{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:3R44QGERLU3MWS5MCUBKUXTJLC","short_pith_number":"pith:3R44QGER","canonical_record":{"source":{"id":"2003.04286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-09T17:45:44Z","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"title_canon_sha256":"b60c7d3c2f9f73d9d18803467fea6e06a25f372ec62e0b93e29c7896212f99be","abstract_canon_sha256":"a5c104ba0d168bc0fab60ea6a4f5f869b66f8defa914b412a7954b6558dc84ec"},"schema_version":"1.0"},"canonical_sha256":"dc79c818915d36cb4bac1502aa5e6958bda07b39dd3931c4b92e7ad1655da9ae","source":{"kind":"arxiv","id":"2003.04286","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.04286","created_at":"2026-07-05T01:37:23Z"},{"alias_kind":"arxiv_version","alias_value":"2003.04286v2","created_at":"2026-07-05T01:37:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04286","created_at":"2026-07-05T01:37:23Z"},{"alias_kind":"pith_short_12","alias_value":"3R44QGERLU3M","created_at":"2026-07-05T01:37:23Z"},{"alias_kind":"pith_short_16","alias_value":"3R44QGERLU3MWS5M","created_at":"2026-07-05T01:37:23Z"},{"alias_kind":"pith_short_8","alias_value":"3R44QGER","created_at":"2026-07-05T01:37:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:3R44QGERLU3MWS5MCUBKUXTJLC","target":"record","payload":{"canonical_record":{"source":{"id":"2003.04286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-09T17:45:44Z","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"title_canon_sha256":"b60c7d3c2f9f73d9d18803467fea6e06a25f372ec62e0b93e29c7896212f99be","abstract_canon_sha256":"a5c104ba0d168bc0fab60ea6a4f5f869b66f8defa914b412a7954b6558dc84ec"},"schema_version":"1.0"},"canonical_sha256":"dc79c818915d36cb4bac1502aa5e6958bda07b39dd3931c4b92e7ad1655da9ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:23.764065Z","signature_b64":"FY3ebZ/+vYgM1fF2/y7yXC0jI/tVra3rkVlNIvf0DCPDl8i+mtgmYxIuFWV94bUHA9oMoscaYSYsS6iD3rLKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc79c818915d36cb4bac1502aa5e6958bda07b39dd3931c4b92e7ad1655da9ae","last_reissued_at":"2026-07-05T01:37:23.763507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:23.763507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.04286","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":"2026-07-05T01:37:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZWx0FPYJ/924uM86ZLqADLUN9yXg0kbPCK1Pwhmu6b/i/67ulW0qc6knA2Z/QKXpstxa8LBD/oNNLFk72VtKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:27:30.307219Z"},"content_sha256":"41aef8d5b8f69b64b0b5b56d8c97669068f1d71193ea5b71638e5fe0a583c5cb","schema_version":"1.0","event_id":"sha256:41aef8d5b8f69b64b0b5b56d8c97669068f1d71193ea5b71638e5fe0a583c5cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:3R44QGERLU3MWS5MCUBKUXTJLC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Manifold Regularization for Locally Stable Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Charles Jin, Martin Rinard","submitted_at":"2020-03-09T17:45:44Z","abstract_excerpt":"We apply concepts from manifold regularization to develop new regularization techniques for training locally stable deep neural networks. Our regularizers are based on a sparsification of the graph Laplacian which holds with high probability when the data is sparse in high dimensions, as is common in deep learning. Empirically, our networks exhibit stability in a diverse set of perturbation models, including $\\ell_2$, $\\ell_\\infty$, and Wasserstein-based perturbations; in particular, we achieve 40% adversarial accuracy on CIFAR-10 against an adaptive PGD attack using $\\ell_\\infty$ perturbation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04286","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/2003.04286/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":"2026-07-05T01:37:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H2EAo0/VR2WTRsaeQJs6fX8FRIauHhczqE4LinVj/T6lrjo6Q2NBRjKQx9I8Tz0B9sYM/+lxuidqXve3167AAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:27:30.308235Z"},"content_sha256":"946cbbe0c878555f29667c7240003956fa2c140609d2fd05fe496c6bb032827c","schema_version":"1.0","event_id":"sha256:946cbbe0c878555f29667c7240003956fa2c140609d2fd05fe496c6bb032827c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3R44QGERLU3MWS5MCUBKUXTJLC/bundle.json","state_url":"https://pith.science/pith/3R44QGERLU3MWS5MCUBKUXTJLC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3R44QGERLU3MWS5MCUBKUXTJLC/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":"2026-08-09T22:27:30Z","links":{"resolver":"https://pith.science/pith/3R44QGERLU3MWS5MCUBKUXTJLC","bundle":"https://pith.science/pith/3R44QGERLU3MWS5MCUBKUXTJLC/bundle.json","state":"https://pith.science/pith/3R44QGERLU3MWS5MCUBKUXTJLC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3R44QGERLU3MWS5MCUBKUXTJLC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3R44QGERLU3MWS5MCUBKUXTJLC","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":"a5c104ba0d168bc0fab60ea6a4f5f869b66f8defa914b412a7954b6558dc84ec","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-09T17:45:44Z","title_canon_sha256":"b60c7d3c2f9f73d9d18803467fea6e06a25f372ec62e0b93e29c7896212f99be"},"schema_version":"1.0","source":{"id":"2003.04286","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.04286","created_at":"2026-07-05T01:37:23Z"},{"alias_kind":"arxiv_version","alias_value":"2003.04286v2","created_at":"2026-07-05T01:37:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04286","created_at":"2026-07-05T01:37:23Z"},{"alias_kind":"pith_short_12","alias_value":"3R44QGERLU3M","created_at":"2026-07-05T01:37:23Z"},{"alias_kind":"pith_short_16","alias_value":"3R44QGERLU3MWS5M","created_at":"2026-07-05T01:37:23Z"},{"alias_kind":"pith_short_8","alias_value":"3R44QGER","created_at":"2026-07-05T01:37:23Z"}],"graph_snapshots":[{"event_id":"sha256:946cbbe0c878555f29667c7240003956fa2c140609d2fd05fe496c6bb032827c","target":"graph","created_at":"2026-07-05T01:37:23Z","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/2003.04286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We apply concepts from manifold regularization to develop new regularization techniques for training locally stable deep neural networks. Our regularizers are based on a sparsification of the graph Laplacian which holds with high probability when the data is sparse in high dimensions, as is common in deep learning. Empirically, our networks exhibit stability in a diverse set of perturbation models, including $\\ell_2$, $\\ell_\\infty$, and Wasserstein-based perturbations; in particular, we achieve 40% adversarial accuracy on CIFAR-10 against an adaptive PGD attack using $\\ell_\\infty$ perturbation","authors_text":"Charles Jin, Martin Rinard","cross_cats":["cs.CV","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-09T17:45:44Z","title":"Manifold Regularization for Locally Stable Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04286","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":"sha256:41aef8d5b8f69b64b0b5b56d8c97669068f1d71193ea5b71638e5fe0a583c5cb","target":"record","created_at":"2026-07-05T01:37:23Z","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":"a5c104ba0d168bc0fab60ea6a4f5f869b66f8defa914b412a7954b6558dc84ec","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-09T17:45:44Z","title_canon_sha256":"b60c7d3c2f9f73d9d18803467fea6e06a25f372ec62e0b93e29c7896212f99be"},"schema_version":"1.0","source":{"id":"2003.04286","kind":"arxiv","version":2}},"canonical_sha256":"dc79c818915d36cb4bac1502aa5e6958bda07b39dd3931c4b92e7ad1655da9ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc79c818915d36cb4bac1502aa5e6958bda07b39dd3931c4b92e7ad1655da9ae","first_computed_at":"2026-07-05T01:37:23.763507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:37:23.763507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FY3ebZ/+vYgM1fF2/y7yXC0jI/tVra3rkVlNIvf0DCPDl8i+mtgmYxIuFWV94bUHA9oMoscaYSYsS6iD3rLKDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:37:23.764065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.04286","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41aef8d5b8f69b64b0b5b56d8c97669068f1d71193ea5b71638e5fe0a583c5cb","sha256:946cbbe0c878555f29667c7240003956fa2c140609d2fd05fe496c6bb032827c"],"state_sha256":"479f7fd5aec0d813ac64e95894356e34a70150a7c865631304c9adae9117119b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rj1ImG8xB+WphHZdeJPX17imPm9LzQOTMxeQrGaj3X9u6YpGDB1IUuA5kuTu65wR+dKHcgJZwtELPKaFGwSdBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:27:30.314248Z","bundle_sha256":"7ed7c2fb23abaae0b85419f6711689000b69bfdd286e4ee81d85a749594635f3"}}