{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:S3YJP7IEIUEORGSBZ556YYUSTY","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":"f227c2213184d29729a651e8b8a64916ef7eb34d9aab48b729dfb9fe27566fd7","cross_cats_sorted":["math.DS","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T03:27:03Z","title_canon_sha256":"9727fb4ee75e8e1d1b5aa8d639982691f3c21d2d05594edb1c9f3a0be0985eb6"},"schema_version":"1.0","source":{"id":"1905.09449","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.09449","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"arxiv_version","alias_value":"1905.09449v5","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09449","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"pith_short_12","alias_value":"S3YJP7IEIUEO","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"pith_short_16","alias_value":"S3YJP7IEIUEORGSB","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"pith_short_8","alias_value":"S3YJP7IE","created_at":"2026-07-05T04:16:33Z"}],"graph_snapshots":[{"event_id":"sha256:3aaf3ee5a2ec03143013588dd1e33e9509bce970cdac071e9be26b53257ce116","target":"graph","created_at":"2026-07-05T04:16:33Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1905.09449/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chen Liu, Donghao Li, Jinshan Zeng, Xinwei Sun, Yanwei Fu, Yuan Yao, Zuyuan Zhong","cross_cats":["math.DS","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T03:27:03Z","title":"Exploring Structural Sparsity of Deep Networks via Inverse Scale Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09449","kind":"arxiv","version":5},"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":"sha256:434377fabd7e339051c58925ded5b693978d9308d46bb7e16c49289c03afe322","target":"record","created_at":"2026-07-05T04:16:33Z","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":"f227c2213184d29729a651e8b8a64916ef7eb34d9aab48b729dfb9fe27566fd7","cross_cats_sorted":["math.DS","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T03:27:03Z","title_canon_sha256":"9727fb4ee75e8e1d1b5aa8d639982691f3c21d2d05594edb1c9f3a0be0985eb6"},"schema_version":"1.0","source":{"id":"1905.09449","kind":"arxiv","version":5}},"canonical_sha256":"96f097fd044508e89a41cf7bec62929e36b4fabd8b460fa1c320bb80a73ffc04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96f097fd044508e89a41cf7bec62929e36b4fabd8b460fa1c320bb80a73ffc04","first_computed_at":"2026-07-05T04:16:33.843857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:16:33.843857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oIL5Enu/M0YYIonfQUwd5bwsRXT6+f8B1HjRBzN7JnRkasOAP3tOZCNQ+M/leM3I5PoMfpw5Y2bwtquPm+BIAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:16:33.844273Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.09449","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:434377fabd7e339051c58925ded5b693978d9308d46bb7e16c49289c03afe322","sha256:3aaf3ee5a2ec03143013588dd1e33e9509bce970cdac071e9be26b53257ce116"],"state_sha256":"52dab1cb50588a2a5eca569497225ec1002391bde202f8aa0579c734dc5c8d90"}