{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:S3YJP7IEIUEORGSBZ556YYUSTY","short_pith_number":"pith:S3YJP7IE","schema_version":"1.0","canonical_sha256":"96f097fd044508e89a41cf7bec62929e36b4fabd8b460fa1c320bb80a73ffc04","source":{"kind":"arxiv","id":"1905.09449","version":5},"attestation_state":"computed","paper":{"title":"Exploring Structural Sparsity of Deep Networks via Inverse Scale Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Liu, Donghao Li, Jinshan Zeng, Xinwei Sun, Yanwei Fu, Yuan Yao, Zuyuan Zhong","submitted_at":"2019-05-23T03:27:03Z","abstract_excerpt":"The great success of deep neural networks is built upon their over-parameterization, which smooths the optimization landscape without degrading the generalization ability. Despite the benefits of over-parameterization, a huge amount of parameters makes deep networks cumbersome in daily life applications. Though techniques such as pruning and distillation are developed, they are expensive in fully training a dense network as backward selection methods, and there is still a void on systematically exploring forward selection methods for learning structural sparsity in deep networks. To fill in th"},"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":"1905.09449","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T03:27:03Z","cross_cats_sorted":["math.DS","math.OC","stat.ML"],"title_canon_sha256":"9727fb4ee75e8e1d1b5aa8d639982691f3c21d2d05594edb1c9f3a0be0985eb6","abstract_canon_sha256":"f227c2213184d29729a651e8b8a64916ef7eb34d9aab48b729dfb9fe27566fd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:33.844273Z","signature_b64":"oIL5Enu/M0YYIonfQUwd5bwsRXT6+f8B1HjRBzN7JnRkasOAP3tOZCNQ+M/leM3I5PoMfpw5Y2bwtquPm+BIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96f097fd044508e89a41cf7bec62929e36b4fabd8b460fa1c320bb80a73ffc04","last_reissued_at":"2026-07-05T04:16:33.843857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:33.843857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Structural Sparsity of Deep Networks via Inverse Scale Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Liu, Donghao Li, Jinshan Zeng, Xinwei Sun, Yanwei Fu, Yuan Yao, Zuyuan Zhong","submitted_at":"2019-05-23T03:27:03Z","abstract_excerpt":"The great success of deep neural networks is built upon their over-parameterization, which smooths the optimization landscape without degrading the generalization ability. Despite the benefits of over-parameterization, a huge amount of parameters makes deep networks cumbersome in daily life applications. Though techniques such as pruning and distillation are developed, they are expensive in fully training a dense network as backward selection methods, and there is still a void on systematically exploring forward selection methods for learning structural sparsity in deep networks. To fill in th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09449","kind":"arxiv","version":5},"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/1905.09449/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":"1905.09449","created_at":"2026-07-05T04:16:33.843907+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.09449v5","created_at":"2026-07-05T04:16:33.843907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09449","created_at":"2026-07-05T04:16:33.843907+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3YJP7IEIUEO","created_at":"2026-07-05T04:16:33.843907+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3YJP7IEIUEORGSB","created_at":"2026-07-05T04:16:33.843907+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3YJP7IE","created_at":"2026-07-05T04:16:33.843907+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/S3YJP7IEIUEORGSBZ556YYUSTY","json":"https://pith.science/pith/S3YJP7IEIUEORGSBZ556YYUSTY.json","graph_json":"https://pith.science/api/pith-number/S3YJP7IEIUEORGSBZ556YYUSTY/graph.json","events_json":"https://pith.science/api/pith-number/S3YJP7IEIUEORGSBZ556YYUSTY/events.json","paper":"https://pith.science/paper/S3YJP7IE"},"agent_actions":{"view_html":"https://pith.science/pith/S3YJP7IEIUEORGSBZ556YYUSTY","download_json":"https://pith.science/pith/S3YJP7IEIUEORGSBZ556YYUSTY.json","view_paper":"https://pith.science/paper/S3YJP7IE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.09449&json=true","fetch_graph":"https://pith.science/api/pith-number/S3YJP7IEIUEORGSBZ556YYUSTY/graph.json","fetch_events":"https://pith.science/api/pith-number/S3YJP7IEIUEORGSBZ556YYUSTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3YJP7IEIUEORGSBZ556YYUSTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3YJP7IEIUEORGSBZ556YYUSTY/action/storage_attestation","attest_author":"https://pith.science/pith/S3YJP7IEIUEORGSBZ556YYUSTY/action/author_attestation","sign_citation":"https://pith.science/pith/S3YJP7IEIUEORGSBZ556YYUSTY/action/citation_signature","submit_replication":"https://pith.science/pith/S3YJP7IEIUEORGSBZ556YYUSTY/action/replication_record"}},"created_at":"2026-07-05T04:16:33.843907+00:00","updated_at":"2026-07-05T04:16:33.843907+00:00"}