{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:GWMZNEIB5E743EUGAPF4YAWJJX","short_pith_number":"pith:GWMZNEIB","canonical_record":{"source":{"id":"1705.09476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-26T08:30:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"61272dfcc53874e5143df1bf5ebf660550c4bb06197b49263f0844eb1b7dfa5a","abstract_canon_sha256":"ba3363eb43a425263f3ee7f640934167fb8346d9a14898292e0aed40c3b329b0"},"schema_version":"1.0"},"canonical_sha256":"3599969101e93fcd928603cbcc02c94dc727b44afb4ec2854e592e14d299871c","source":{"kind":"arxiv","id":"1705.09476","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.09476","created_at":"2026-05-18T00:43:38Z"},{"alias_kind":"arxiv_version","alias_value":"1705.09476v1","created_at":"2026-05-18T00:43:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09476","created_at":"2026-05-18T00:43:38Z"},{"alias_kind":"pith_short_12","alias_value":"GWMZNEIB5E74","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GWMZNEIB5E743EUG","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GWMZNEIB","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:GWMZNEIB5E743EUGAPF4YAWJJX","target":"record","payload":{"canonical_record":{"source":{"id":"1705.09476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-26T08:30:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"61272dfcc53874e5143df1bf5ebf660550c4bb06197b49263f0844eb1b7dfa5a","abstract_canon_sha256":"ba3363eb43a425263f3ee7f640934167fb8346d9a14898292e0aed40c3b329b0"},"schema_version":"1.0"},"canonical_sha256":"3599969101e93fcd928603cbcc02c94dc727b44afb4ec2854e592e14d299871c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:38.610197Z","signature_b64":"R86WbcxJiGWRDdNqm0wRGLwaQ8F0UAkinCICnVO3hRv/hdumknRsRO40Es5Th3eX6ulbh6xSIDWVwM9JHUlVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3599969101e93fcd928603cbcc02c94dc727b44afb4ec2854e592e14d299871c","last_reissued_at":"2026-05-18T00:43:38.609759Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:38.609759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.09476","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":"2026-05-18T00:43:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mozJrWjPrj+Rv10kQp84rJqcVxJ3Ul/hobkGfqDSOzRN2c32YAYimUWJ/3B5ZLlYf/G2G2AdepxrtQ7ptaYoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T12:40:37.174987Z"},"content_sha256":"5bc07d558efeb5c8d27cafecfa794554823e849054beaf980b10bef89186420b","schema_version":"1.0","event_id":"sha256:5bc07d558efeb5c8d27cafecfa794554823e849054beaf980b10bef89186420b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:GWMZNEIB5E743EUGAPF4YAWJJX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Robust Features with Incremental Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Donghui Wang, Yanan Li","submitted_at":"2017-05-26T08:30:41Z","abstract_excerpt":"Automatically learning features, especially robust features, has attracted much attention in the machine learning community. In this paper, we propose a new method to learn non-linear robust features by taking advantage of the data manifold structure. We first follow the commonly used trick of the trade, that is learning robust features with artificially corrupted data, which are training samples with manually injected noise. Following the idea of the auto-encoder, we first assume features should contain much information to well reconstruct the input from its corrupted copies. However, merely "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09476","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":""},"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":"2026-05-18T00:43:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"82ll9MtG4+BOdMcjR8lDGEr4yKhCMZ9jhQvJnmC3vbXDg/osJ8kbUQhWP1ejYn79psCh2tkUPmU0XSmNnFYRCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T12:40:37.175347Z"},"content_sha256":"834480193f178484e84241d856d8620f2f93fa60db68f982acecaed348dac1a2","schema_version":"1.0","event_id":"sha256:834480193f178484e84241d856d8620f2f93fa60db68f982acecaed348dac1a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GWMZNEIB5E743EUGAPF4YAWJJX/bundle.json","state_url":"https://pith.science/pith/GWMZNEIB5E743EUGAPF4YAWJJX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GWMZNEIB5E743EUGAPF4YAWJJX/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":"2026-06-03T12:40:37Z","links":{"resolver":"https://pith.science/pith/GWMZNEIB5E743EUGAPF4YAWJJX","bundle":"https://pith.science/pith/GWMZNEIB5E743EUGAPF4YAWJJX/bundle.json","state":"https://pith.science/pith/GWMZNEIB5E743EUGAPF4YAWJJX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GWMZNEIB5E743EUGAPF4YAWJJX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GWMZNEIB5E743EUGAPF4YAWJJX","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":"ba3363eb43a425263f3ee7f640934167fb8346d9a14898292e0aed40c3b329b0","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-26T08:30:41Z","title_canon_sha256":"61272dfcc53874e5143df1bf5ebf660550c4bb06197b49263f0844eb1b7dfa5a"},"schema_version":"1.0","source":{"id":"1705.09476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.09476","created_at":"2026-05-18T00:43:38Z"},{"alias_kind":"arxiv_version","alias_value":"1705.09476v1","created_at":"2026-05-18T00:43:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09476","created_at":"2026-05-18T00:43:38Z"},{"alias_kind":"pith_short_12","alias_value":"GWMZNEIB5E74","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GWMZNEIB5E743EUG","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GWMZNEIB","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:834480193f178484e84241d856d8620f2f93fa60db68f982acecaed348dac1a2","target":"graph","created_at":"2026-05-18T00:43:38Z","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":"Automatically learning features, especially robust features, has attracted much attention in the machine learning community. In this paper, we propose a new method to learn non-linear robust features by taking advantage of the data manifold structure. We first follow the commonly used trick of the trade, that is learning robust features with artificially corrupted data, which are training samples with manually injected noise. Following the idea of the auto-encoder, we first assume features should contain much information to well reconstruct the input from its corrupted copies. However, merely ","authors_text":"Donghui Wang, Yanan Li","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-26T08:30:41Z","title":"Learning Robust Features with Incremental Auto-Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09476","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":"sha256:5bc07d558efeb5c8d27cafecfa794554823e849054beaf980b10bef89186420b","target":"record","created_at":"2026-05-18T00:43:38Z","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":"ba3363eb43a425263f3ee7f640934167fb8346d9a14898292e0aed40c3b329b0","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-26T08:30:41Z","title_canon_sha256":"61272dfcc53874e5143df1bf5ebf660550c4bb06197b49263f0844eb1b7dfa5a"},"schema_version":"1.0","source":{"id":"1705.09476","kind":"arxiv","version":1}},"canonical_sha256":"3599969101e93fcd928603cbcc02c94dc727b44afb4ec2854e592e14d299871c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3599969101e93fcd928603cbcc02c94dc727b44afb4ec2854e592e14d299871c","first_computed_at":"2026-05-18T00:43:38.609759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:38.609759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R86WbcxJiGWRDdNqm0wRGLwaQ8F0UAkinCICnVO3hRv/hdumknRsRO40Es5Th3eX6ulbh6xSIDWVwM9JHUlVBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:38.610197Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.09476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bc07d558efeb5c8d27cafecfa794554823e849054beaf980b10bef89186420b","sha256:834480193f178484e84241d856d8620f2f93fa60db68f982acecaed348dac1a2"],"state_sha256":"1a868e00673af31d86e279be933c9c3736aba67a27ad2adf9236c239fa041bec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nFBPm2ZFvgVNwmrG52QQv15nAjj6WLzhTWZg5yH1DARW0rGoCgDyYsA3wAz2jAgYdDKO1JP5J1jvNBAL7m+WCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T12:40:37.177411Z","bundle_sha256":"99792693e5b637c0afd8e0153f373209fd071124d3af3a5ac9fc860c4e588cd3"}}