{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:CTCXFY3RLTQLPGOHEG7ZVYJ7AS","short_pith_number":"pith:CTCXFY3R","canonical_record":{"source":{"id":"1502.06626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-23T21:06:39Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.CO","stat.ML"],"title_canon_sha256":"b27d7a4bfc913d3bd3f8476474770a9e27f79cc21d9a8048ea4b17d70efadc7b","abstract_canon_sha256":"c0ac3d0c56d831fbf12ec7e20fb0380558b49027a9cf73926d936252afc445c9"},"schema_version":"1.0"},"canonical_sha256":"14c572e3715ce0b799c721bf9ae13f04b7db8970459ab3ebc609bc3c15e0c8da","source":{"kind":"arxiv","id":"1502.06626","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.06626","created_at":"2026-05-18T02:26:29Z"},{"alias_kind":"arxiv_version","alias_value":"1502.06626v1","created_at":"2026-05-18T02:26:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.06626","created_at":"2026-05-18T02:26:29Z"},{"alias_kind":"pith_short_12","alias_value":"CTCXFY3RLTQL","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"CTCXFY3RLTQLPGOH","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"CTCXFY3R","created_at":"2026-05-18T12:29:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:CTCXFY3RLTQLPGOHEG7ZVYJ7AS","target":"record","payload":{"canonical_record":{"source":{"id":"1502.06626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-23T21:06:39Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.CO","stat.ML"],"title_canon_sha256":"b27d7a4bfc913d3bd3f8476474770a9e27f79cc21d9a8048ea4b17d70efadc7b","abstract_canon_sha256":"c0ac3d0c56d831fbf12ec7e20fb0380558b49027a9cf73926d936252afc445c9"},"schema_version":"1.0"},"canonical_sha256":"14c572e3715ce0b799c721bf9ae13f04b7db8970459ab3ebc609bc3c15e0c8da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:26:29.602698Z","signature_b64":"k3bJSBrai3KgeoSwb5mQQUTKEkE/dvuR/aCfI4U4eUXZqFQNu6NSq6FH18RhGH9IdaeCv0lYlBE+y/p1Lf9XAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14c572e3715ce0b799c721bf9ae13f04b7db8970459ab3ebc609bc3c15e0c8da","last_reissued_at":"2026-05-18T02:26:29.602232Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:26:29.602232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1502.06626","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":"2026-05-18T02:26:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PIl59zPDVaRiAt3/iUSiBtTNLDMRgTXCaDsbtzSNs0ce2eOGr6nW3VDEWkCYKFA9RzF1L7ehu6g1HaIer6X4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:25:24.236659Z"},"content_sha256":"b2c5a3af9d7332dfb1433aa90f71b3d229ce135b8a2f181699e4e92bf309f092","schema_version":"1.0","event_id":"sha256:b2c5a3af9d7332dfb1433aa90f71b3d229ce135b8a2f181699e4e92bf309f092"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:CTCXFY3RLTQLPGOHEG7ZVYJ7AS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Sparse Linear Auto-Encoders and Sparse PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christos Boutsidis, Malik Magdon-Ismail","submitted_at":"2015-02-23T21:06:39Z","abstract_excerpt":"Principal components analysis (PCA) is the optimal linear auto-encoder of data, and it is often used to construct features. Enforcing sparsity on the principal components can promote better generalization, while improving the interpretability of the features. We study the problem of constructing optimal sparse linear auto-encoders. Two natural questions in such a setting are: i) Given a level of sparsity, what is the best approximation to PCA that can be achieved? ii) Are there low-order polynomial-time algorithms which can asymptotically achieve this optimal tradeoff between the sparsity and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.06626","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":"2026-05-18T02:26:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/nSY5dOwtRqtbjocoF3NzPPzpRBr7nhbyrmuCMBrBn2mUqhbgxJNvunOgCbRmHSlFu44IFfUdzb+3tdIuVssBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:25:24.237370Z"},"content_sha256":"34b6e6d2d4fd0f9173bab8e45e9d88f7d9a9869918bf6919192b5252e234210a","schema_version":"1.0","event_id":"sha256:34b6e6d2d4fd0f9173bab8e45e9d88f7d9a9869918bf6919192b5252e234210a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CTCXFY3RLTQLPGOHEG7ZVYJ7AS/bundle.json","state_url":"https://pith.science/pith/CTCXFY3RLTQLPGOHEG7ZVYJ7AS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CTCXFY3RLTQLPGOHEG7ZVYJ7AS/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":"2026-05-25T18:25:24Z","links":{"resolver":"https://pith.science/pith/CTCXFY3RLTQLPGOHEG7ZVYJ7AS","bundle":"https://pith.science/pith/CTCXFY3RLTQLPGOHEG7ZVYJ7AS/bundle.json","state":"https://pith.science/pith/CTCXFY3RLTQLPGOHEG7ZVYJ7AS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CTCXFY3RLTQLPGOHEG7ZVYJ7AS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:CTCXFY3RLTQLPGOHEG7ZVYJ7AS","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":"c0ac3d0c56d831fbf12ec7e20fb0380558b49027a9cf73926d936252afc445c9","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.CO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-23T21:06:39Z","title_canon_sha256":"b27d7a4bfc913d3bd3f8476474770a9e27f79cc21d9a8048ea4b17d70efadc7b"},"schema_version":"1.0","source":{"id":"1502.06626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.06626","created_at":"2026-05-18T02:26:29Z"},{"alias_kind":"arxiv_version","alias_value":"1502.06626v1","created_at":"2026-05-18T02:26:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.06626","created_at":"2026-05-18T02:26:29Z"},{"alias_kind":"pith_short_12","alias_value":"CTCXFY3RLTQL","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"CTCXFY3RLTQLPGOH","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"CTCXFY3R","created_at":"2026-05-18T12:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:34b6e6d2d4fd0f9173bab8e45e9d88f7d9a9869918bf6919192b5252e234210a","target":"graph","created_at":"2026-05-18T02:26:29Z","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":"Principal components analysis (PCA) is the optimal linear auto-encoder of data, and it is often used to construct features. Enforcing sparsity on the principal components can promote better generalization, while improving the interpretability of the features. We study the problem of constructing optimal sparse linear auto-encoders. Two natural questions in such a setting are: i) Given a level of sparsity, what is the best approximation to PCA that can be achieved? ii) Are there low-order polynomial-time algorithms which can asymptotically achieve this optimal tradeoff between the sparsity and ","authors_text":"Christos Boutsidis, Malik Magdon-Ismail","cross_cats":["cs.AI","cs.IT","math.IT","stat.CO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-23T21:06:39Z","title":"Optimal Sparse Linear Auto-Encoders and Sparse PCA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.06626","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:b2c5a3af9d7332dfb1433aa90f71b3d229ce135b8a2f181699e4e92bf309f092","target":"record","created_at":"2026-05-18T02:26:29Z","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":"c0ac3d0c56d831fbf12ec7e20fb0380558b49027a9cf73926d936252afc445c9","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.CO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-23T21:06:39Z","title_canon_sha256":"b27d7a4bfc913d3bd3f8476474770a9e27f79cc21d9a8048ea4b17d70efadc7b"},"schema_version":"1.0","source":{"id":"1502.06626","kind":"arxiv","version":1}},"canonical_sha256":"14c572e3715ce0b799c721bf9ae13f04b7db8970459ab3ebc609bc3c15e0c8da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14c572e3715ce0b799c721bf9ae13f04b7db8970459ab3ebc609bc3c15e0c8da","first_computed_at":"2026-05-18T02:26:29.602232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:26:29.602232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k3bJSBrai3KgeoSwb5mQQUTKEkE/dvuR/aCfI4U4eUXZqFQNu6NSq6FH18RhGH9IdaeCv0lYlBE+y/p1Lf9XAw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:26:29.602698Z","signed_message":"canonical_sha256_bytes"},"source_id":"1502.06626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2c5a3af9d7332dfb1433aa90f71b3d229ce135b8a2f181699e4e92bf309f092","sha256:34b6e6d2d4fd0f9173bab8e45e9d88f7d9a9869918bf6919192b5252e234210a"],"state_sha256":"ff9ab982a847c21b748d0e82b9e31eba650913039c2cc450cc87f25b9132d6dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WZmO/lhojaDLmVWJRLlXaB2T5t7EvE93foOpOCxJ+UF98xUIZNnJAfMGKayb7VvCdDk0u64SlQU6J/rzwTwcCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:25:24.241237Z","bundle_sha256":"50d731465dbbdb4ddc33f2419d821f6a06a47ce8f1b4c8ba4d04ddb86381258e"}}