{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RSA5PDS7FYFNBYCFVFCG4NGP3A","short_pith_number":"pith:RSA5PDS7","schema_version":"1.0","canonical_sha256":"8c81d78e5f2e0ad0e045a9446e34cfd81e8f68cb34b0771a174ffdfcdb0371d6","source":{"kind":"arxiv","id":"2206.12562","version":1},"attestation_state":"computed","paper":{"title":"PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Bukharin, Chen Liang, Pengcheng He, Qingru Zhang, Simiao Zuo, Tuo Zhao, Weizhu Chen","submitted_at":"2022-06-25T05:38:39Z","abstract_excerpt":"Large Transformer-based models have exhibited superior performance in various natural language processing and computer vision tasks. However, these models contain enormous amounts of parameters, which restrict their deployment to real-world applications. To reduce the model size, researchers prune these models based on the weights' importance scores. However, such scores are usually estimated on mini-batches during training, which incurs large variability/uncertainty due to mini-batch sampling and complicated training dynamics. As a result, some crucial weights could be pruned by commonly used"},"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":"2206.12562","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-25T05:38:39Z","cross_cats_sorted":[],"title_canon_sha256":"3d12ca4be72f32fa0871fa3ced306430e5f7518d914d19345f8a84ad88030b4c","abstract_canon_sha256":"7e1a5b2a8935d507dd12c38b38384348228fea3404cd53cb334aaa6c0d372625"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:56.501042Z","signature_b64":"MRd43EoVd4sZe/kGwkw9Bk71Ru/11Xb/s0y4LfDMdCzV3RTZfq9fSQZOmI6Ck1OqrkXeY8qA9ObuWrx/7izyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c81d78e5f2e0ad0e045a9446e34cfd81e8f68cb34b0771a174ffdfcdb0371d6","last_reissued_at":"2026-07-05T04:34:56.500648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:56.500648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Bukharin, Chen Liang, Pengcheng He, Qingru Zhang, Simiao Zuo, Tuo Zhao, Weizhu Chen","submitted_at":"2022-06-25T05:38:39Z","abstract_excerpt":"Large Transformer-based models have exhibited superior performance in various natural language processing and computer vision tasks. However, these models contain enormous amounts of parameters, which restrict their deployment to real-world applications. To reduce the model size, researchers prune these models based on the weights' importance scores. However, such scores are usually estimated on mini-batches during training, which incurs large variability/uncertainty due to mini-batch sampling and complicated training dynamics. As a result, some crucial weights could be pruned by commonly used"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12562","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.12562/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":"2206.12562","created_at":"2026-07-05T04:34:56.500704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.12562v1","created_at":"2026-07-05T04:34:56.500704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12562","created_at":"2026-07-05T04:34:56.500704+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSA5PDS7FYFN","created_at":"2026-07-05T04:34:56.500704+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSA5PDS7FYFNBYCF","created_at":"2026-07-05T04:34:56.500704+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSA5PDS7","created_at":"2026-07-05T04:34:56.500704+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/RSA5PDS7FYFNBYCFVFCG4NGP3A","json":"https://pith.science/pith/RSA5PDS7FYFNBYCFVFCG4NGP3A.json","graph_json":"https://pith.science/api/pith-number/RSA5PDS7FYFNBYCFVFCG4NGP3A/graph.json","events_json":"https://pith.science/api/pith-number/RSA5PDS7FYFNBYCFVFCG4NGP3A/events.json","paper":"https://pith.science/paper/RSA5PDS7"},"agent_actions":{"view_html":"https://pith.science/pith/RSA5PDS7FYFNBYCFVFCG4NGP3A","download_json":"https://pith.science/pith/RSA5PDS7FYFNBYCFVFCG4NGP3A.json","view_paper":"https://pith.science/paper/RSA5PDS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.12562&json=true","fetch_graph":"https://pith.science/api/pith-number/RSA5PDS7FYFNBYCFVFCG4NGP3A/graph.json","fetch_events":"https://pith.science/api/pith-number/RSA5PDS7FYFNBYCFVFCG4NGP3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSA5PDS7FYFNBYCFVFCG4NGP3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSA5PDS7FYFNBYCFVFCG4NGP3A/action/storage_attestation","attest_author":"https://pith.science/pith/RSA5PDS7FYFNBYCFVFCG4NGP3A/action/author_attestation","sign_citation":"https://pith.science/pith/RSA5PDS7FYFNBYCFVFCG4NGP3A/action/citation_signature","submit_replication":"https://pith.science/pith/RSA5PDS7FYFNBYCFVFCG4NGP3A/action/replication_record"}},"created_at":"2026-07-05T04:34:56.500704+00:00","updated_at":"2026-07-05T04:34:56.500704+00:00"}