{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:HPJZE4JSQPJGLLCTVA4H5GCSPI","short_pith_number":"pith:HPJZE4JS","canonical_record":{"source":{"id":"1611.06652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-21T05:15:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a9f93e9229c50cbea81709e2e5484b7ec8278f5c1140085648aeeb5b65016433","abstract_canon_sha256":"f13049bea0e3ac4403e85c8c940599b677388b7a0df534609b597d65aa33a3a7"},"schema_version":"1.0"},"canonical_sha256":"3bd392713283d265ac53a8387e98527a397fc98fbdc9986add33ecdf43071bd4","source":{"kind":"arxiv","id":"1611.06652","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.06652","created_at":"2026-05-18T00:57:33Z"},{"alias_kind":"arxiv_version","alias_value":"1611.06652v1","created_at":"2026-05-18T00:57:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06652","created_at":"2026-05-18T00:57:33Z"},{"alias_kind":"pith_short_12","alias_value":"HPJZE4JSQPJG","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"HPJZE4JSQPJGLLCT","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"HPJZE4JS","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:HPJZE4JSQPJGLLCTVA4H5GCSPI","target":"record","payload":{"canonical_record":{"source":{"id":"1611.06652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-21T05:15:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a9f93e9229c50cbea81709e2e5484b7ec8278f5c1140085648aeeb5b65016433","abstract_canon_sha256":"f13049bea0e3ac4403e85c8c940599b677388b7a0df534609b597d65aa33a3a7"},"schema_version":"1.0"},"canonical_sha256":"3bd392713283d265ac53a8387e98527a397fc98fbdc9986add33ecdf43071bd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:33.279664Z","signature_b64":"so6LS/gMdBgvUZ1mZmlivTeHxAqK2DHWqSPQEsz6TzQUeB+RmVP0zDd8pG36xn45C8o2cdsJq52TWsbGDfFxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bd392713283d265ac53a8387e98527a397fc98fbdc9986add33ecdf43071bd4","last_reissued_at":"2026-05-18T00:57:33.279236Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:33.279236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.06652","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":"2026-05-18T00:57:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M96AenPfxJbJ24hgS+wYS4+dS0xVrqO2q3W+caPIWQUQBB30f/17SU5lcLbd9yCPtO4NrseM5pYqUdFGnTF+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:20:04.117071Z"},"content_sha256":"5019b95ec3023612de6c87d9c797fe556871afa53d2fa0bb0c22e56f4f92dfcc","schema_version":"1.0","event_id":"sha256:5019b95ec3023612de6c87d9c797fe556871afa53d2fa0bb0c22e56f4f92dfcc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:HPJZE4JSQPJGLLCTVA4H5GCSPI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Adaptive Stochastic Optimization Using Random Projections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Brian McWilliams, Gabriel Krummenacher, Joachim M. Buhmann, Nicolai Meinshausen, Yannic Kilcher","submitted_at":"2016-11-21T05:15:50Z","abstract_excerpt":"Adaptive stochastic gradient methods such as AdaGrad have gained popularity in particular for training deep neural networks. The most commonly used and studied variant maintains a diagonal matrix approximation to second order information by accumulating past gradients which are used to tune the step size adaptively. In certain situations the full-matrix variant of AdaGrad is expected to attain better performance, however in high dimensions it is computationally impractical. We present Ada-LR and RadaGrad two computationally efficient approximations to full-matrix AdaGrad based on randomized di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06652","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":""},"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":"2026-05-18T00:57:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z5HGB4s/tfhr18lP0hBCelYj5snZujM280ZmeOzhl5Jix9R5sTFkHofibpMfnyL23KVwh68wOfwwKHH2JAVhBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:20:04.117474Z"},"content_sha256":"2b57551f90557de35a916e1f363eb6346e858cd3a0a24e2e5e36c04d847c0297","schema_version":"1.0","event_id":"sha256:2b57551f90557de35a916e1f363eb6346e858cd3a0a24e2e5e36c04d847c0297"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HPJZE4JSQPJGLLCTVA4H5GCSPI/bundle.json","state_url":"https://pith.science/pith/HPJZE4JSQPJGLLCTVA4H5GCSPI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HPJZE4JSQPJGLLCTVA4H5GCSPI/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":"2026-05-29T19:20:04Z","links":{"resolver":"https://pith.science/pith/HPJZE4JSQPJGLLCTVA4H5GCSPI","bundle":"https://pith.science/pith/HPJZE4JSQPJGLLCTVA4H5GCSPI/bundle.json","state":"https://pith.science/pith/HPJZE4JSQPJGLLCTVA4H5GCSPI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HPJZE4JSQPJGLLCTVA4H5GCSPI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:HPJZE4JSQPJGLLCTVA4H5GCSPI","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":"f13049bea0e3ac4403e85c8c940599b677388b7a0df534609b597d65aa33a3a7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-21T05:15:50Z","title_canon_sha256":"a9f93e9229c50cbea81709e2e5484b7ec8278f5c1140085648aeeb5b65016433"},"schema_version":"1.0","source":{"id":"1611.06652","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.06652","created_at":"2026-05-18T00:57:33Z"},{"alias_kind":"arxiv_version","alias_value":"1611.06652v1","created_at":"2026-05-18T00:57:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06652","created_at":"2026-05-18T00:57:33Z"},{"alias_kind":"pith_short_12","alias_value":"HPJZE4JSQPJG","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"HPJZE4JSQPJGLLCT","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"HPJZE4JS","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:2b57551f90557de35a916e1f363eb6346e858cd3a0a24e2e5e36c04d847c0297","target":"graph","created_at":"2026-05-18T00:57:33Z","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"},"paper":{"abstract_excerpt":"Adaptive stochastic gradient methods such as AdaGrad have gained popularity in particular for training deep neural networks. The most commonly used and studied variant maintains a diagonal matrix approximation to second order information by accumulating past gradients which are used to tune the step size adaptively. In certain situations the full-matrix variant of AdaGrad is expected to attain better performance, however in high dimensions it is computationally impractical. We present Ada-LR and RadaGrad two computationally efficient approximations to full-matrix AdaGrad based on randomized di","authors_text":"Brian McWilliams, Gabriel Krummenacher, Joachim M. Buhmann, Nicolai Meinshausen, Yannic Kilcher","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-21T05:15:50Z","title":"Scalable Adaptive Stochastic Optimization Using Random Projections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06652","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":"sha256:5019b95ec3023612de6c87d9c797fe556871afa53d2fa0bb0c22e56f4f92dfcc","target":"record","created_at":"2026-05-18T00:57:33Z","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":"f13049bea0e3ac4403e85c8c940599b677388b7a0df534609b597d65aa33a3a7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-21T05:15:50Z","title_canon_sha256":"a9f93e9229c50cbea81709e2e5484b7ec8278f5c1140085648aeeb5b65016433"},"schema_version":"1.0","source":{"id":"1611.06652","kind":"arxiv","version":1}},"canonical_sha256":"3bd392713283d265ac53a8387e98527a397fc98fbdc9986add33ecdf43071bd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bd392713283d265ac53a8387e98527a397fc98fbdc9986add33ecdf43071bd4","first_computed_at":"2026-05-18T00:57:33.279236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:57:33.279236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"so6LS/gMdBgvUZ1mZmlivTeHxAqK2DHWqSPQEsz6TzQUeB+RmVP0zDd8pG36xn45C8o2cdsJq52TWsbGDfFxDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:57:33.279664Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.06652","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5019b95ec3023612de6c87d9c797fe556871afa53d2fa0bb0c22e56f4f92dfcc","sha256:2b57551f90557de35a916e1f363eb6346e858cd3a0a24e2e5e36c04d847c0297"],"state_sha256":"4ce4b68d40299a2758a33cacf031bbf07ad9607e8a65c81a74d6c7f678c1479d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"prlanYz1BA41hgV766VAlTadPP1M0dh2OKFLC0Huaq1zRrz2rJD4Ej8G/A251Mqaoun8YHC9qzwOg4aZwXybAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T19:20:04.121189Z","bundle_sha256":"a8912e726de7a541727c19246de7ef502493ed9b80bbc2fd7c4bfc83fd611895"}}