{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:F3GE7CYO44VKRPJH7UXO5IVFXG","short_pith_number":"pith:F3GE7CYO","schema_version":"1.0","canonical_sha256":"2ecc4f8b0ee72aa8bd27fd2eeea2a5b9bed1ddbd3c7b6bf94a7dd76c8305c7b6","source":{"kind":"arxiv","id":"2111.06636","version":3},"attestation_state":"computed","paper":{"title":"Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heung Yeung Shum, Kwan Ho Ryan Chan, Michael Psenka, Mingyang Li, Pengyuan Zhai, Shengbang Tong, Xiaojun Yuan, Xili Dai, Yaodong Yu, Yi Ma, Ziyang Wu","submitted_at":"2021-11-12T10:06:08Z","abstract_excerpt":"This work proposes a new computational framework for learning a structured generative model for real-world datasets. In particular, we propose to learn a closed-loop transcription between a multi-class multi-dimensional data distribution and a linear discriminative representation (LDR) in the feature space that consists of multiple independent multi-dimensional linear subspaces. In particular, we argue that the optimal encoding and decoding mappings sought can be formulated as the equilibrium point of a two-player minimax game between the encoder and decoder. A natural utility function for thi"},"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":"2111.06636","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-12T10:06:08Z","cross_cats_sorted":[],"title_canon_sha256":"d6f626ac7136e0a56af29ef3c6e33f26c079675fd93eafde9b6532363dcd5105","abstract_canon_sha256":"8ffb8d38a4a59618a98cb678f4a35db1af38467d2c1cf4f34000162c6c8cbd55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:28.411963Z","signature_b64":"Aa1h1GCfI7IatKd2bCDihIBN7k7BtRmDkAsaeybl55CW7/Ae3tbo/+tGcouok3DkEPGawbRdtQeqO2ls5xFmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ecc4f8b0ee72aa8bd27fd2eeea2a5b9bed1ddbd3c7b6bf94a7dd76c8305c7b6","last_reissued_at":"2026-07-05T04:11:28.411436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:28.411436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heung Yeung Shum, Kwan Ho Ryan Chan, Michael Psenka, Mingyang Li, Pengyuan Zhai, Shengbang Tong, Xiaojun Yuan, Xili Dai, Yaodong Yu, Yi Ma, Ziyang Wu","submitted_at":"2021-11-12T10:06:08Z","abstract_excerpt":"This work proposes a new computational framework for learning a structured generative model for real-world datasets. In particular, we propose to learn a closed-loop transcription between a multi-class multi-dimensional data distribution and a linear discriminative representation (LDR) in the feature space that consists of multiple independent multi-dimensional linear subspaces. In particular, we argue that the optimal encoding and decoding mappings sought can be formulated as the equilibrium point of a two-player minimax game between the encoder and decoder. A natural utility function for thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.06636","kind":"arxiv","version":3},"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/2111.06636/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.06636","created_at":"2026-07-05T04:11:28.411489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.06636v3","created_at":"2026-07-05T04:11:28.411489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.06636","created_at":"2026-07-05T04:11:28.411489+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3GE7CYO44VK","created_at":"2026-07-05T04:11:28.411489+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3GE7CYO44VKRPJH","created_at":"2026-07-05T04:11:28.411489+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3GE7CYO","created_at":"2026-07-05T04:11:28.411489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18237","citing_title":"Semantic-based Distributed Learning for Diverse and Discriminative Representations","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F3GE7CYO44VKRPJH7UXO5IVFXG","json":"https://pith.science/pith/F3GE7CYO44VKRPJH7UXO5IVFXG.json","graph_json":"https://pith.science/api/pith-number/F3GE7CYO44VKRPJH7UXO5IVFXG/graph.json","events_json":"https://pith.science/api/pith-number/F3GE7CYO44VKRPJH7UXO5IVFXG/events.json","paper":"https://pith.science/paper/F3GE7CYO"},"agent_actions":{"view_html":"https://pith.science/pith/F3GE7CYO44VKRPJH7UXO5IVFXG","download_json":"https://pith.science/pith/F3GE7CYO44VKRPJH7UXO5IVFXG.json","view_paper":"https://pith.science/paper/F3GE7CYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.06636&json=true","fetch_graph":"https://pith.science/api/pith-number/F3GE7CYO44VKRPJH7UXO5IVFXG/graph.json","fetch_events":"https://pith.science/api/pith-number/F3GE7CYO44VKRPJH7UXO5IVFXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3GE7CYO44VKRPJH7UXO5IVFXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3GE7CYO44VKRPJH7UXO5IVFXG/action/storage_attestation","attest_author":"https://pith.science/pith/F3GE7CYO44VKRPJH7UXO5IVFXG/action/author_attestation","sign_citation":"https://pith.science/pith/F3GE7CYO44VKRPJH7UXO5IVFXG/action/citation_signature","submit_replication":"https://pith.science/pith/F3GE7CYO44VKRPJH7UXO5IVFXG/action/replication_record"}},"created_at":"2026-07-05T04:11:28.411489+00:00","updated_at":"2026-07-05T04:11:28.411489+00:00"}