{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ISW4NGQZXJ3KDDXLVPT4D5YJJE","short_pith_number":"pith:ISW4NGQZ","canonical_record":{"source":{"id":"2112.06134","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-12-12T03:11:23Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"98cdd8aa015d8a9b6f1158223485d69ac676e1f4fe3ae48eb2e6435d182d42d4","abstract_canon_sha256":"e64527d3eb24b4eb0cf9c5bda45a2f69e6d1cff97310ce75b841b983f59dc69c"},"schema_version":"1.0"},"canonical_sha256":"44adc69a19ba76a18eebabe7c1f709492db4b31f5b064b1ee76c5b684b7d7cc9","source":{"kind":"arxiv","id":"2112.06134","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.06134","created_at":"2026-07-05T04:01:58Z"},{"alias_kind":"arxiv_version","alias_value":"2112.06134v2","created_at":"2026-07-05T04:01:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06134","created_at":"2026-07-05T04:01:58Z"},{"alias_kind":"pith_short_12","alias_value":"ISW4NGQZXJ3K","created_at":"2026-07-05T04:01:58Z"},{"alias_kind":"pith_short_16","alias_value":"ISW4NGQZXJ3KDDXL","created_at":"2026-07-05T04:01:58Z"},{"alias_kind":"pith_short_8","alias_value":"ISW4NGQZ","created_at":"2026-07-05T04:01:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ISW4NGQZXJ3KDDXLVPT4D5YJJE","target":"record","payload":{"canonical_record":{"source":{"id":"2112.06134","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-12-12T03:11:23Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"98cdd8aa015d8a9b6f1158223485d69ac676e1f4fe3ae48eb2e6435d182d42d4","abstract_canon_sha256":"e64527d3eb24b4eb0cf9c5bda45a2f69e6d1cff97310ce75b841b983f59dc69c"},"schema_version":"1.0"},"canonical_sha256":"44adc69a19ba76a18eebabe7c1f709492db4b31f5b064b1ee76c5b684b7d7cc9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:58.112942Z","signature_b64":"207la9kVxmk3HCFcc2BcMArj9QJdp00TNrksaqewPWn0Fc6Rc5HV15MdPa4/g/W9m3DmYjsBXNI+lkDZPWdDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44adc69a19ba76a18eebabe7c1f709492db4b31f5b064b1ee76c5b684b7d7cc9","last_reissued_at":"2026-07-05T04:01:58.112492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:58.112492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.06134","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":"2026-07-05T04:01:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dl5WlCNkchmO5dJ5TzBKShNjR2AEkNHzS6VWWefg/avlHb6TkPzwn2eU2wiy3lBLk3lZBll7N9A3MNR8/UnhAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:45:49.400545Z"},"content_sha256":"76675d4a67422f49bfb2e9a3ef68461d0242a955e5e784783ca8545574b874b5","schema_version":"1.0","event_id":"sha256:76675d4a67422f49bfb2e9a3ef68461d0242a955e5e784783ca8545574b874b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ISW4NGQZXJ3KDDXLVPT4D5YJJE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Markov subsampling based Huber Criterion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Bo Dong, Chen Li, Hong Chen, Tieliang Gong, Yuxin Dong","submitted_at":"2021-12-12T03:11:23Z","abstract_excerpt":"Subsampling is an important technique to tackle the computational challenges brought by big data. Many subsampling procedures fall within the framework of importance sampling, which assigns high sampling probabilities to the samples appearing to have big impacts. When the noise level is high, those sampling procedures tend to pick many outliers and thus often do not perform satisfactorily in practice. To tackle this issue, we design a new Markov subsampling strategy based on Huber criterion (HMS) to construct an informative subset from the noisy full data; the constructed subset then serves as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06134","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.06134/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":"2026-07-05T04:01:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HDRpsdShePDBWayo4Dytd+fsmVSgX7BPTdKCMHFKSRuhJ7h81aVpkeeFDmeQ4fDR46BoYELIwHTCvnZWKhTkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:45:49.401449Z"},"content_sha256":"f0e2eb89183f23b0a2f59968f75c9065e89411ce08c7f3f7b03e453295f8d912","schema_version":"1.0","event_id":"sha256:f0e2eb89183f23b0a2f59968f75c9065e89411ce08c7f3f7b03e453295f8d912"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ISW4NGQZXJ3KDDXLVPT4D5YJJE/bundle.json","state_url":"https://pith.science/pith/ISW4NGQZXJ3KDDXLVPT4D5YJJE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ISW4NGQZXJ3KDDXLVPT4D5YJJE/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":"2026-08-20T10:45:49Z","links":{"resolver":"https://pith.science/pith/ISW4NGQZXJ3KDDXLVPT4D5YJJE","bundle":"https://pith.science/pith/ISW4NGQZXJ3KDDXLVPT4D5YJJE/bundle.json","state":"https://pith.science/pith/ISW4NGQZXJ3KDDXLVPT4D5YJJE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ISW4NGQZXJ3KDDXLVPT4D5YJJE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ISW4NGQZXJ3KDDXLVPT4D5YJJE","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":"e64527d3eb24b4eb0cf9c5bda45a2f69e6d1cff97310ce75b841b983f59dc69c","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-12-12T03:11:23Z","title_canon_sha256":"98cdd8aa015d8a9b6f1158223485d69ac676e1f4fe3ae48eb2e6435d182d42d4"},"schema_version":"1.0","source":{"id":"2112.06134","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.06134","created_at":"2026-07-05T04:01:58Z"},{"alias_kind":"arxiv_version","alias_value":"2112.06134v2","created_at":"2026-07-05T04:01:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06134","created_at":"2026-07-05T04:01:58Z"},{"alias_kind":"pith_short_12","alias_value":"ISW4NGQZXJ3K","created_at":"2026-07-05T04:01:58Z"},{"alias_kind":"pith_short_16","alias_value":"ISW4NGQZXJ3KDDXL","created_at":"2026-07-05T04:01:58Z"},{"alias_kind":"pith_short_8","alias_value":"ISW4NGQZ","created_at":"2026-07-05T04:01:58Z"}],"graph_snapshots":[{"event_id":"sha256:f0e2eb89183f23b0a2f59968f75c9065e89411ce08c7f3f7b03e453295f8d912","target":"graph","created_at":"2026-07-05T04:01:58Z","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/2112.06134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Subsampling is an important technique to tackle the computational challenges brought by big data. Many subsampling procedures fall within the framework of importance sampling, which assigns high sampling probabilities to the samples appearing to have big impacts. When the noise level is high, those sampling procedures tend to pick many outliers and thus often do not perform satisfactorily in practice. To tackle this issue, we design a new Markov subsampling strategy based on Huber criterion (HMS) to construct an informative subset from the noisy full data; the constructed subset then serves as","authors_text":"Bo Dong, Chen Li, Hong Chen, Tieliang Gong, Yuxin Dong","cross_cats":["cs.LG","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-12-12T03:11:23Z","title":"Markov subsampling based Huber Criterion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06134","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":"sha256:76675d4a67422f49bfb2e9a3ef68461d0242a955e5e784783ca8545574b874b5","target":"record","created_at":"2026-07-05T04:01:58Z","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":"e64527d3eb24b4eb0cf9c5bda45a2f69e6d1cff97310ce75b841b983f59dc69c","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-12-12T03:11:23Z","title_canon_sha256":"98cdd8aa015d8a9b6f1158223485d69ac676e1f4fe3ae48eb2e6435d182d42d4"},"schema_version":"1.0","source":{"id":"2112.06134","kind":"arxiv","version":2}},"canonical_sha256":"44adc69a19ba76a18eebabe7c1f709492db4b31f5b064b1ee76c5b684b7d7cc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44adc69a19ba76a18eebabe7c1f709492db4b31f5b064b1ee76c5b684b7d7cc9","first_computed_at":"2026-07-05T04:01:58.112492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:58.112492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"207la9kVxmk3HCFcc2BcMArj9QJdp00TNrksaqewPWn0Fc6Rc5HV15MdPa4/g/W9m3DmYjsBXNI+lkDZPWdDBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:58.112942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.06134","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76675d4a67422f49bfb2e9a3ef68461d0242a955e5e784783ca8545574b874b5","sha256:f0e2eb89183f23b0a2f59968f75c9065e89411ce08c7f3f7b03e453295f8d912"],"state_sha256":"82c049d57c2e58d5e147ba6aa0c63d423431d92ac35742cb5e5637fb8d09485a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WXvqNwJHkWdKyCKY+rgmy7pUCyxlm8c981OLUe2/4AR3QEaUsuoxiY9zA7qdREE2rJbO1dyp9O3BcDczqZ+LBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T10:45:49.408235Z","bundle_sha256":"45ef373a90c3ac4cb8a7cfe47a29ed4598f20c0990b32475efb2f9ba9928e709"}}