{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:E4GKYU5FL3AXTQSBG5SLEJC3JD","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":"b70987cdf1165aee98c9850ea2f3e5c0c28562c2822c12c6c8603230adf35f89","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T16:42:56Z","title_canon_sha256":"7a762510ba9d7f0cd0c7265c8838ad0be3be1f7d999b6c6e106739e7de2b0322"},"schema_version":"1.0","source":{"id":"2110.08190","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08190","created_at":"2026-07-05T05:33:06Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08190v4","created_at":"2026-07-05T05:33:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08190","created_at":"2026-07-05T05:33:06Z"},{"alias_kind":"pith_short_12","alias_value":"E4GKYU5FL3AX","created_at":"2026-07-05T05:33:06Z"},{"alias_kind":"pith_short_16","alias_value":"E4GKYU5FL3AXTQSB","created_at":"2026-07-05T05:33:06Z"},{"alias_kind":"pith_short_8","alias_value":"E4GKYU5F","created_at":"2026-07-05T05:33:06Z"}],"graph_snapshots":[{"event_id":"sha256:a295c25b75bfe67fae8ed65cd4e979bb5b2cb77bdc54d290a338a92e096ce30e","target":"graph","created_at":"2026-07-05T05:33:06Z","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/2110.08190/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional wisdom in pruning Transformer-based language models is that pruning reduces the model expressiveness and thus is more likely to underfit rather than overfit. However, under the trending pretrain-and-finetune paradigm, we postulate a counter-traditional hypothesis, that is: pruning increases the risk of overfitting when performed at the fine-tuning phase. In this paper, we aim to address the overfitting problem and improve pruning performance via progressive knowledge distillation with error-bound properties. We show for the first time that reducing the risk of overfitting can help","authors_text":"Bingbing Li, Caiwen Ding, Dongkuan Xu, Hang Liu, Ian E.H. Yen, Mimi Xie, Sanguthevar Rajasekaran, Shaoyi Huang, Shiyang Chen, Sung-En Chang, Yijue Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T16:42:56Z","title":"Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08190","kind":"arxiv","version":4},"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:c588a8344cfc9bc175c245a32fc8ff588117fe19cdcb862c6cc934a7e8ef2af3","target":"record","created_at":"2026-07-05T05:33:06Z","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":"b70987cdf1165aee98c9850ea2f3e5c0c28562c2822c12c6c8603230adf35f89","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T16:42:56Z","title_canon_sha256":"7a762510ba9d7f0cd0c7265c8838ad0be3be1f7d999b6c6e106739e7de2b0322"},"schema_version":"1.0","source":{"id":"2110.08190","kind":"arxiv","version":4}},"canonical_sha256":"270cac53a55ec179c2413764b2245b48db33416153db703a7ab5b8ac653686db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"270cac53a55ec179c2413764b2245b48db33416153db703a7ab5b8ac653686db","first_computed_at":"2026-07-05T05:33:06.669089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:33:06.669089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UoJmqNrCxCvNkrrtHEp3eQXGwfCrsL+QPV6yDCZpbgcSyBiYlBZRa/eJsf8rLADQ/zFCvDakC+UEEX+GB+rHBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:33:06.669537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.08190","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c588a8344cfc9bc175c245a32fc8ff588117fe19cdcb862c6cc934a7e8ef2af3","sha256:a295c25b75bfe67fae8ed65cd4e979bb5b2cb77bdc54d290a338a92e096ce30e"],"state_sha256":"723e71c76a23f534f576a156dbc3f6341362b2c181ad7e9bc5b3f0ad54fc937c"}