{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GSXWYSLVTKDB5FT6WONK3B2GEZ","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":"f7ce340817bcc604e43a1532d5e4ab27ad6f9f9fb51d730e3409531a50734f84","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-18T01:03:13Z","title_canon_sha256":"d8bfb0e900dfe3cf57acfc5e18ed4dfed7d02254d86d8ea66f6d8ac7e172c1bd"},"schema_version":"1.0","source":{"id":"2106.09857","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09857","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09857v3","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09857","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"GSXWYSLVTKDB","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"pith_short_16","alias_value":"GSXWYSLVTKDB5FT6","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"pith_short_8","alias_value":"GSXWYSLV","created_at":"2026-07-05T04:01:56Z"}],"graph_snapshots":[{"event_id":"sha256:934ad8e0903cde7b6908183221e9149a5e1fdb25f7b2fdf1b4aa2f897c2b1f20","target":"graph","created_at":"2026-07-05T04:01:56Z","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/2106.09857/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks (DNNs) are effective in solving many real-world problems. Larger DNN models usually exhibit better quality (e.g., accuracy) but their excessive computation results in long inference time. Model sparsification can reduce the computation and memory cost while maintaining model quality. Most existing sparsification algorithms unidirectionally remove weights, while others randomly or greedily explore a small subset of weights in each layer for pruning. The limitations of these algorithms reduce the level of achievable sparsity. In addition, many algorithms still require pre-tr","authors_text":"Fei Sun, Kun Yuan, Minghai Qin, Rong Jin, Xiaolong Ma, Yanzhi Wang, Yen-Kuang Chen, Yi Xu, Yuan Xie, Zejiang Hou","cross_cats":["cs.AI","cs.LG","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-18T01:03:13Z","title":"Effective Model Sparsification by Scheduled Grow-and-Prune Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09857","kind":"arxiv","version":3},"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:c85a9eabdaa726d6e4e664047c18462830efedf927f5de0b828fec536951cd90","target":"record","created_at":"2026-07-05T04:01:56Z","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":"f7ce340817bcc604e43a1532d5e4ab27ad6f9f9fb51d730e3409531a50734f84","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-18T01:03:13Z","title_canon_sha256":"d8bfb0e900dfe3cf57acfc5e18ed4dfed7d02254d86d8ea66f6d8ac7e172c1bd"},"schema_version":"1.0","source":{"id":"2106.09857","kind":"arxiv","version":3}},"canonical_sha256":"34af6c49759a861e967eb39aad8746265db735d24f414f4b31ad206a7281a382","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34af6c49759a861e967eb39aad8746265db735d24f414f4b31ad206a7281a382","first_computed_at":"2026-07-05T04:01:56.020415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:56.020415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CvUu4i6FxKNdRKLhV1K3kPHJ9l9Yt/JBDPyqay+XUvondX5drHtwAZHvlTN0EHQzCEmYKs3RIt+iN/zNEFnbCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:56.020845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.09857","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c85a9eabdaa726d6e4e664047c18462830efedf927f5de0b828fec536951cd90","sha256:934ad8e0903cde7b6908183221e9149a5e1fdb25f7b2fdf1b4aa2f897c2b1f20"],"state_sha256":"0e31d2fcc7c9890764b4283daed5db25d720013c64c98cec85afbf5dd383689d"}