{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:K7WNPB4J6IC5KJQG6YCC2B3B3Z","short_pith_number":"pith:K7WNPB4J","canonical_record":{"source":{"id":"1510.02054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-07T18:32:41Z","cross_cats_sorted":[],"title_canon_sha256":"ee8fda690f9862a78b9c8ca0b923128168db5ddb92ed73da04db6113edd0e9c1","abstract_canon_sha256":"551805946f97135411afa78afd7a2c184415bd9c12761ee21707282efb588181"},"schema_version":"1.0"},"canonical_sha256":"57ecd78789f205d52606f6042d0761de5f26a2a925e88d1161e939390aadbe95","source":{"kind":"arxiv","id":"1510.02054","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.02054","created_at":"2026-05-18T01:30:49Z"},{"alias_kind":"arxiv_version","alias_value":"1510.02054v1","created_at":"2026-05-18T01:30:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.02054","created_at":"2026-05-18T01:30:49Z"},{"alias_kind":"pith_short_12","alias_value":"K7WNPB4J6IC5","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"K7WNPB4J6IC5KJQG","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"K7WNPB4J","created_at":"2026-05-18T12:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:K7WNPB4J6IC5KJQG6YCC2B3B3Z","target":"record","payload":{"canonical_record":{"source":{"id":"1510.02054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-07T18:32:41Z","cross_cats_sorted":[],"title_canon_sha256":"ee8fda690f9862a78b9c8ca0b923128168db5ddb92ed73da04db6113edd0e9c1","abstract_canon_sha256":"551805946f97135411afa78afd7a2c184415bd9c12761ee21707282efb588181"},"schema_version":"1.0"},"canonical_sha256":"57ecd78789f205d52606f6042d0761de5f26a2a925e88d1161e939390aadbe95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:30:49.787334Z","signature_b64":"C/8pTpY8q8Ze5LVkhp+APoc+bSGY5H/PSoo+ImNtPOL6sXJrhHiJ0dSnITWIoiGilJC/ALDYN6cc2L8DWUBJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57ecd78789f205d52606f6042d0761de5f26a2a925e88d1161e939390aadbe95","last_reissued_at":"2026-05-18T01:30:49.786829Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:30:49.786829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1510.02054","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":"2026-05-18T01:30:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q8VfxB4aCpDTxWlg4LixiWBIuELIcVWK2Rmr/CHjdNVCRVl4guqkamUGNMBnFWsRWVGNXJiWMKrMtaD+D7WoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:39:39.652026Z"},"content_sha256":"b73d1ee3af562bebb48daeb7bda1b275cca6fe2e7f41c89bb9e376175278e1d2","schema_version":"1.0","event_id":"sha256:b73d1ee3af562bebb48daeb7bda1b275cca6fe2e7f41c89bb9e376175278e1d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:K7WNPB4J6IC5KJQG6YCC2B3B3Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Optimization for Deep CCA via Nonlinear Orthogonal Iterations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Karen Livescu, Nathan Srebro, Raman Arora, Weiran Wang","submitted_at":"2015-10-07T18:32:41Z","abstract_excerpt":"Deep CCA is a recently proposed deep neural network extension to the traditional canonical correlation analysis (CCA), and has been successful for multi-view representation learning in several domains. However, stochastic optimization of the deep CCA objective is not straightforward, because it does not decouple over training examples. Previous optimizers for deep CCA are either batch-based algorithms or stochastic optimization using large minibatches, which can have high memory consumption. In this paper, we tackle the problem of stochastic optimization for deep CCA with small minibatches, ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.02054","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":"2026-05-18T01:30:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+fJeYwD/oGx0967I++mL5mpV+JJVaZPuNfSkGk0xlIESVbMZ4b2enYT2sG+f05WRthcLv+x2wmVUtHJ+hrAkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:39:39.652383Z"},"content_sha256":"2738a641f4bf9c580076263632bf8b9fed76c8748b7c5cbe321d497437d65efe","schema_version":"1.0","event_id":"sha256:2738a641f4bf9c580076263632bf8b9fed76c8748b7c5cbe321d497437d65efe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K7WNPB4J6IC5KJQG6YCC2B3B3Z/bundle.json","state_url":"https://pith.science/pith/K7WNPB4J6IC5KJQG6YCC2B3B3Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K7WNPB4J6IC5KJQG6YCC2B3B3Z/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":"2026-05-27T05:39:39Z","links":{"resolver":"https://pith.science/pith/K7WNPB4J6IC5KJQG6YCC2B3B3Z","bundle":"https://pith.science/pith/K7WNPB4J6IC5KJQG6YCC2B3B3Z/bundle.json","state":"https://pith.science/pith/K7WNPB4J6IC5KJQG6YCC2B3B3Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K7WNPB4J6IC5KJQG6YCC2B3B3Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:K7WNPB4J6IC5KJQG6YCC2B3B3Z","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":"551805946f97135411afa78afd7a2c184415bd9c12761ee21707282efb588181","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-07T18:32:41Z","title_canon_sha256":"ee8fda690f9862a78b9c8ca0b923128168db5ddb92ed73da04db6113edd0e9c1"},"schema_version":"1.0","source":{"id":"1510.02054","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.02054","created_at":"2026-05-18T01:30:49Z"},{"alias_kind":"arxiv_version","alias_value":"1510.02054v1","created_at":"2026-05-18T01:30:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.02054","created_at":"2026-05-18T01:30:49Z"},{"alias_kind":"pith_short_12","alias_value":"K7WNPB4J6IC5","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"K7WNPB4J6IC5KJQG","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"K7WNPB4J","created_at":"2026-05-18T12:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:2738a641f4bf9c580076263632bf8b9fed76c8748b7c5cbe321d497437d65efe","target":"graph","created_at":"2026-05-18T01:30:49Z","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":"Deep CCA is a recently proposed deep neural network extension to the traditional canonical correlation analysis (CCA), and has been successful for multi-view representation learning in several domains. However, stochastic optimization of the deep CCA objective is not straightforward, because it does not decouple over training examples. Previous optimizers for deep CCA are either batch-based algorithms or stochastic optimization using large minibatches, which can have high memory consumption. In this paper, we tackle the problem of stochastic optimization for deep CCA with small minibatches, ba","authors_text":"Karen Livescu, Nathan Srebro, Raman Arora, Weiran Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-07T18:32:41Z","title":"Stochastic Optimization for Deep CCA via Nonlinear Orthogonal Iterations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.02054","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:b73d1ee3af562bebb48daeb7bda1b275cca6fe2e7f41c89bb9e376175278e1d2","target":"record","created_at":"2026-05-18T01:30:49Z","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":"551805946f97135411afa78afd7a2c184415bd9c12761ee21707282efb588181","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-07T18:32:41Z","title_canon_sha256":"ee8fda690f9862a78b9c8ca0b923128168db5ddb92ed73da04db6113edd0e9c1"},"schema_version":"1.0","source":{"id":"1510.02054","kind":"arxiv","version":1}},"canonical_sha256":"57ecd78789f205d52606f6042d0761de5f26a2a925e88d1161e939390aadbe95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57ecd78789f205d52606f6042d0761de5f26a2a925e88d1161e939390aadbe95","first_computed_at":"2026-05-18T01:30:49.786829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:30:49.786829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C/8pTpY8q8Ze5LVkhp+APoc+bSGY5H/PSoo+ImNtPOL6sXJrhHiJ0dSnITWIoiGilJC/ALDYN6cc2L8DWUBJBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:30:49.787334Z","signed_message":"canonical_sha256_bytes"},"source_id":"1510.02054","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b73d1ee3af562bebb48daeb7bda1b275cca6fe2e7f41c89bb9e376175278e1d2","sha256:2738a641f4bf9c580076263632bf8b9fed76c8748b7c5cbe321d497437d65efe"],"state_sha256":"eff7ac9abe9b1dd601c85f8348941a39c22772a63674d631040f8296857dc8fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pLPutEcukV29Nu4CC8enFn4b4grLi9pHhVlIPGZCekH6aNeqLFlqFqNjD2moyX0DsSOrdPHuVpVWQweXXq00Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T05:39:39.655051Z","bundle_sha256":"78094b1359843b3fd79a1b1856618601fe075c7dba5276b0f64d1cde22515024"}}