{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EV66MXJKLOH2GP7ZW34ZNCFLYY","short_pith_number":"pith:EV66MXJK","schema_version":"1.0","canonical_sha256":"257de65d2a5b8fa33ff9b6f99688abc63775c2a9eea5d31e78d28c3cbf0c29a2","source":{"kind":"arxiv","id":"2111.12621","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Deep Learning with Dynamic Data Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kyle Daruwalla, Mikko Lipasti, Ravi S Raju","submitted_at":"2021-11-24T16:47:34Z","abstract_excerpt":"Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data. As this trend continues, model training has become prohibitively costly, requiring access to powerful computing systems to train state-of-the-art networks. A large body of research has been devoted to addressing the cost per iteration of training through various model compression techniques like pruning and quantization. Less effort has been spent targeting the number of iterations. Previous work, such as forget scores and GraNd/EL2N scores, address this problem by identif"},"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":"2111.12621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-24T16:47:34Z","cross_cats_sorted":[],"title_canon_sha256":"204b912392cb3574e47ffb1ce631997ac829c6afb964bd9cd9793009bba60df3","abstract_canon_sha256":"68eab537601a3bd09aee7d9cd7a2c10b24c706fe1f6badeccd580f2821a60a31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:54.060975Z","signature_b64":"p+az8W+NMQgOl/e5PXubEO9Us8Qu+86FXex4iUaLunbkPHdRYPXK4yn4BcdVnrFf+SDY31eiKw6GI552BaQTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"257de65d2a5b8fa33ff9b6f99688abc63775c2a9eea5d31e78d28c3cbf0c29a2","last_reissued_at":"2026-07-05T03:34:54.060564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:54.060564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Deep Learning with Dynamic Data Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kyle Daruwalla, Mikko Lipasti, Ravi S Raju","submitted_at":"2021-11-24T16:47:34Z","abstract_excerpt":"Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data. As this trend continues, model training has become prohibitively costly, requiring access to powerful computing systems to train state-of-the-art networks. A large body of research has been devoted to addressing the cost per iteration of training through various model compression techniques like pruning and quantization. Less effort has been spent targeting the number of iterations. Previous work, such as forget scores and GraNd/EL2N scores, address this problem by identif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12621","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/2111.12621/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":"2111.12621","created_at":"2026-07-05T03:34:54.060620+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.12621v1","created_at":"2026-07-05T03:34:54.060620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12621","created_at":"2026-07-05T03:34:54.060620+00:00"},{"alias_kind":"pith_short_12","alias_value":"EV66MXJKLOH2","created_at":"2026-07-05T03:34:54.060620+00:00"},{"alias_kind":"pith_short_16","alias_value":"EV66MXJKLOH2GP7Z","created_at":"2026-07-05T03:34:54.060620+00:00"},{"alias_kind":"pith_short_8","alias_value":"EV66MXJK","created_at":"2026-07-05T03:34:54.060620+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12913","citing_title":"Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11761","citing_title":"RCAP: Robust, Class-Aware, Probabilistic Dynamic Dataset Pruning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14773","citing_title":"Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07433","citing_title":"Data Agent: Learning to Select Data via End-to-End Dynamic Optimization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07306","citing_title":"Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignment","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04681","citing_title":"Batch Loss Score for Dynamic Data Pruning","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EV66MXJKLOH2GP7ZW34ZNCFLYY","json":"https://pith.science/pith/EV66MXJKLOH2GP7ZW34ZNCFLYY.json","graph_json":"https://pith.science/api/pith-number/EV66MXJKLOH2GP7ZW34ZNCFLYY/graph.json","events_json":"https://pith.science/api/pith-number/EV66MXJKLOH2GP7ZW34ZNCFLYY/events.json","paper":"https://pith.science/paper/EV66MXJK"},"agent_actions":{"view_html":"https://pith.science/pith/EV66MXJKLOH2GP7ZW34ZNCFLYY","download_json":"https://pith.science/pith/EV66MXJKLOH2GP7ZW34ZNCFLYY.json","view_paper":"https://pith.science/paper/EV66MXJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.12621&json=true","fetch_graph":"https://pith.science/api/pith-number/EV66MXJKLOH2GP7ZW34ZNCFLYY/graph.json","fetch_events":"https://pith.science/api/pith-number/EV66MXJKLOH2GP7ZW34ZNCFLYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EV66MXJKLOH2GP7ZW34ZNCFLYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EV66MXJKLOH2GP7ZW34ZNCFLYY/action/storage_attestation","attest_author":"https://pith.science/pith/EV66MXJKLOH2GP7ZW34ZNCFLYY/action/author_attestation","sign_citation":"https://pith.science/pith/EV66MXJKLOH2GP7ZW34ZNCFLYY/action/citation_signature","submit_replication":"https://pith.science/pith/EV66MXJKLOH2GP7ZW34ZNCFLYY/action/replication_record"}},"created_at":"2026-07-05T03:34:54.060620+00:00","updated_at":"2026-07-05T03:34:54.060620+00:00"}