{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EFJXE4ORMMMLL6GAG5KXEV7SI7","short_pith_number":"pith:EFJXE4OR","schema_version":"1.0","canonical_sha256":"21537271d16318b5f8c037557257f247f74ec3cd1e9bfd965145e40ed67895bb","source":{"kind":"arxiv","id":"2111.00843","version":3},"attestation_state":"computed","paper":{"title":"How I Learned to Stop Worrying and Love Retraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christoph Spiegel, Max Zimmer, Sebastian Pokutta","submitted_at":"2021-11-01T11:23:44Z","abstract_excerpt":"Many Neural Network Pruning approaches consist of several iterative training and pruning steps, seemingly losing a significant amount of their performance after pruning and then recovering it in the subsequent retraining phase. Recent works of Renda et al. (2020) and Le & Hua (2021) demonstrate the significance of the learning rate schedule during the retraining phase and propose specific heuristics for choosing such a schedule for IMP (Han et al., 2015). We place these findings in the context of the results of Li et al. (2020) regarding the training of models within a fixed training budget an"},"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":"2111.00843","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T11:23:44Z","cross_cats_sorted":[],"title_canon_sha256":"e82c3e4a96db6e76c7547c4c91d90ea5a8684511e3bea4a8d2833bc6a1972136","abstract_canon_sha256":"875f70e1bce98e71db6b7e7be7299b6ef97e7d899831d2b37c2ba271059d95ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:04.053931Z","signature_b64":"NuKAvBi32YmKu7O06o4GsNJoA5JGsvnFWVa/AMXr+NpUwVCuuFSRg13riG/zVaiPox1irLBH6kPfcrKYi07eDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21537271d16318b5f8c037557257f247f74ec3cd1e9bfd965145e40ed67895bb","last_reissued_at":"2026-07-05T05:50:04.053511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:04.053511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How I Learned to Stop Worrying and Love Retraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christoph Spiegel, Max Zimmer, Sebastian Pokutta","submitted_at":"2021-11-01T11:23:44Z","abstract_excerpt":"Many Neural Network Pruning approaches consist of several iterative training and pruning steps, seemingly losing a significant amount of their performance after pruning and then recovering it in the subsequent retraining phase. Recent works of Renda et al. (2020) and Le & Hua (2021) demonstrate the significance of the learning rate schedule during the retraining phase and propose specific heuristics for choosing such a schedule for IMP (Han et al., 2015). We place these findings in the context of the results of Li et al. (2020) regarding the training of models within a fixed training budget an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00843","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/2111.00843/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":"2111.00843","created_at":"2026-07-05T05:50:04.053566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.00843v3","created_at":"2026-07-05T05:50:04.053566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00843","created_at":"2026-07-05T05:50:04.053566+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFJXE4ORMMML","created_at":"2026-07-05T05:50:04.053566+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFJXE4ORMMMLL6GA","created_at":"2026-07-05T05:50:04.053566+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFJXE4OR","created_at":"2026-07-05T05:50:04.053566+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/EFJXE4ORMMMLL6GAG5KXEV7SI7","json":"https://pith.science/pith/EFJXE4ORMMMLL6GAG5KXEV7SI7.json","graph_json":"https://pith.science/api/pith-number/EFJXE4ORMMMLL6GAG5KXEV7SI7/graph.json","events_json":"https://pith.science/api/pith-number/EFJXE4ORMMMLL6GAG5KXEV7SI7/events.json","paper":"https://pith.science/paper/EFJXE4OR"},"agent_actions":{"view_html":"https://pith.science/pith/EFJXE4ORMMMLL6GAG5KXEV7SI7","download_json":"https://pith.science/pith/EFJXE4ORMMMLL6GAG5KXEV7SI7.json","view_paper":"https://pith.science/paper/EFJXE4OR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.00843&json=true","fetch_graph":"https://pith.science/api/pith-number/EFJXE4ORMMMLL6GAG5KXEV7SI7/graph.json","fetch_events":"https://pith.science/api/pith-number/EFJXE4ORMMMLL6GAG5KXEV7SI7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFJXE4ORMMMLL6GAG5KXEV7SI7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFJXE4ORMMMLL6GAG5KXEV7SI7/action/storage_attestation","attest_author":"https://pith.science/pith/EFJXE4ORMMMLL6GAG5KXEV7SI7/action/author_attestation","sign_citation":"https://pith.science/pith/EFJXE4ORMMMLL6GAG5KXEV7SI7/action/citation_signature","submit_replication":"https://pith.science/pith/EFJXE4ORMMMLL6GAG5KXEV7SI7/action/replication_record"}},"created_at":"2026-07-05T05:50:04.053566+00:00","updated_at":"2026-07-05T05:50:04.053566+00:00"}