{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6BMREFMZWELP2RB3E5YAH46FID","short_pith_number":"pith:6BMREFMZ","schema_version":"1.0","canonical_sha256":"f059121599b116fd443b277003f3c540e47aab5469a19b22ec183d623116c4a6","source":{"kind":"arxiv","id":"1707.09669","version":2},"attestation_state":"computed","paper":{"title":"Scalable and Effective Deep CCA via Soft Decorrelation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tao Xiang, Timothy M. Hospedales, Xiaobin Chang","submitted_at":"2017-07-30T20:53:54Z","abstract_excerpt":"Recently the widely used multi-view learning model, Canonical Correlation Analysis (CCA) has been generalised to the non-linear setting via deep neural networks. Existing deep CCA models typically first decorrelate the feature dimensions of each view before the different views are maximally correlated in a common latent space. This feature decorrelation is achieved by enforcing an exact decorrelation constraint; these models are thus computationally expensive due to the matrix inversion or SVD operations required for exact decorrelation at each training iteration. Furthermore, the decorrelatio"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1707.09669","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-30T20:53:54Z","cross_cats_sorted":[],"title_canon_sha256":"1ab97d4c7b757ef0a8d7639f9eee36b1d8e6f9cb1684b3b27d40b1a545bb17b4","abstract_canon_sha256":"373c3a3df581ea2b36ea94798cda5b8469029226482b2f69838f2d8681c5fd09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:16.916546Z","signature_b64":"WY1uNT+/uIxtczIn757BMhqwPhpcIVSSRjhr1WRcHJqK0ZF2od/ZhEw5po3aD3TmLfH/aluYIgi/QOW60DejCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f059121599b116fd443b277003f3c540e47aab5469a19b22ec183d623116c4a6","last_reissued_at":"2026-05-18T00:20:16.916008Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:16.916008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable and Effective Deep CCA via Soft Decorrelation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tao Xiang, Timothy M. Hospedales, Xiaobin Chang","submitted_at":"2017-07-30T20:53:54Z","abstract_excerpt":"Recently the widely used multi-view learning model, Canonical Correlation Analysis (CCA) has been generalised to the non-linear setting via deep neural networks. Existing deep CCA models typically first decorrelate the feature dimensions of each view before the different views are maximally correlated in a common latent space. This feature decorrelation is achieved by enforcing an exact decorrelation constraint; these models are thus computationally expensive due to the matrix inversion or SVD operations required for exact decorrelation at each training iteration. Furthermore, the decorrelatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09669","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1707.09669","created_at":"2026-05-18T00:20:16.916091+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.09669v2","created_at":"2026-05-18T00:20:16.916091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09669","created_at":"2026-05-18T00:20:16.916091+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BMREFMZWELP","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BMREFMZWELP2RB3","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BMREFMZ","created_at":"2026-05-18T12:31:03.183658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BMREFMZWELP2RB3E5YAH46FID","json":"https://pith.science/pith/6BMREFMZWELP2RB3E5YAH46FID.json","graph_json":"https://pith.science/api/pith-number/6BMREFMZWELP2RB3E5YAH46FID/graph.json","events_json":"https://pith.science/api/pith-number/6BMREFMZWELP2RB3E5YAH46FID/events.json","paper":"https://pith.science/paper/6BMREFMZ"},"agent_actions":{"view_html":"https://pith.science/pith/6BMREFMZWELP2RB3E5YAH46FID","download_json":"https://pith.science/pith/6BMREFMZWELP2RB3E5YAH46FID.json","view_paper":"https://pith.science/paper/6BMREFMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.09669&json=true","fetch_graph":"https://pith.science/api/pith-number/6BMREFMZWELP2RB3E5YAH46FID/graph.json","fetch_events":"https://pith.science/api/pith-number/6BMREFMZWELP2RB3E5YAH46FID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BMREFMZWELP2RB3E5YAH46FID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BMREFMZWELP2RB3E5YAH46FID/action/storage_attestation","attest_author":"https://pith.science/pith/6BMREFMZWELP2RB3E5YAH46FID/action/author_attestation","sign_citation":"https://pith.science/pith/6BMREFMZWELP2RB3E5YAH46FID/action/citation_signature","submit_replication":"https://pith.science/pith/6BMREFMZWELP2RB3E5YAH46FID/action/replication_record"}},"created_at":"2026-05-18T00:20:16.916091+00:00","updated_at":"2026-05-18T00:20:16.916091+00:00"}