{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:RDCDYQHQEJ2BOVNJBDKJYQKLXS","short_pith_number":"pith:RDCDYQHQ","canonical_record":{"source":{"id":"1411.5417","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-11-20T01:33:53Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"82def0a93794217ac02a270ae161d07c50a5ad83161cf5f66672cda3bdebba48","abstract_canon_sha256":"571358620c694e7f33ea1d861229dfac69f173fbcec6aaac8737b13f9789ebb9"},"schema_version":"1.0"},"canonical_sha256":"88c43c40f022741755a908d49c414bbca0f937558ecce03d365a28c33ec23a26","source":{"kind":"arxiv","id":"1411.5417","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1411.5417","created_at":"2026-05-18T00:57:38Z"},{"alias_kind":"arxiv_version","alias_value":"1411.5417v3","created_at":"2026-05-18T00:57:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.5417","created_at":"2026-05-18T00:57:38Z"},{"alias_kind":"pith_short_12","alias_value":"RDCDYQHQEJ2B","created_at":"2026-05-18T12:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"RDCDYQHQEJ2BOVNJ","created_at":"2026-05-18T12:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"RDCDYQHQ","created_at":"2026-05-18T12:28:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:RDCDYQHQEJ2BOVNJBDKJYQKLXS","target":"record","payload":{"canonical_record":{"source":{"id":"1411.5417","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-11-20T01:33:53Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"82def0a93794217ac02a270ae161d07c50a5ad83161cf5f66672cda3bdebba48","abstract_canon_sha256":"571358620c694e7f33ea1d861229dfac69f173fbcec6aaac8737b13f9789ebb9"},"schema_version":"1.0"},"canonical_sha256":"88c43c40f022741755a908d49c414bbca0f937558ecce03d365a28c33ec23a26","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:38.462291Z","signature_b64":"2dKR226Q0cLruvEoa7FP5666qlaHQq7YqrQ/CWzbyiqwMn972ezHJ/4jH6O1K0QjEmoGt5UrRWCKAxRMe1v0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88c43c40f022741755a908d49c414bbca0f937558ecce03d365a28c33ec23a26","last_reissued_at":"2026-05-18T00:57:38.461455Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:38.461455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1411.5417","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:57:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"93WKopxWbu7T1J4bGQboakeD2Wiik3IdM0krkDM5fvpZDR57KLYQB2QV00SwQ9bc9KhthnNM04vIthcF1IgmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T15:31:51.768137Z"},"content_sha256":"89f2d211ecf0a9bf118d92209f74c1bcfdade36f3fb0f1946c4329a78a6fbb1f","schema_version":"1.0","event_id":"sha256:89f2d211ecf0a9bf118d92209f74c1bcfdade36f3fb0f1946c4329a78a6fbb1f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:RDCDYQHQEJ2BOVNJBDKJYQKLXS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhradeep Thakurta, Kunal Talwar, Li Zhang","submitted_at":"2014-11-20T01:33:53Z","abstract_excerpt":"Empirical Risk Minimization (ERM) is a standard technique in machine learning, where a model is selected by minimizing a loss function over constraint set. When the training dataset consists of private information, it is natural to use a differentially private ERM algorithm, and this problem has been the subject of a long line of work started with Chaudhuri and Monteleoni 2008. A private ERM algorithm outputs an approximate minimizer of the loss function and its error can be measured as the difference from the optimal value of the loss function. When the constraint set is arbitrary, the requir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.5417","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:57:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DkScI0fabH091KYgg4T0PPE3pnBhvAn4IzYc5uNzaS2bL0mRGiSiytJeYQoNcXEZZkSv18PpNeUxI9ZA9iKICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T15:31:51.768512Z"},"content_sha256":"50ca5c88493674dcff81c2e234579b3a4a03e93690ffd7e87e315c6e22e3db74","schema_version":"1.0","event_id":"sha256:50ca5c88493674dcff81c2e234579b3a4a03e93690ffd7e87e315c6e22e3db74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RDCDYQHQEJ2BOVNJBDKJYQKLXS/bundle.json","state_url":"https://pith.science/pith/RDCDYQHQEJ2BOVNJBDKJYQKLXS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RDCDYQHQEJ2BOVNJBDKJYQKLXS/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":"2026-06-05T15:31:51Z","links":{"resolver":"https://pith.science/pith/RDCDYQHQEJ2BOVNJBDKJYQKLXS","bundle":"https://pith.science/pith/RDCDYQHQEJ2BOVNJBDKJYQKLXS/bundle.json","state":"https://pith.science/pith/RDCDYQHQEJ2BOVNJBDKJYQKLXS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RDCDYQHQEJ2BOVNJBDKJYQKLXS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:RDCDYQHQEJ2BOVNJBDKJYQKLXS","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":"571358620c694e7f33ea1d861229dfac69f173fbcec6aaac8737b13f9789ebb9","cross_cats_sorted":["cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-11-20T01:33:53Z","title_canon_sha256":"82def0a93794217ac02a270ae161d07c50a5ad83161cf5f66672cda3bdebba48"},"schema_version":"1.0","source":{"id":"1411.5417","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1411.5417","created_at":"2026-05-18T00:57:38Z"},{"alias_kind":"arxiv_version","alias_value":"1411.5417v3","created_at":"2026-05-18T00:57:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.5417","created_at":"2026-05-18T00:57:38Z"},{"alias_kind":"pith_short_12","alias_value":"RDCDYQHQEJ2B","created_at":"2026-05-18T12:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"RDCDYQHQEJ2BOVNJ","created_at":"2026-05-18T12:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"RDCDYQHQ","created_at":"2026-05-18T12:28:46Z"}],"graph_snapshots":[{"event_id":"sha256:50ca5c88493674dcff81c2e234579b3a4a03e93690ffd7e87e315c6e22e3db74","target":"graph","created_at":"2026-05-18T00:57:38Z","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"},"paper":{"abstract_excerpt":"Empirical Risk Minimization (ERM) is a standard technique in machine learning, where a model is selected by minimizing a loss function over constraint set. When the training dataset consists of private information, it is natural to use a differentially private ERM algorithm, and this problem has been the subject of a long line of work started with Chaudhuri and Monteleoni 2008. A private ERM algorithm outputs an approximate minimizer of the loss function and its error can be measured as the difference from the optimal value of the loss function. When the constraint set is arbitrary, the requir","authors_text":"Abhradeep Thakurta, Kunal Talwar, Li Zhang","cross_cats":["cs.CR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-11-20T01:33:53Z","title":"Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.5417","kind":"arxiv","version":3},"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":"sha256:89f2d211ecf0a9bf118d92209f74c1bcfdade36f3fb0f1946c4329a78a6fbb1f","target":"record","created_at":"2026-05-18T00:57:38Z","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":"571358620c694e7f33ea1d861229dfac69f173fbcec6aaac8737b13f9789ebb9","cross_cats_sorted":["cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-11-20T01:33:53Z","title_canon_sha256":"82def0a93794217ac02a270ae161d07c50a5ad83161cf5f66672cda3bdebba48"},"schema_version":"1.0","source":{"id":"1411.5417","kind":"arxiv","version":3}},"canonical_sha256":"88c43c40f022741755a908d49c414bbca0f937558ecce03d365a28c33ec23a26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88c43c40f022741755a908d49c414bbca0f937558ecce03d365a28c33ec23a26","first_computed_at":"2026-05-18T00:57:38.461455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:57:38.461455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2dKR226Q0cLruvEoa7FP5666qlaHQq7YqrQ/CWzbyiqwMn972ezHJ/4jH6O1K0QjEmoGt5UrRWCKAxRMe1v0Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:57:38.462291Z","signed_message":"canonical_sha256_bytes"},"source_id":"1411.5417","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89f2d211ecf0a9bf118d92209f74c1bcfdade36f3fb0f1946c4329a78a6fbb1f","sha256:50ca5c88493674dcff81c2e234579b3a4a03e93690ffd7e87e315c6e22e3db74"],"state_sha256":"f48d71e30892ac2fc84aa2f2d4a1f502cf5a59bf1b600f7f576950feff5d7579"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NA5pCPE9pB6Rlannfq0onKCmSaJcXNBonwFc2Fv8sdehn8EO782r4AoSknHXR1jx2vW++drUYo2wYvnWOHO2AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T15:31:51.770505Z","bundle_sha256":"9040a95667f945d4cadfc1c5adb6905e603e7ef6e9556e26801a3d0eb180ca3b"}}