{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5FFXL32FQKFUL4MLIRR6VTHJEL","short_pith_number":"pith:5FFXL32F","schema_version":"1.0","canonical_sha256":"e94b75ef45828b45f18b4463eacce922e78d4410e9187bd8eb6709c7714e2f1f","source":{"kind":"arxiv","id":"2205.03665","version":2},"attestation_state":"computed","paper":{"title":"Variational Sparse Coding with Learned Thresholding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.SP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher J. Rozell, Kion Fallah","submitted_at":"2022-05-07T14:49:50Z","abstract_excerpt":"Sparse coding strategies have been lauded for their parsimonious representations of data that leverage low dimensional structure. However, inference of these codes typically relies on an optimization procedure with poor computational scaling in high-dimensional problems. For example, sparse inference in the representations learned in the high-dimensional intermediary layers of deep neural networks (DNNs) requires an iterative minimization to be performed at each training step. As such, recent, quick methods in variational inference have been proposed to infer sparse codes by learning a distrib"},"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":"2205.03665","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-07T14:49:50Z","cross_cats_sorted":["eess.SP","stat.ML"],"title_canon_sha256":"65c8b377e55a54c8a81791d1f76680dd970e982f88ff964c9d203a8f266fd0f3","abstract_canon_sha256":"21a54f3b11c5b5d7a330b1c726cea085e1edcfcba65626572a77ba9bcafe682e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:41.989780Z","signature_b64":"nl6O9R28CfHwuMyn0378YHz4fG/KBaTMU7s0hvZxGWaN18eTFbjw5hBCEBvHABjE3cGihgcZBkGXN8Qv5HDoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e94b75ef45828b45f18b4463eacce922e78d4410e9187bd8eb6709c7714e2f1f","last_reissued_at":"2026-07-05T04:53:41.989429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:41.989429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Sparse Coding with Learned Thresholding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.SP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher J. Rozell, Kion Fallah","submitted_at":"2022-05-07T14:49:50Z","abstract_excerpt":"Sparse coding strategies have been lauded for their parsimonious representations of data that leverage low dimensional structure. However, inference of these codes typically relies on an optimization procedure with poor computational scaling in high-dimensional problems. For example, sparse inference in the representations learned in the high-dimensional intermediary layers of deep neural networks (DNNs) requires an iterative minimization to be performed at each training step. As such, recent, quick methods in variational inference have been proposed to infer sparse codes by learning a distrib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03665","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.03665/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":"2205.03665","created_at":"2026-07-05T04:53:41.989486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.03665v2","created_at":"2026-07-05T04:53:41.989486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03665","created_at":"2026-07-05T04:53:41.989486+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FFXL32FQKFU","created_at":"2026-07-05T04:53:41.989486+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FFXL32FQKFUL4ML","created_at":"2026-07-05T04:53:41.989486+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FFXL32F","created_at":"2026-07-05T04:53:41.989486+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/5FFXL32FQKFUL4MLIRR6VTHJEL","json":"https://pith.science/pith/5FFXL32FQKFUL4MLIRR6VTHJEL.json","graph_json":"https://pith.science/api/pith-number/5FFXL32FQKFUL4MLIRR6VTHJEL/graph.json","events_json":"https://pith.science/api/pith-number/5FFXL32FQKFUL4MLIRR6VTHJEL/events.json","paper":"https://pith.science/paper/5FFXL32F"},"agent_actions":{"view_html":"https://pith.science/pith/5FFXL32FQKFUL4MLIRR6VTHJEL","download_json":"https://pith.science/pith/5FFXL32FQKFUL4MLIRR6VTHJEL.json","view_paper":"https://pith.science/paper/5FFXL32F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.03665&json=true","fetch_graph":"https://pith.science/api/pith-number/5FFXL32FQKFUL4MLIRR6VTHJEL/graph.json","fetch_events":"https://pith.science/api/pith-number/5FFXL32FQKFUL4MLIRR6VTHJEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FFXL32FQKFUL4MLIRR6VTHJEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FFXL32FQKFUL4MLIRR6VTHJEL/action/storage_attestation","attest_author":"https://pith.science/pith/5FFXL32FQKFUL4MLIRR6VTHJEL/action/author_attestation","sign_citation":"https://pith.science/pith/5FFXL32FQKFUL4MLIRR6VTHJEL/action/citation_signature","submit_replication":"https://pith.science/pith/5FFXL32FQKFUL4MLIRR6VTHJEL/action/replication_record"}},"created_at":"2026-07-05T04:53:41.989486+00:00","updated_at":"2026-07-05T04:53:41.989486+00:00"}