{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YV47JCLHAG73JLPLUMUA54EVAN","short_pith_number":"pith:YV47JCLH","schema_version":"1.0","canonical_sha256":"c579f4896701bfb4adeba3280ef0950362f6c5d60d46ca9d190e3b9deefafbb6","source":{"kind":"arxiv","id":"2209.08247","version":2},"attestation_state":"computed","paper":{"title":"Gradient Properties of Hard Thresholding Operator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Jinglai Shen, Saeed Damadi","submitted_at":"2022-09-17T05:01:58Z","abstract_excerpt":"Sparse optimization receives increasing attention in many applications such as compressed sensing, variable selection in regression problems, and recently neural network compression in machine learning. For example, the problem of compressing a neural network is a bi-level, stochastic, and nonconvex problem that can be cast into a sparse optimization problem. Hence, developing efficient methods for sparse optimization plays a critical role in applications. The goal of this paper is to develop analytical techniques for general, large size sparse optimization problems using the hard thresholding"},"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":"2209.08247","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2022-09-17T05:01:58Z","cross_cats_sorted":[],"title_canon_sha256":"3cfc8846c5133045f157d15ab91f48c99f0afc38c845762819b192e06a2a9cdd","abstract_canon_sha256":"008d430377b79ee7aaf50137e9696433545db38e410bfaf0f041ab7cb859477a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:41.131307Z","signature_b64":"uKWZlYNmeBMVoMkGtrxb5vVzZxEjV50zPtDvEZ2iHXS4rXzhMX6aZgrZI98jqSRVwG2GkPu9+RO00KFdqB/bBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c579f4896701bfb4adeba3280ef0950362f6c5d60d46ca9d190e3b9deefafbb6","last_reissued_at":"2026-07-05T05:01:41.130967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:41.130967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Properties of Hard Thresholding Operator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Jinglai Shen, Saeed Damadi","submitted_at":"2022-09-17T05:01:58Z","abstract_excerpt":"Sparse optimization receives increasing attention in many applications such as compressed sensing, variable selection in regression problems, and recently neural network compression in machine learning. For example, the problem of compressing a neural network is a bi-level, stochastic, and nonconvex problem that can be cast into a sparse optimization problem. Hence, developing efficient methods for sparse optimization plays a critical role in applications. The goal of this paper is to develop analytical techniques for general, large size sparse optimization problems using the hard thresholding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08247","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/2209.08247/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":"2209.08247","created_at":"2026-07-05T05:01:41.131021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.08247v2","created_at":"2026-07-05T05:01:41.131021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08247","created_at":"2026-07-05T05:01:41.131021+00:00"},{"alias_kind":"pith_short_12","alias_value":"YV47JCLHAG73","created_at":"2026-07-05T05:01:41.131021+00:00"},{"alias_kind":"pith_short_16","alias_value":"YV47JCLHAG73JLPL","created_at":"2026-07-05T05:01:41.131021+00:00"},{"alias_kind":"pith_short_8","alias_value":"YV47JCLH","created_at":"2026-07-05T05:01:41.131021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08558","citing_title":"Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YV47JCLHAG73JLPLUMUA54EVAN","json":"https://pith.science/pith/YV47JCLHAG73JLPLUMUA54EVAN.json","graph_json":"https://pith.science/api/pith-number/YV47JCLHAG73JLPLUMUA54EVAN/graph.json","events_json":"https://pith.science/api/pith-number/YV47JCLHAG73JLPLUMUA54EVAN/events.json","paper":"https://pith.science/paper/YV47JCLH"},"agent_actions":{"view_html":"https://pith.science/pith/YV47JCLHAG73JLPLUMUA54EVAN","download_json":"https://pith.science/pith/YV47JCLHAG73JLPLUMUA54EVAN.json","view_paper":"https://pith.science/paper/YV47JCLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.08247&json=true","fetch_graph":"https://pith.science/api/pith-number/YV47JCLHAG73JLPLUMUA54EVAN/graph.json","fetch_events":"https://pith.science/api/pith-number/YV47JCLHAG73JLPLUMUA54EVAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YV47JCLHAG73JLPLUMUA54EVAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YV47JCLHAG73JLPLUMUA54EVAN/action/storage_attestation","attest_author":"https://pith.science/pith/YV47JCLHAG73JLPLUMUA54EVAN/action/author_attestation","sign_citation":"https://pith.science/pith/YV47JCLHAG73JLPLUMUA54EVAN/action/citation_signature","submit_replication":"https://pith.science/pith/YV47JCLHAG73JLPLUMUA54EVAN/action/replication_record"}},"created_at":"2026-07-05T05:01:41.131021+00:00","updated_at":"2026-07-05T05:01:41.131021+00:00"}