{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UIWKWUILOJLGJKPRWDRINGOFLM","short_pith_number":"pith:UIWKWUIL","schema_version":"1.0","canonical_sha256":"a22cab510b725664a9f1b0e28699c55b127e869d394ae9757604f8bca9aa6591","source":{"kind":"arxiv","id":"2007.15353","version":2},"attestation_state":"computed","paper":{"title":"Growing Efficient Deep Networks by Structured Continuous Sparsification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael Maire, Pedro Savarese, Xin Yuan","submitted_at":"2020-07-30T10:03:47Z","abstract_excerpt":"We develop an approach to growing deep network architectures over the course of training, driven by a principled combination of accuracy and sparsity objectives. Unlike existing pruning or architecture search techniques that operate on full-sized models or supernet architectures, our method can start from a small, simple seed architecture and dynamically grow and prune both layers and filters. By combining a continuous relaxation of discrete network structure optimization with a scheme for sampling sparse subnetworks, we produce compact, pruned networks, while also drastically reducing the com"},"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":"2007.15353","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-30T10:03:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"98a7cd41491aa996a1b49405e6b2b3369f9eed914259e824354a574254df54d9","abstract_canon_sha256":"5200dff330b2f07c6b5f71cc757a366fa0e733bf812e323691b21ec2676822d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:35.306037Z","signature_b64":"VgYblbbMpvITp4W9htko8N9/Pv4FhS6diG0oS00QM3aHnr1iTJyuwURyITOowtbT+mt1qiSlera3Zzjfh9WeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a22cab510b725664a9f1b0e28699c55b127e869d394ae9757604f8bca9aa6591","last_reissued_at":"2026-07-05T06:17:35.305566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:35.305566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Growing Efficient Deep Networks by Structured Continuous Sparsification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael Maire, Pedro Savarese, Xin Yuan","submitted_at":"2020-07-30T10:03:47Z","abstract_excerpt":"We develop an approach to growing deep network architectures over the course of training, driven by a principled combination of accuracy and sparsity objectives. Unlike existing pruning or architecture search techniques that operate on full-sized models or supernet architectures, our method can start from a small, simple seed architecture and dynamically grow and prune both layers and filters. By combining a continuous relaxation of discrete network structure optimization with a scheme for sampling sparse subnetworks, we produce compact, pruned networks, while also drastically reducing the com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.15353","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/2007.15353/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":"2007.15353","created_at":"2026-07-05T06:17:35.305623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.15353v2","created_at":"2026-07-05T06:17:35.305623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.15353","created_at":"2026-07-05T06:17:35.305623+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIWKWUILOJLG","created_at":"2026-07-05T06:17:35.305623+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIWKWUILOJLGJKPR","created_at":"2026-07-05T06:17:35.305623+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIWKWUIL","created_at":"2026-07-05T06:17:35.305623+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/UIWKWUILOJLGJKPRWDRINGOFLM","json":"https://pith.science/pith/UIWKWUILOJLGJKPRWDRINGOFLM.json","graph_json":"https://pith.science/api/pith-number/UIWKWUILOJLGJKPRWDRINGOFLM/graph.json","events_json":"https://pith.science/api/pith-number/UIWKWUILOJLGJKPRWDRINGOFLM/events.json","paper":"https://pith.science/paper/UIWKWUIL"},"agent_actions":{"view_html":"https://pith.science/pith/UIWKWUILOJLGJKPRWDRINGOFLM","download_json":"https://pith.science/pith/UIWKWUILOJLGJKPRWDRINGOFLM.json","view_paper":"https://pith.science/paper/UIWKWUIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.15353&json=true","fetch_graph":"https://pith.science/api/pith-number/UIWKWUILOJLGJKPRWDRINGOFLM/graph.json","fetch_events":"https://pith.science/api/pith-number/UIWKWUILOJLGJKPRWDRINGOFLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIWKWUILOJLGJKPRWDRINGOFLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIWKWUILOJLGJKPRWDRINGOFLM/action/storage_attestation","attest_author":"https://pith.science/pith/UIWKWUILOJLGJKPRWDRINGOFLM/action/author_attestation","sign_citation":"https://pith.science/pith/UIWKWUILOJLGJKPRWDRINGOFLM/action/citation_signature","submit_replication":"https://pith.science/pith/UIWKWUILOJLGJKPRWDRINGOFLM/action/replication_record"}},"created_at":"2026-07-05T06:17:35.305623+00:00","updated_at":"2026-07-05T06:17:35.305623+00:00"}