{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:W3OMZEO66QNKEKHSXAL5MPJXQY","short_pith_number":"pith:W3OMZEO6","canonical_record":{"source":{"id":"2002.10477","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-24T19:01:47Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"e92add50399b1022bf8ffc2a4ab26e3cdfe3551e41cdf193ab4ba87e087d171f","abstract_canon_sha256":"3ca5f9195b34fa3ea7b10fc1ab1f4f1f58ac5e3e65c14f506d1b04f472af0a79"},"schema_version":"1.0"},"canonical_sha256":"b6dccc91def41aa228f2b817d63d378630571192c71fe24f4970a17244c0de13","source":{"kind":"arxiv","id":"2002.10477","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.10477","created_at":"2026-07-05T00:43:22Z"},{"alias_kind":"arxiv_version","alias_value":"2002.10477v1","created_at":"2026-07-05T00:43:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10477","created_at":"2026-07-05T00:43:22Z"},{"alias_kind":"pith_short_12","alias_value":"W3OMZEO66QNK","created_at":"2026-07-05T00:43:22Z"},{"alias_kind":"pith_short_16","alias_value":"W3OMZEO66QNKEKHS","created_at":"2026-07-05T00:43:22Z"},{"alias_kind":"pith_short_8","alias_value":"W3OMZEO6","created_at":"2026-07-05T00:43:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:W3OMZEO66QNKEKHSXAL5MPJXQY","target":"record","payload":{"canonical_record":{"source":{"id":"2002.10477","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-24T19:01:47Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"e92add50399b1022bf8ffc2a4ab26e3cdfe3551e41cdf193ab4ba87e087d171f","abstract_canon_sha256":"3ca5f9195b34fa3ea7b10fc1ab1f4f1f58ac5e3e65c14f506d1b04f472af0a79"},"schema_version":"1.0"},"canonical_sha256":"b6dccc91def41aa228f2b817d63d378630571192c71fe24f4970a17244c0de13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:22.414858Z","signature_b64":"vFPD6iRYIJMMfpRsRckFvqDousUwvZdUPDeIfS65OWuuld3BNvtM/lph9ykw90X/alcuV76TNupmTl+szMEYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6dccc91def41aa228f2b817d63d378630571192c71fe24f4970a17244c0de13","last_reissued_at":"2026-07-05T00:43:22.414435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:22.414435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.10477","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:43:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yTwRwpt1pdnnW3wgq3nF905y3hmZMtq527XP5x5LfcpmP+gcccNJpva/VY1Y0yivQl0TPKOcYB2sVPB+aEsJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:57:46.277536Z"},"content_sha256":"704640e2eb931dfaa1cd231ec1b0a7461e76f35db713ab1a48e7d364c7b4f502","schema_version":"1.0","event_id":"sha256:704640e2eb931dfaa1cd231ec1b0a7461e76f35db713ab1a48e7d364c7b4f502"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:W3OMZEO66QNKEKHSXAL5MPJXQY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Precise Tradeoffs in Adversarial Training for Linear Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adel Javanmard, Hamed Hassani, Mahdi Soltanolkotabi","submitted_at":"2020-02-24T19:01:47Z","abstract_excerpt":"Despite breakthrough performance, modern learning models are known to be highly vulnerable to small adversarial perturbations in their inputs. While a wide variety of recent \\emph{adversarial training} methods have been effective at improving robustness to perturbed inputs (robust accuracy), often this benefit is accompanied by a decrease in accuracy on benign inputs (standard accuracy), leading to a tradeoff between often competing objectives. Complicating matters further, recent empirical evidence suggest that a variety of other factors (size and quality of training data, model size, etc.) a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10477","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/2002.10477/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":"2026-07-05T00:43:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TjEfJfwUbkbyvwMmfTCL1t8gyg5VP5XDW9YwXFnl1OAEN9d3ARWlI7vqY+UZpBlODQ6RguZXedyKWpCy4G9gDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:57:46.277895Z"},"content_sha256":"4752425d822d5f9cf3e9988edafa5ac26c56ba6a1cf01d62ed905550534fde05","schema_version":"1.0","event_id":"sha256:4752425d822d5f9cf3e9988edafa5ac26c56ba6a1cf01d62ed905550534fde05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W3OMZEO66QNKEKHSXAL5MPJXQY/bundle.json","state_url":"https://pith.science/pith/W3OMZEO66QNKEKHSXAL5MPJXQY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W3OMZEO66QNKEKHSXAL5MPJXQY/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":"2026-07-05T11:57:46Z","links":{"resolver":"https://pith.science/pith/W3OMZEO66QNKEKHSXAL5MPJXQY","bundle":"https://pith.science/pith/W3OMZEO66QNKEKHSXAL5MPJXQY/bundle.json","state":"https://pith.science/pith/W3OMZEO66QNKEKHSXAL5MPJXQY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W3OMZEO66QNKEKHSXAL5MPJXQY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:W3OMZEO66QNKEKHSXAL5MPJXQY","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":"3ca5f9195b34fa3ea7b10fc1ab1f4f1f58ac5e3e65c14f506d1b04f472af0a79","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-24T19:01:47Z","title_canon_sha256":"e92add50399b1022bf8ffc2a4ab26e3cdfe3551e41cdf193ab4ba87e087d171f"},"schema_version":"1.0","source":{"id":"2002.10477","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.10477","created_at":"2026-07-05T00:43:22Z"},{"alias_kind":"arxiv_version","alias_value":"2002.10477v1","created_at":"2026-07-05T00:43:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10477","created_at":"2026-07-05T00:43:22Z"},{"alias_kind":"pith_short_12","alias_value":"W3OMZEO66QNK","created_at":"2026-07-05T00:43:22Z"},{"alias_kind":"pith_short_16","alias_value":"W3OMZEO66QNKEKHS","created_at":"2026-07-05T00:43:22Z"},{"alias_kind":"pith_short_8","alias_value":"W3OMZEO6","created_at":"2026-07-05T00:43:22Z"}],"graph_snapshots":[{"event_id":"sha256:4752425d822d5f9cf3e9988edafa5ac26c56ba6a1cf01d62ed905550534fde05","target":"graph","created_at":"2026-07-05T00:43:22Z","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/2002.10477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite breakthrough performance, modern learning models are known to be highly vulnerable to small adversarial perturbations in their inputs. While a wide variety of recent \\emph{adversarial training} methods have been effective at improving robustness to perturbed inputs (robust accuracy), often this benefit is accompanied by a decrease in accuracy on benign inputs (standard accuracy), leading to a tradeoff between often competing objectives. Complicating matters further, recent empirical evidence suggest that a variety of other factors (size and quality of training data, model size, etc.) a","authors_text":"Adel Javanmard, Hamed Hassani, Mahdi Soltanolkotabi","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-24T19:01:47Z","title":"Precise Tradeoffs in Adversarial Training for Linear Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10477","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":"sha256:704640e2eb931dfaa1cd231ec1b0a7461e76f35db713ab1a48e7d364c7b4f502","target":"record","created_at":"2026-07-05T00:43:22Z","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":"3ca5f9195b34fa3ea7b10fc1ab1f4f1f58ac5e3e65c14f506d1b04f472af0a79","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-24T19:01:47Z","title_canon_sha256":"e92add50399b1022bf8ffc2a4ab26e3cdfe3551e41cdf193ab4ba87e087d171f"},"schema_version":"1.0","source":{"id":"2002.10477","kind":"arxiv","version":1}},"canonical_sha256":"b6dccc91def41aa228f2b817d63d378630571192c71fe24f4970a17244c0de13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6dccc91def41aa228f2b817d63d378630571192c71fe24f4970a17244c0de13","first_computed_at":"2026-07-05T00:43:22.414435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:43:22.414435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vFPD6iRYIJMMfpRsRckFvqDousUwvZdUPDeIfS65OWuuld3BNvtM/lph9ykw90X/alcuV76TNupmTl+szMEYDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:43:22.414858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.10477","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:704640e2eb931dfaa1cd231ec1b0a7461e76f35db713ab1a48e7d364c7b4f502","sha256:4752425d822d5f9cf3e9988edafa5ac26c56ba6a1cf01d62ed905550534fde05"],"state_sha256":"81040584758b3ccdd28a1995953ab9ee8e743454600906bfe54cd843a51ebe18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jPlUP6qfTI+rDoDLmd9F8kSXy5N083rCr8dXuboxW1o2n7EKyNjgyZvMi3q8VQXmZkMTcYBCmE02SoCBq2R3Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T11:57:46.279764Z","bundle_sha256":"319f5336e269092d932e616bedcf8dbc78c347ad3cd51096abe3ff0625acc6a3"}}