{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DX5Z5HHFGDEDG3QOU3PQ3ERBA2","short_pith_number":"pith:DX5Z5HHF","canonical_record":{"source":{"id":"1806.10175","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-26T19:11:22Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"5ec932c0840006f63938add1fe61c5848ba58df5df81b782c18f1cffe2c7240a","abstract_canon_sha256":"b062d4e8c87e050463bbdc48565f2f7efd6ada8d665477837dd837ec841752e0"},"schema_version":"1.0"},"canonical_sha256":"1dfb9e9ce530c8336e0ea6df0d92210690a3ac43c4fbbd86e0d4ef21a03f5e31","source":{"kind":"arxiv","id":"1806.10175","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.10175","created_at":"2026-05-17T23:41:46Z"},{"alias_kind":"arxiv_version","alias_value":"1806.10175v4","created_at":"2026-05-17T23:41:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.10175","created_at":"2026-05-17T23:41:46Z"},{"alias_kind":"pith_short_12","alias_value":"DX5Z5HHFGDED","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DX5Z5HHFGDEDG3QO","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DX5Z5HHF","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DX5Z5HHFGDEDG3QOU3PQ3ERBA2","target":"record","payload":{"canonical_record":{"source":{"id":"1806.10175","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-26T19:11:22Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"5ec932c0840006f63938add1fe61c5848ba58df5df81b782c18f1cffe2c7240a","abstract_canon_sha256":"b062d4e8c87e050463bbdc48565f2f7efd6ada8d665477837dd837ec841752e0"},"schema_version":"1.0"},"canonical_sha256":"1dfb9e9ce530c8336e0ea6df0d92210690a3ac43c4fbbd86e0d4ef21a03f5e31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:46.433042Z","signature_b64":"ILfhhn/BkrUUqDcPfrlUgGMwx0Aj+yZEUdVg6QlU8BQDv8Xsk8h4lVOSrdlCRV1wR1V1/PBoukrvcJhhcRIBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dfb9e9ce530c8336e0ea6df0d92210690a3ac43c4fbbd86e0d4ef21a03f5e31","last_reissued_at":"2026-05-17T23:41:46.432225Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:46.432225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.10175","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CtDO/opm0IBJjWplEIvK5NnsjH+KSXZB9fcSh7lH8UkhGbADX+uIHkJab8ZsiKRgVcbPmtBINkZy8BWtg1w9AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:13:50.138542Z"},"content_sha256":"707f295dc6bfa54e8e28bb18f31dfe448868b5b34508028500f961f61db91c2e","schema_version":"1.0","event_id":"sha256:707f295dc6bfa54e8e28bb18f31dfe448868b5b34508028500f961f61db91c2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DX5Z5HHFGDEDG3QOU3PQ3ERBA2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Afshin Rostamizadeh, Alexandros G. Dimakis, Daniel Holtmann-Rice, Dmitry Storcheus, Felix X. Yu, Sanjiv Kumar, Shanshan Wu, Sujay Sanghavi","submitted_at":"2018-06-26T19:11:22Z","abstract_excerpt":"Linear encoding of sparse vectors is widely popular, but is commonly data-independent -- missing any possible extra (but a priori unknown) structure beyond sparsity. In this paper we present a new method to learn linear encoders that adapt to data, while still performing well with the widely used $\\ell_1$ decoder. The convex $\\ell_1$ decoder prevents gradient propagation as needed in standard gradient-based training. Our method is based on the insight that unrolling the convex decoder into $T$ projected subgradient steps can address this issue. Our method can be seen as a data-driven way to le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.10175","kind":"arxiv","version":4},"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":"2026-05-17T23:41:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XzNSf9uk9kbf0qKWGFojJAZ6gDWGM2eaWf07baVZ+7qVwDO2LNuchptfehsP/SG7oxlAwKfX8tUs3rSd4CFnCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:13:50.139298Z"},"content_sha256":"7e0e92bf974f9532f0c056a2ef2f304ef289b81158953f045e0a66d6ec7c9fad","schema_version":"1.0","event_id":"sha256:7e0e92bf974f9532f0c056a2ef2f304ef289b81158953f045e0a66d6ec7c9fad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DX5Z5HHFGDEDG3QOU3PQ3ERBA2/bundle.json","state_url":"https://pith.science/pith/DX5Z5HHFGDEDG3QOU3PQ3ERBA2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DX5Z5HHFGDEDG3QOU3PQ3ERBA2/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":"2026-05-26T06:13:50Z","links":{"resolver":"https://pith.science/pith/DX5Z5HHFGDEDG3QOU3PQ3ERBA2","bundle":"https://pith.science/pith/DX5Z5HHFGDEDG3QOU3PQ3ERBA2/bundle.json","state":"https://pith.science/pith/DX5Z5HHFGDEDG3QOU3PQ3ERBA2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DX5Z5HHFGDEDG3QOU3PQ3ERBA2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DX5Z5HHFGDEDG3QOU3PQ3ERBA2","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":"b062d4e8c87e050463bbdc48565f2f7efd6ada8d665477837dd837ec841752e0","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-26T19:11:22Z","title_canon_sha256":"5ec932c0840006f63938add1fe61c5848ba58df5df81b782c18f1cffe2c7240a"},"schema_version":"1.0","source":{"id":"1806.10175","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.10175","created_at":"2026-05-17T23:41:46Z"},{"alias_kind":"arxiv_version","alias_value":"1806.10175v4","created_at":"2026-05-17T23:41:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.10175","created_at":"2026-05-17T23:41:46Z"},{"alias_kind":"pith_short_12","alias_value":"DX5Z5HHFGDED","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DX5Z5HHFGDEDG3QO","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DX5Z5HHF","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:7e0e92bf974f9532f0c056a2ef2f304ef289b81158953f045e0a66d6ec7c9fad","target":"graph","created_at":"2026-05-17T23:41:46Z","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":"Linear encoding of sparse vectors is widely popular, but is commonly data-independent -- missing any possible extra (but a priori unknown) structure beyond sparsity. In this paper we present a new method to learn linear encoders that adapt to data, while still performing well with the widely used $\\ell_1$ decoder. The convex $\\ell_1$ decoder prevents gradient propagation as needed in standard gradient-based training. Our method is based on the insight that unrolling the convex decoder into $T$ projected subgradient steps can address this issue. Our method can be seen as a data-driven way to le","authors_text":"Afshin Rostamizadeh, Alexandros G. Dimakis, Daniel Holtmann-Rice, Dmitry Storcheus, Felix X. Yu, Sanjiv Kumar, Shanshan Wu, Sujay Sanghavi","cross_cats":["cs.IT","cs.LG","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-26T19:11:22Z","title":"Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.10175","kind":"arxiv","version":4},"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":"sha256:707f295dc6bfa54e8e28bb18f31dfe448868b5b34508028500f961f61db91c2e","target":"record","created_at":"2026-05-17T23:41:46Z","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":"b062d4e8c87e050463bbdc48565f2f7efd6ada8d665477837dd837ec841752e0","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-26T19:11:22Z","title_canon_sha256":"5ec932c0840006f63938add1fe61c5848ba58df5df81b782c18f1cffe2c7240a"},"schema_version":"1.0","source":{"id":"1806.10175","kind":"arxiv","version":4}},"canonical_sha256":"1dfb9e9ce530c8336e0ea6df0d92210690a3ac43c4fbbd86e0d4ef21a03f5e31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1dfb9e9ce530c8336e0ea6df0d92210690a3ac43c4fbbd86e0d4ef21a03f5e31","first_computed_at":"2026-05-17T23:41:46.432225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:46.432225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ILfhhn/BkrUUqDcPfrlUgGMwx0Aj+yZEUdVg6QlU8BQDv8Xsk8h4lVOSrdlCRV1wR1V1/PBoukrvcJhhcRIBBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:46.433042Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.10175","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:707f295dc6bfa54e8e28bb18f31dfe448868b5b34508028500f961f61db91c2e","sha256:7e0e92bf974f9532f0c056a2ef2f304ef289b81158953f045e0a66d6ec7c9fad"],"state_sha256":"8cf7a9677a5c9b2d18771a017894fb63e1f5276bf2d314067babf7187959331b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e43guWzbRhk04oSNbflDoXIJ+4KXc3A9Tj0EwERzi+aIzCbjEb8drAGn51EHZYLfFw7K9KRLsiBxUBzelexSCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T06:13:50.142765Z","bundle_sha256":"c5d1547b43a6e05ace4e69fcbe8ede415f56fc074a5bf45093d1c67a4d49b5aa"}}