{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:744NNGSWYRXO25ZY2E4PCMCFTD","short_pith_number":"pith:744NNGSW","canonical_record":{"source":{"id":"1610.01101","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-04T17:24:43Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"7a0e32db73ee2db29579a42833f52dc5b898788de773d47da6fe41ef4d6ac1a1","abstract_canon_sha256":"4e015811b92acff882f9fef626b151ab9e13b3d76e12cb5f6eb6073c380896bb"},"schema_version":"1.0"},"canonical_sha256":"ff38d69a56c46eed7738d138f1304598f60017fd481ee1f4dfc3362409f86e0b","source":{"kind":"arxiv","id":"1610.01101","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.01101","created_at":"2026-05-18T00:51:25Z"},{"alias_kind":"arxiv_version","alias_value":"1610.01101v2","created_at":"2026-05-18T00:51:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01101","created_at":"2026-05-18T00:51:25Z"},{"alias_kind":"pith_short_12","alias_value":"744NNGSWYRXO","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"744NNGSWYRXO25ZY","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"744NNGSW","created_at":"2026-05-18T12:30:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:744NNGSWYRXO25ZY2E4PCMCFTD","target":"record","payload":{"canonical_record":{"source":{"id":"1610.01101","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-04T17:24:43Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"7a0e32db73ee2db29579a42833f52dc5b898788de773d47da6fe41ef4d6ac1a1","abstract_canon_sha256":"4e015811b92acff882f9fef626b151ab9e13b3d76e12cb5f6eb6073c380896bb"},"schema_version":"1.0"},"canonical_sha256":"ff38d69a56c46eed7738d138f1304598f60017fd481ee1f4dfc3362409f86e0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:25.234547Z","signature_b64":"Ladv0aaUTEtPysd92rsd8+wMAGbuf9/DPMD1UxGL76jZNSF7hy0mp1o5ZX6w+Sl0ySz+N4YpEiA8PSEZNInZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff38d69a56c46eed7738d138f1304598f60017fd481ee1f4dfc3362409f86e0b","last_reissued_at":"2026-05-18T00:51:25.234052Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:25.234052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.01101","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":"2026-05-18T00:51:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vKBKu4mThocBX7KCtxqoEZkkmMmRhysvK4Rm8FYAb9xAwuCRUIF2sEZ27eJ3jc+DuXF7EY3vofI8fGRaBpQtCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:30:37.294472Z"},"content_sha256":"d1f2bcc9e0f4313261fc75611a38b204679f89f1b26738f2e5930cc2234b55fe","schema_version":"1.0","event_id":"sha256:d1f2bcc9e0f4313261fc75611a38b204679f89f1b26738f2e5930cc2234b55fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:744NNGSWYRXO25ZY2E4PCMCFTD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A SMART Stochastic Algorithm for Nonconvex Optimization with Applications to Robust Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Aleksandr Aravkin, Damek Davis","submitted_at":"2016-10-04T17:24:43Z","abstract_excerpt":"In this paper, we show how to transform any optimization problem that arises from fitting a machine learning model into one that (1) detects and removes contaminated data from the training set while (2) simultaneously fitting the trimmed model on the uncontaminated data that remains. To solve the resulting nonconvex optimization problem, we introduce a fast stochastic proximal-gradient algorithm that incorporates prior knowledge through nonsmooth regularization. For datasets of size $n$, our approach requires $O(n^{2/3}/\\varepsilon)$ gradient evaluations to reach $\\varepsilon$-accuracy and, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.01101","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":"2026-05-18T00:51:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fGonTLIquCeZXAjcA+DBEPDu4050UwzV8CeboyAQZ3myZJV3FQRRJOb7CUyjbi9OdgnycZhMHImoOMsbjP5FBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:30:37.295240Z"},"content_sha256":"99db679a5c6e06c41d42a4394d47d3f53258f66a1c214dcf287b289f666f54f6","schema_version":"1.0","event_id":"sha256:99db679a5c6e06c41d42a4394d47d3f53258f66a1c214dcf287b289f666f54f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/744NNGSWYRXO25ZY2E4PCMCFTD/bundle.json","state_url":"https://pith.science/pith/744NNGSWYRXO25ZY2E4PCMCFTD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/744NNGSWYRXO25ZY2E4PCMCFTD/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":"2026-06-07T21:30:37Z","links":{"resolver":"https://pith.science/pith/744NNGSWYRXO25ZY2E4PCMCFTD","bundle":"https://pith.science/pith/744NNGSWYRXO25ZY2E4PCMCFTD/bundle.json","state":"https://pith.science/pith/744NNGSWYRXO25ZY2E4PCMCFTD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/744NNGSWYRXO25ZY2E4PCMCFTD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:744NNGSWYRXO25ZY2E4PCMCFTD","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":"4e015811b92acff882f9fef626b151ab9e13b3d76e12cb5f6eb6073c380896bb","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-04T17:24:43Z","title_canon_sha256":"7a0e32db73ee2db29579a42833f52dc5b898788de773d47da6fe41ef4d6ac1a1"},"schema_version":"1.0","source":{"id":"1610.01101","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.01101","created_at":"2026-05-18T00:51:25Z"},{"alias_kind":"arxiv_version","alias_value":"1610.01101v2","created_at":"2026-05-18T00:51:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01101","created_at":"2026-05-18T00:51:25Z"},{"alias_kind":"pith_short_12","alias_value":"744NNGSWYRXO","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"744NNGSWYRXO25ZY","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"744NNGSW","created_at":"2026-05-18T12:30:04Z"}],"graph_snapshots":[{"event_id":"sha256:99db679a5c6e06c41d42a4394d47d3f53258f66a1c214dcf287b289f666f54f6","target":"graph","created_at":"2026-05-18T00:51:25Z","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":"In this paper, we show how to transform any optimization problem that arises from fitting a machine learning model into one that (1) detects and removes contaminated data from the training set while (2) simultaneously fitting the trimmed model on the uncontaminated data that remains. To solve the resulting nonconvex optimization problem, we introduce a fast stochastic proximal-gradient algorithm that incorporates prior knowledge through nonsmooth regularization. For datasets of size $n$, our approach requires $O(n^{2/3}/\\varepsilon)$ gradient evaluations to reach $\\varepsilon$-accuracy and, wh","authors_text":"Aleksandr Aravkin, Damek Davis","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-04T17:24:43Z","title":"A SMART Stochastic Algorithm for Nonconvex Optimization with Applications to Robust Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.01101","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:d1f2bcc9e0f4313261fc75611a38b204679f89f1b26738f2e5930cc2234b55fe","target":"record","created_at":"2026-05-18T00:51:25Z","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":"4e015811b92acff882f9fef626b151ab9e13b3d76e12cb5f6eb6073c380896bb","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-04T17:24:43Z","title_canon_sha256":"7a0e32db73ee2db29579a42833f52dc5b898788de773d47da6fe41ef4d6ac1a1"},"schema_version":"1.0","source":{"id":"1610.01101","kind":"arxiv","version":2}},"canonical_sha256":"ff38d69a56c46eed7738d138f1304598f60017fd481ee1f4dfc3362409f86e0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff38d69a56c46eed7738d138f1304598f60017fd481ee1f4dfc3362409f86e0b","first_computed_at":"2026-05-18T00:51:25.234052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:51:25.234052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ladv0aaUTEtPysd92rsd8+wMAGbuf9/DPMD1UxGL76jZNSF7hy0mp1o5ZX6w+Sl0ySz+N4YpEiA8PSEZNInZAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:51:25.234547Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.01101","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1f2bcc9e0f4313261fc75611a38b204679f89f1b26738f2e5930cc2234b55fe","sha256:99db679a5c6e06c41d42a4394d47d3f53258f66a1c214dcf287b289f666f54f6"],"state_sha256":"08fb633a464713ede81d7e9a70170d4ad039e4c218b48b3922082dba7ce66fca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MwUj3fJTS/gb3WzR8uwG6YAU5m+uJ1bhmIoOIwT2wPNsOVfgH/IfhRu1cGAYUhXsOO0GIpQ46mxXQbJH9VUpBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T21:30:37.299051Z","bundle_sha256":"581c4671f1e4cb35408c871f3ce241188b7faa19d309a8b01c6c7fa1a5c09852"}}