alias_kind":"arxiv_version","alias_value":"1803.02865v2","created_at":"2026-07-05T01:53:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.02865","created_at":"2026-07-05T01:53:05Z"},{"alias_kind":"pith_short_12","alias_value":"PZLU33YBBJZA","created_at":"2026-07-05T01:53:05Z"},{"alias_kind":"pith_short_16","alias_value":"PZLU33YBBJZAP3WY","created_at":"2026-07-05T01:53:05Z"},{"alias_kind":"pith_short_8","alias_value":"PZLU33YB","created_at":"2026-07-05T01:53:05Z"}],"graph_snapshots":[{"event_id":"sha256:bc0bf7b1c2140639691a17c9043d32e32dc4fb290efaeae0635ed31294b19af7","target":"graph","created_at":"2026-07-05T01:53:05Z","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/1803.02865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adjusting the learning rate schedule in stochastic gradient methods is an important unresolved problem which requires tuning in practice. If certain parameters of the loss function such as smoothness or strong convexity constants are known, theoretical learning rate schedules can be applied. However, in practice, such parameters are not known, and the loss function of interest is not convex in any case. The recently proposed batch normalization reparametrization is widely adopted in most neural network architectures today because, among other advantages, it is robust to the choice of Lipschitz","authors_text":"L\\'eon Bottou, Rachel Ward, Xiaoxia Wu","cross_cats":["cs.AI","cs.LG","cs.NA","math.NA","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-07T20:30:35Z","title":"WNGrad: Learn the Learning Rate in Gradient Descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.02865","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":"sha256:94b4627cf72a02199ad4e71c34f88d0f607fc8bd0874a91cb97c6fd78da2d8b4","target":"record","created_at":"2026-07-05T01:53:05Z","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":"31c206f18231217c9ae9b228895c1395aea4d5b06100e00f99e27078d0ab50b1","cross_cats_sorted":["cs.AI","cs.LG","cs.NA","math.NA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-07T20:30:35Z","title_canon_sha256":"d2aad522be117678a23dafac981996374666a1f24d1a2461b25783b2e3d917d0"},"schema_version":"1.0","source":{"id":"1803.02865","kind":"arxiv","version":2}},"canonical_sha256":"7e574def010a7207eed84a15e5e9c1e95e6c17bccf49d09ef2c85b4bb02f0b95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e574def010a7207eed84a15e5e9c1e95e6c17bccf49d09ef2c85b4bb02f0b95","first_computed_at":"2026-07-05T01:53:05.629167Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:05.629167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fHoQ1msP2FoBGR1L4SV7+20UNqflCx20OURwobqIv7s+rmIocNi0EIdiEzSLvd16c57A/gjpY1XTDbWeAFxUBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:05.629600Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.02865","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94b4627cf72a02199ad4e71c34f88d0f607fc8bd0874a91cb97c6fd78da2d8b4","sha256:bc0bf7b1c2140639691a17c9043d32e32dc4fb290efaeae0635ed31294b19af7"],"state_sha256":"b7ddbcb40380907a8fca8c70fc6987eb0023ebc438cf91d9cc869150501b7ad4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ApspzTZbFu/Ip6ykOj+/cuejASuntsq5UcbP/f5ccIN6obX/P5q19lGvqaERtOCalwZ/eYgBf+gTC1GBkK4wCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:02:29.699604Z","bundle_sha256":"b1dc37ef36fa63c3ac8b46ddab2e46c52b8ec6285adf5cdc41600b9d3c9045df"}}