{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:Q3AMBALHSP2QCRZB5EAPMVOHBE","short_pith_number":"pith:Q3AMBALH","canonical_record":{"source":{"id":"1611.02315","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-07T21:43:39Z","cross_cats_sorted":["cs.AI","cs.CC","cs.CR","math.ST","stat.TH"],"title_canon_sha256":"e5dd477a1bf5ffb5b0f0bce14e48c4e3dc361671eb228a2c1025c09898a8a667","abstract_canon_sha256":"a9b80c10035f787e691d5c93d4f42996dc1c7f7ccb6c6a1baec851ee28d37101"},"schema_version":"1.0"},"canonical_sha256":"86c0c0816793f5014721e900f655c7093beda775773cf795a760b5b4d446413a","source":{"kind":"arxiv","id":"1611.02315","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.02315","created_at":"2026-05-18T00:42:39Z"},{"alias_kind":"arxiv_version","alias_value":"1611.02315v2","created_at":"2026-05-18T00:42:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.02315","created_at":"2026-05-18T00:42:39Z"},{"alias_kind":"pith_short_12","alias_value":"Q3AMBALHSP2Q","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"Q3AMBALHSP2QCRZB","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"Q3AMBALH","created_at":"2026-05-18T12:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:Q3AMBALHSP2QCRZB5EAPMVOHBE","target":"record","payload":{"canonical_record":{"source":{"id":"1611.02315","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-07T21:43:39Z","cross_cats_sorted":["cs.AI","cs.CC","cs.CR","math.ST","stat.TH"],"title_canon_sha256":"e5dd477a1bf5ffb5b0f0bce14e48c4e3dc361671eb228a2c1025c09898a8a667","abstract_canon_sha256":"a9b80c10035f787e691d5c93d4f42996dc1c7f7ccb6c6a1baec851ee28d37101"},"schema_version":"1.0"},"canonical_sha256":"86c0c0816793f5014721e900f655c7093beda775773cf795a760b5b4d446413a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:39.293503Z","signature_b64":"rEIPtgFyNBNRNuYamAYIWVx/4TuBB8Ln8c1kTq1lFsYavx2rvZI2PMO6YYuhA+PKK0YU1HP0ICS3czDurTJdAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86c0c0816793f5014721e900f655c7093beda775773cf795a760b5b4d446413a","last_reissued_at":"2026-05-18T00:42:39.292773Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:39.292773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.02315","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:42:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WdgoJsc1YXNdTZOMnfCWWKjjdYTqBsO478x0IwXxrNrO2OHhrOtU6mIZ95+5vCdOYQn0vpneNzThyCvucRvdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T23:52:54.775417Z"},"content_sha256":"201c4bd71a318afc98d6519f109f6f07a76a439951a9179e326c105f921ef0d1","schema_version":"1.0","event_id":"sha256:201c4bd71a318afc98d6519f109f6f07a76a439951a9179e326c105f921ef0d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:Q3AMBALHSP2QCRZB5EAPMVOHBE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning from Untrusted Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CC","cs.CR","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Gregory Valiant, Jacob Steinhardt, Moses Charikar","submitted_at":"2016-11-07T21:43:39Z","abstract_excerpt":"The vast majority of theoretical results in machine learning and statistics assume that the available training data is a reasonably reliable reflection of the phenomena to be learned or estimated. Similarly, the majority of machine learning and statistical techniques used in practice are brittle to the presence of large amounts of biased or malicious data. In this work we consider two frameworks in which to study estimation, learning, and optimization in the presence of significant fractions of arbitrary data.\n  The first framework, list-decodable learning, asks whether it is possible to retur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.02315","kind":"arxiv","version":2},"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":"2026-05-18T00:42:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4yZr9cVHgvgugb+fiA5OFKsSVcWYRXLP39Szweo1vTnbH3Aw+xquj2NddKG6tUNBb2Sg4yRo+QEfRMHKGsxhCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T23:52:54.776076Z"},"content_sha256":"3dabf915f6cff072b6db6e8b3f3bc13c7f9082585a9ff07d4222ec94bda63ddd","schema_version":"1.0","event_id":"sha256:3dabf915f6cff072b6db6e8b3f3bc13c7f9082585a9ff07d4222ec94bda63ddd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q3AMBALHSP2QCRZB5EAPMVOHBE/bundle.json","state_url":"https://pith.science/pith/Q3AMBALHSP2QCRZB5EAPMVOHBE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q3AMBALHSP2QCRZB5EAPMVOHBE/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":"2026-05-30T23:52:54Z","links":{"resolver":"https://pith.science/pith/Q3AMBALHSP2QCRZB5EAPMVOHBE","bundle":"https://pith.science/pith/Q3AMBALHSP2QCRZB5EAPMVOHBE/bundle.json","state":"https://pith.science/pith/Q3AMBALHSP2QCRZB5EAPMVOHBE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q3AMBALHSP2QCRZB5EAPMVOHBE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:Q3AMBALHSP2QCRZB5EAPMVOHBE","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":"a9b80c10035f787e691d5c93d4f42996dc1c7f7ccb6c6a1baec851ee28d37101","cross_cats_sorted":["cs.AI","cs.CC","cs.CR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-07T21:43:39Z","title_canon_sha256":"e5dd477a1bf5ffb5b0f0bce14e48c4e3dc361671eb228a2c1025c09898a8a667"},"schema_version":"1.0","source":{"id":"1611.02315","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.02315","created_at":"2026-05-18T00:42:39Z"},{"alias_kind":"arxiv_version","alias_value":"1611.02315v2","created_at":"2026-05-18T00:42:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.02315","created_at":"2026-05-18T00:42:39Z"},{"alias_kind":"pith_short_12","alias_value":"Q3AMBALHSP2Q","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"Q3AMBALHSP2QCRZB","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"Q3AMBALH","created_at":"2026-05-18T12:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:3dabf915f6cff072b6db6e8b3f3bc13c7f9082585a9ff07d4222ec94bda63ddd","target":"graph","created_at":"2026-05-18T00:42:39Z","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":"The vast majority of theoretical results in machine learning and statistics assume that the available training data is a reasonably reliable reflection of the phenomena to be learned or estimated. Similarly, the majority of machine learning and statistical techniques used in practice are brittle to the presence of large amounts of biased or malicious data. In this work we consider two frameworks in which to study estimation, learning, and optimization in the presence of significant fractions of arbitrary data.\n  The first framework, list-decodable learning, asks whether it is possible to retur","authors_text":"Gregory Valiant, Jacob Steinhardt, Moses Charikar","cross_cats":["cs.AI","cs.CC","cs.CR","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-07T21:43:39Z","title":"Learning from Untrusted Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.02315","kind":"arxiv","version":2},"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":"sha256:201c4bd71a318afc98d6519f109f6f07a76a439951a9179e326c105f921ef0d1","target":"record","created_at":"2026-05-18T00:42:39Z","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":"a9b80c10035f787e691d5c93d4f42996dc1c7f7ccb6c6a1baec851ee28d37101","cross_cats_sorted":["cs.AI","cs.CC","cs.CR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-07T21:43:39Z","title_canon_sha256":"e5dd477a1bf5ffb5b0f0bce14e48c4e3dc361671eb228a2c1025c09898a8a667"},"schema_version":"1.0","source":{"id":"1611.02315","kind":"arxiv","version":2}},"canonical_sha256":"86c0c0816793f5014721e900f655c7093beda775773cf795a760b5b4d446413a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86c0c0816793f5014721e900f655c7093beda775773cf795a760b5b4d446413a","first_computed_at":"2026-05-18T00:42:39.292773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:39.292773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rEIPtgFyNBNRNuYamAYIWVx/4TuBB8Ln8c1kTq1lFsYavx2rvZI2PMO6YYuhA+PKK0YU1HP0ICS3czDurTJdAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:39.293503Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.02315","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:201c4bd71a318afc98d6519f109f6f07a76a439951a9179e326c105f921ef0d1","sha256:3dabf915f6cff072b6db6e8b3f3bc13c7f9082585a9ff07d4222ec94bda63ddd"],"state_sha256":"958e634bfe4de7fb3acfb2a651f4d03923810520e51e5344dc3737a28a08c886"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+IyAALDemOpXWf6aqOvmXuXBTUhFo2h3t+ObkydeuymPR5BR0ShaYaPTZ/7zDEDKp1y/D7G1SVSG1+sH0KMlCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T23:52:54.780714Z","bundle_sha256":"f6a0338006f032128b340eb3a735407f5e570e0a308e4ca3696e2d6f689f9ddc"}}