{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SP5YO3WB47CM4ZJAV3IJRZYQNB","short_pith_number":"pith:SP5YO3WB","schema_version":"1.0","canonical_sha256":"93fb876ec1e7c4ce6520aed098e7106867e28fa81f5274f884930290b3d5dabe","source":{"kind":"arxiv","id":"2103.06460","version":3},"attestation_state":"computed","paper":{"title":"Recent Advances on Neural Network Pruning at Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Can Qin, Huan Wang, Yue Bai, Yulun Zhang, Yun Fu","submitted_at":"2021-03-11T05:01:52Z","abstract_excerpt":"Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune a randomly initialized network. This paper offers the first survey concentrated on this emerging pruning fashion. We first introduce a generic formulation of neural network pruning, followed by the major classic pruning topics. Then, as the main body of this paper, a thorough and structured literature review of PaI methods is presented, consisting of two major tracks (sparse training and sparse selection). Finally, w"},"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":"2103.06460","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-11T05:01:52Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE"],"title_canon_sha256":"c44be2c4e0999edf84f1fbcf57c378b7424cc09f39b13ab42bc0244dba928c79","abstract_canon_sha256":"b7561ced3df7ae56cbce899c54dd7b16c6327e22e08fd54fa04b507ac1dfd074"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:40.975176Z","signature_b64":"NLfcFluKGgdL2iS0hqVzo/PhZ1j3cL1RVMOjcWTWQNvLCd5htcwUQ9S7TzARrNJY93AEaRDEHcOuA1j4NLDkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93fb876ec1e7c4ce6520aed098e7106867e28fa81f5274f884930290b3d5dabe","last_reissued_at":"2026-07-05T04:25:40.974672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:40.974672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recent Advances on Neural Network Pruning at Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Can Qin, Huan Wang, Yue Bai, Yulun Zhang, Yun Fu","submitted_at":"2021-03-11T05:01:52Z","abstract_excerpt":"Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune a randomly initialized network. This paper offers the first survey concentrated on this emerging pruning fashion. We first introduce a generic formulation of neural network pruning, followed by the major classic pruning topics. Then, as the main body of this paper, a thorough and structured literature review of PaI methods is presented, consisting of two major tracks (sparse training and sparse selection). Finally, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06460","kind":"arxiv","version":3},"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/2103.06460/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":"2103.06460","created_at":"2026-07-05T04:25:40.974730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.06460v3","created_at":"2026-07-05T04:25:40.974730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06460","created_at":"2026-07-05T04:25:40.974730+00:00"},{"alias_kind":"pith_short_12","alias_value":"SP5YO3WB47CM","created_at":"2026-07-05T04:25:40.974730+00:00"},{"alias_kind":"pith_short_16","alias_value":"SP5YO3WB47CM4ZJA","created_at":"2026-07-05T04:25:40.974730+00:00"},{"alias_kind":"pith_short_8","alias_value":"SP5YO3WB","created_at":"2026-07-05T04:25:40.974730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12883","citing_title":"A Comparative Study of Pruning Methods in Transformer-based Time Series Forecasting","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SP5YO3WB47CM4ZJAV3IJRZYQNB","json":"https://pith.science/pith/SP5YO3WB47CM4ZJAV3IJRZYQNB.json","graph_json":"https://pith.science/api/pith-number/SP5YO3WB47CM4ZJAV3IJRZYQNB/graph.json","events_json":"https://pith.science/api/pith-number/SP5YO3WB47CM4ZJAV3IJRZYQNB/events.json","paper":"https://pith.science/paper/SP5YO3WB"},"agent_actions":{"view_html":"https://pith.science/pith/SP5YO3WB47CM4ZJAV3IJRZYQNB","download_json":"https://pith.science/pith/SP5YO3WB47CM4ZJAV3IJRZYQNB.json","view_paper":"https://pith.science/paper/SP5YO3WB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.06460&json=true","fetch_graph":"https://pith.science/api/pith-number/SP5YO3WB47CM4ZJAV3IJRZYQNB/graph.json","fetch_events":"https://pith.science/api/pith-number/SP5YO3WB47CM4ZJAV3IJRZYQNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SP5YO3WB47CM4ZJAV3IJRZYQNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SP5YO3WB47CM4ZJAV3IJRZYQNB/action/storage_attestation","attest_author":"https://pith.science/pith/SP5YO3WB47CM4ZJAV3IJRZYQNB/action/author_attestation","sign_citation":"https://pith.science/pith/SP5YO3WB47CM4ZJAV3IJRZYQNB/action/citation_signature","submit_replication":"https://pith.science/pith/SP5YO3WB47CM4ZJAV3IJRZYQNB/action/replication_record"}},"created_at":"2026-07-05T04:25:40.974730+00:00","updated_at":"2026-07-05T04:25:40.974730+00:00"}