{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LBLZ5JPH2QL6EV7FH7PLZ5X4S5","short_pith_number":"pith:LBLZ5JPH","schema_version":"1.0","canonical_sha256":"58579ea5e7d417e257e53fdebcf6fc974dcd1ed860272363aae8dfaea1ffc46d","source":{"kind":"arxiv","id":"1901.08455","version":1},"attestation_state":"computed","paper":{"title":"Really should we pruning after model be totally trained? Pruning based on a small amount of training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Li Yue, Shang Lin, Zhao Weibin","submitted_at":"2019-01-24T15:30:54Z","abstract_excerpt":"Pre-training of models in pruning algorithms plays an important role in pruning decision-making. We find that excessive pre-training is not necessary for pruning algorithms. According to this idea, we propose a pruning algorithm---Incremental pruning based on less training (IPLT). Compared with the traditional pruning algorithm based on a large number of pre-training, IPLT has competitive compression effect than the traditional pruning algorithm under the same simple pruning strategy. On the premise of ensuring accuracy, IPLT can achieve 8x-9x compression for VGG-19 on CIFAR-10 and only needs "},"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":"1901.08455","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-01-24T15:30:54Z","cross_cats_sorted":[],"title_canon_sha256":"5b4dd38646e94e2433e9b89ed9afd14383c7637807042e8ff3b27b5a061792da","abstract_canon_sha256":"5e5ed18544a66a85ab6a5742b7560fbac2ade2a1b8c72109376de799af3c070f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:35.395677Z","signature_b64":"98MiySftP/Xn64bYI5WKJTQIgsGQf9x3L9BuTqrEqTwWred5YYBkDWZwZ71QElnC++9jxzc6myzXnLgdU60FAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58579ea5e7d417e257e53fdebcf6fc974dcd1ed860272363aae8dfaea1ffc46d","last_reissued_at":"2026-05-17T23:55:35.395056Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:35.395056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Really should we pruning after model be totally trained? Pruning based on a small amount of training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Li Yue, Shang Lin, Zhao Weibin","submitted_at":"2019-01-24T15:30:54Z","abstract_excerpt":"Pre-training of models in pruning algorithms plays an important role in pruning decision-making. We find that excessive pre-training is not necessary for pruning algorithms. According to this idea, we propose a pruning algorithm---Incremental pruning based on less training (IPLT). Compared with the traditional pruning algorithm based on a large number of pre-training, IPLT has competitive compression effect than the traditional pruning algorithm under the same simple pruning strategy. On the premise of ensuring accuracy, IPLT can achieve 8x-9x compression for VGG-19 on CIFAR-10 and only needs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08455","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1901.08455","created_at":"2026-05-17T23:55:35.395135+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08455v1","created_at":"2026-05-17T23:55:35.395135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08455","created_at":"2026-05-17T23:55:35.395135+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBLZ5JPH2QL6","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBLZ5JPH2QL6EV7F","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBLZ5JPH","created_at":"2026-05-18T12:33:21.387695+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/LBLZ5JPH2QL6EV7FH7PLZ5X4S5","json":"https://pith.science/pith/LBLZ5JPH2QL6EV7FH7PLZ5X4S5.json","graph_json":"https://pith.science/api/pith-number/LBLZ5JPH2QL6EV7FH7PLZ5X4S5/graph.json","events_json":"https://pith.science/api/pith-number/LBLZ5JPH2QL6EV7FH7PLZ5X4S5/events.json","paper":"https://pith.science/paper/LBLZ5JPH"},"agent_actions":{"view_html":"https://pith.science/pith/LBLZ5JPH2QL6EV7FH7PLZ5X4S5","download_json":"https://pith.science/pith/LBLZ5JPH2QL6EV7FH7PLZ5X4S5.json","view_paper":"https://pith.science/paper/LBLZ5JPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08455&json=true","fetch_graph":"https://pith.science/api/pith-number/LBLZ5JPH2QL6EV7FH7PLZ5X4S5/graph.json","fetch_events":"https://pith.science/api/pith-number/LBLZ5JPH2QL6EV7FH7PLZ5X4S5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBLZ5JPH2QL6EV7FH7PLZ5X4S5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBLZ5JPH2QL6EV7FH7PLZ5X4S5/action/storage_attestation","attest_author":"https://pith.science/pith/LBLZ5JPH2QL6EV7FH7PLZ5X4S5/action/author_attestation","sign_citation":"https://pith.science/pith/LBLZ5JPH2QL6EV7FH7PLZ5X4S5/action/citation_signature","submit_replication":"https://pith.science/pith/LBLZ5JPH2QL6EV7FH7PLZ5X4S5/action/replication_record"}},"created_at":"2026-05-17T23:55:35.395135+00:00","updated_at":"2026-05-17T23:55:35.395135+00:00"}