{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GA2G4BRIMYLHIWRPQU4EIJSMP2","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":"6bc362f3d4d43eee9610e8ea5f8983387a56c4789eb3a24cac8e05449ec53fe2","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-05T17:54:35Z","title_canon_sha256":"6d4da3a68b649870199e4461d7e7b64364f818becd2b486a937ca784a603e8df"},"schema_version":"1.0","source":{"id":"2011.02999","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.02999","created_at":"2026-07-05T01:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"2011.02999v1","created_at":"2026-07-05T01:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02999","created_at":"2026-07-05T01:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"GA2G4BRIMYLH","created_at":"2026-07-05T01:49:33Z"},{"alias_kind":"pith_short_16","alias_value":"GA2G4BRIMYLHIWRP","created_at":"2026-07-05T01:49:33Z"},{"alias_kind":"pith_short_8","alias_value":"GA2G4BRI","created_at":"2026-07-05T01:49:33Z"}],"graph_snapshots":[{"event_id":"sha256:13dbc9e832c3572d1b76f847c0ae5b6721bbbb654820984131b19658738d8702","target":"graph","created_at":"2026-07-05T01:49:33Z","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/2011.02999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The paper proposes and optimizes a partial recovery training system, CPR, for recommendation models. CPR relaxes the consistency requirement by enabling non-failed nodes to proceed without loading checkpoints when a node fails during training, improving failure-related overheads. The paper is the first to the extent of our knowledge to perform a data-driven, in-depth analysis of applying partial recovery to recommendation models and identified a trade-off between accuracy and performance. Motivated by the analysis, we present CPR, a partial recovery training system that can reduce the training","authors_text":"Bor-Yiing Su, Brandon Lucia, Carole-Jean Wu, Caroline Trippel, Isabel Gao, Jiyan Yang, Kiwan Maeng, Mark C. Jeffrey, Mike Rabbat, Shivam Bharuka, Vikram Saraph","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-05T17:54:35Z","title":"CPR: Understanding and Improving Failure Tolerant Training for Deep Learning Recommendation with Partial Recovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02999","kind":"arxiv","version":1},"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":"sha256:6cfe9c9cc11bee4a318418f0fd71033dbc0acf2fb8ab3edd5f1a03b85a4585d6","target":"record","created_at":"2026-07-05T01:49:33Z","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":"6bc362f3d4d43eee9610e8ea5f8983387a56c4789eb3a24cac8e05449ec53fe2","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-05T17:54:35Z","title_canon_sha256":"6d4da3a68b649870199e4461d7e7b64364f818becd2b486a937ca784a603e8df"},"schema_version":"1.0","source":{"id":"2011.02999","kind":"arxiv","version":1}},"canonical_sha256":"30346e06286616745a2f853844264c7e960358296767fcf8921478c7242d3ab2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30346e06286616745a2f853844264c7e960358296767fcf8921478c7242d3ab2","first_computed_at":"2026-07-05T01:49:33.062511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:33.062511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S8IUUTgZW10peou45alRk/7wEsf8Bx2tL4deZ9gR6FAhEGPolTxGSV5nTFGi5H0swF9JfblHmvglUJftgWwcAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:33.062965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.02999","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cfe9c9cc11bee4a318418f0fd71033dbc0acf2fb8ab3edd5f1a03b85a4585d6","sha256:13dbc9e832c3572d1b76f847c0ae5b6721bbbb654820984131b19658738d8702"],"state_sha256":"d509830ed9906a7cdaa37cb700a77200cf47613683202717556cdb425e1d6460"}