{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QDE7ASTYIKID3XO2J2UH243N67","short_pith_number":"pith:QDE7ASTY","canonical_record":{"source":{"id":"2103.11109","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-20T06:14:19Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"fc0c801ffcf22b69e3866f0c02a5b22711a3b81f8f42d09b5f8e03562d661c68","abstract_canon_sha256":"69729d85cbf50adb78a52b55f1f85446ac441e1c190b36f45356d71d82f4ab29"},"schema_version":"1.0"},"canonical_sha256":"80c9f04a7842903dddda4ea87d736df7ecb3ef050221ea8be837c7f60a3864fd","source":{"kind":"arxiv","id":"2103.11109","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.11109","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2103.11109v6","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11109","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"QDE7ASTYIKID","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"QDE7ASTYIKID3XO2","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"QDE7ASTY","created_at":"2026-07-05T04:08:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QDE7ASTYIKID3XO2J2UH243N67","target":"record","payload":{"canonical_record":{"source":{"id":"2103.11109","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-20T06:14:19Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"fc0c801ffcf22b69e3866f0c02a5b22711a3b81f8f42d09b5f8e03562d661c68","abstract_canon_sha256":"69729d85cbf50adb78a52b55f1f85446ac441e1c190b36f45356d71d82f4ab29"},"schema_version":"1.0"},"canonical_sha256":"80c9f04a7842903dddda4ea87d736df7ecb3ef050221ea8be837c7f60a3864fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:56.756639Z","signature_b64":"I4+6vuriYAEGGw5YMyq5voti3CX0X6/jhgWzB1j1Xyy1GMtkfkty0qsMEYWungjRES7zTO14MqBKmm+4LkYmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80c9f04a7842903dddda4ea87d736df7ecb3ef050221ea8be837c7f60a3864fd","last_reissued_at":"2026-07-05T04:08:56.756183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:56.756183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.11109","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ML5kp0omaA2v0JBtj2/ig9k6yTbobTUwLEiA85ElJpSxloOLHa4DimPZQDzcuB8N9QcXOx2LG6hhuEA7zSGtCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:36:53.930290Z"},"content_sha256":"d564e3a495370119979c91afde98facbc0893001458c592156b77d7dee2e12c6","schema_version":"1.0","event_id":"sha256:d564e3a495370119979c91afde98facbc0893001458c592156b77d7dee2e12c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QDE7ASTYIKID3XO2J2UH243N67","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Bo Li, Boxin Wang, Ce Zhang, Fan Wu, Luka Rimanic, Yunhui Long","submitted_at":"2021-03-20T06:14:19Z","abstract_excerpt":"Recent success of deep neural networks (DNNs) hinges on the availability of large-scale dataset; however, training on such dataset often poses privacy risks for sensitive training information. In this paper, we aim to explore the power of generative models and gradient sparsity, and propose a scalable privacy-preserving generative model DATALENS. Comparing with the standard PATE privacy-preserving framework which allows teachers to vote on one-dimensional predictions, voting on the high dimensional gradient vectors is challenging in terms of privacy preservation. As dimension reduction techniq"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11109","kind":"arxiv","version":6},"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/2103.11109/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wiItEIQH7r/OJVI+Lj69Z15xBF5zVKcU3JqqZvjGzHFYiPUGJtlIAb/qPK25bckOKjryDqhtlDUdk+q4GeOwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:36:53.930805Z"},"content_sha256":"15aaf4e7c08271c670abce8dbc84d747b0211f77d0ab708b2237a12280bd8f3e","schema_version":"1.0","event_id":"sha256:15aaf4e7c08271c670abce8dbc84d747b0211f77d0ab708b2237a12280bd8f3e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QDE7ASTYIKID3XO2J2UH243N67/bundle.json","state_url":"https://pith.science/pith/QDE7ASTYIKID3XO2J2UH243N67/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QDE7ASTYIKID3XO2J2UH243N67/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T20:36:53Z","links":{"resolver":"https://pith.science/pith/QDE7ASTYIKID3XO2J2UH243N67","bundle":"https://pith.science/pith/QDE7ASTYIKID3XO2J2UH243N67/bundle.json","state":"https://pith.science/pith/QDE7ASTYIKID3XO2J2UH243N67/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QDE7ASTYIKID3XO2J2UH243N67/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QDE7ASTYIKID3XO2J2UH243N67","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":"69729d85cbf50adb78a52b55f1f85446ac441e1c190b36f45356d71d82f4ab29","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-20T06:14:19Z","title_canon_sha256":"fc0c801ffcf22b69e3866f0c02a5b22711a3b81f8f42d09b5f8e03562d661c68"},"schema_version":"1.0","source":{"id":"2103.11109","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.11109","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2103.11109v6","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11109","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"QDE7ASTYIKID","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"QDE7ASTYIKID3XO2","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"QDE7ASTY","created_at":"2026-07-05T04:08:56Z"}],"graph_snapshots":[{"event_id":"sha256:15aaf4e7c08271c670abce8dbc84d747b0211f77d0ab708b2237a12280bd8f3e","target":"graph","created_at":"2026-07-05T04:08:56Z","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/2103.11109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent success of deep neural networks (DNNs) hinges on the availability of large-scale dataset; however, training on such dataset often poses privacy risks for sensitive training information. In this paper, we aim to explore the power of generative models and gradient sparsity, and propose a scalable privacy-preserving generative model DATALENS. Comparing with the standard PATE privacy-preserving framework which allows teachers to vote on one-dimensional predictions, voting on the high dimensional gradient vectors is challenging in terms of privacy preservation. As dimension reduction techniq","authors_text":"Bo Li, Boxin Wang, Ce Zhang, Fan Wu, Luka Rimanic, Yunhui Long","cross_cats":["cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-20T06:14:19Z","title":"DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11109","kind":"arxiv","version":6},"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:d564e3a495370119979c91afde98facbc0893001458c592156b77d7dee2e12c6","target":"record","created_at":"2026-07-05T04:08:56Z","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":"69729d85cbf50adb78a52b55f1f85446ac441e1c190b36f45356d71d82f4ab29","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-20T06:14:19Z","title_canon_sha256":"fc0c801ffcf22b69e3866f0c02a5b22711a3b81f8f42d09b5f8e03562d661c68"},"schema_version":"1.0","source":{"id":"2103.11109","kind":"arxiv","version":6}},"canonical_sha256":"80c9f04a7842903dddda4ea87d736df7ecb3ef050221ea8be837c7f60a3864fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80c9f04a7842903dddda4ea87d736df7ecb3ef050221ea8be837c7f60a3864fd","first_computed_at":"2026-07-05T04:08:56.756183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:56.756183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I4+6vuriYAEGGw5YMyq5voti3CX0X6/jhgWzB1j1Xyy1GMtkfkty0qsMEYWungjRES7zTO14MqBKmm+4LkYmAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:56.756639Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.11109","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d564e3a495370119979c91afde98facbc0893001458c592156b77d7dee2e12c6","sha256:15aaf4e7c08271c670abce8dbc84d747b0211f77d0ab708b2237a12280bd8f3e"],"state_sha256":"12a2f135b842008cf4d19071df7bcfdac90911e4f3d53ea71a36034e8c057897"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dYOah/pkqYLBAp6N3KAo8keazOsTYkzuVTEQyR+0vu+oDkCDb3UJOQAMe6QHvklLKuEDPhvQG32k1nl5vycIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:36:53.935016Z","bundle_sha256":"bff099f5000bc39d38c5b28a6aad61046ed3693dc72edcc3273a0711cabac58f"}}