{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5TZUAENRATDVNW4HC66PISFZFJ","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":"727b3a78da4552aba185ca4ec6cf53b54e948131a78e4f4de8e0c48b53ccc285","cross_cats_sorted":["cs.AI","cs.LG","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-07-31T15:08:36Z","title_canon_sha256":"9f78f0fb631579ee72dc3d1045a0d932dc503ad979f45ea52fc45718d70b224a"},"schema_version":"1.0","source":{"id":"2108.00259","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.00259","created_at":"2026-07-05T06:43:43Z"},{"alias_kind":"arxiv_version","alias_value":"2108.00259v3","created_at":"2026-07-05T06:43:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.00259","created_at":"2026-07-05T06:43:43Z"},{"alias_kind":"pith_short_12","alias_value":"5TZUAENRATDV","created_at":"2026-07-05T06:43:43Z"},{"alias_kind":"pith_short_16","alias_value":"5TZUAENRATDVNW4H","created_at":"2026-07-05T06:43:43Z"},{"alias_kind":"pith_short_8","alias_value":"5TZUAENR","created_at":"2026-07-05T06:43:43Z"}],"graph_snapshots":[{"event_id":"sha256:1ce199d357f996a245869b35a66aba208c9ad7e26baafc38501db748fe6486b4","target":"graph","created_at":"2026-07-05T06:43:43Z","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/2108.00259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural network pruning is useful for discovering efficient, high-performing subnetworks within pre-trained, dense network architectures. More often than not, it involves a three-step process -- pre-training, pruning, and re-training -- that is computationally expensive, as the dense model must be fully pre-trained. While previous work has revealed through experiments the relationship between the amount of pre-training and the performance of the pruned network, a theoretical characterization of such dependency is still missing. Aiming to mathematically analyze the amount of dense network pre-tr","authors_text":"Anastasios Kyrillidis, Cameron R. Wolfe, Fangshuo Liao, Junhyung Lyle Kim, Qihan Wang","cross_cats":["cs.AI","cs.LG","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-07-31T15:08:36Z","title":"How much pre-training is enough to discover a good subnetwork?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.00259","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":"sha256:90234bc0cac44be029e708e0113af7d8b29d0ca1130714467c7d946efd2f0d10","target":"record","created_at":"2026-07-05T06:43:43Z","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":"727b3a78da4552aba185ca4ec6cf53b54e948131a78e4f4de8e0c48b53ccc285","cross_cats_sorted":["cs.AI","cs.LG","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-07-31T15:08:36Z","title_canon_sha256":"9f78f0fb631579ee72dc3d1045a0d932dc503ad979f45ea52fc45718d70b224a"},"schema_version":"1.0","source":{"id":"2108.00259","kind":"arxiv","version":3}},"canonical_sha256":"ecf34011b104c756db8717bcf448b92a50112bb6a096255d888e3bcfae260fdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecf34011b104c756db8717bcf448b92a50112bb6a096255d888e3bcfae260fdb","first_computed_at":"2026-07-05T06:43:43.285927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:43.285927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"64X+QocdSiNqkL8BE4/TZ52bqg8mTQLuF+/gWRhnkLyfNDQ6IFNZDpJGs8LrxnonlJgzvA0NgO1XnDCyLWI+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:43.286350Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.00259","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90234bc0cac44be029e708e0113af7d8b29d0ca1130714467c7d946efd2f0d10","sha256:1ce199d357f996a245869b35a66aba208c9ad7e26baafc38501db748fe6486b4"],"state_sha256":"ab335a28f99d421daa53560b4a3b2d7f6485c60c916f067adae796f7d237fdb5"}