{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CPRNRG64HFZGVEPFLTUSY5K2FT","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":"9cd5b2ec18dd1a500ebe759add3be2ec3fd674d4176093cc67f5f8adcd25a4d2","cross_cats_sorted":["math.AT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T03:46:32Z","title_canon_sha256":"0b0c48250c986d16349770b703c1865d80a2564acad58549bfdfa5874d72e65d"},"schema_version":"1.0","source":{"id":"1905.12200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12200","created_at":"2026-07-05T00:57:49Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12200v2","created_at":"2026-07-05T00:57:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12200","created_at":"2026-07-05T00:57:49Z"},{"alias_kind":"pith_short_12","alias_value":"CPRNRG64HFZG","created_at":"2026-07-05T00:57:49Z"},{"alias_kind":"pith_short_16","alias_value":"CPRNRG64HFZGVEPF","created_at":"2026-07-05T00:57:49Z"},{"alias_kind":"pith_short_8","alias_value":"CPRNRG64","created_at":"2026-07-05T00:57:49Z"}],"graph_snapshots":[{"event_id":"sha256:692056572768448608d1a48cd877c76afef605ebb7366ea28c0c4934ccd8885b","target":"graph","created_at":"2026-07-05T00:57:49Z","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/1905.12200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Topology applied to real world data using persistent homology has started to find applications within machine learning, including deep learning. We present a differentiable topology layer that computes persistent homology based on level set filtrations and edge-based filtrations. We present three novel applications: the topological layer can (i) regularize data reconstruction or the weights of machine learning models, (ii) construct a loss on the output of a deep generative network to incorporate topological priors, and (iii) perform topological adversarial attacks on deep networks trained wit","authors_text":"Anjan Dwaraknath, Bradley J. Nelson, Gunnar Carlsson, Leonidas J. Guibas, Primoz Skraba, Rickard Br\\\"uel-Gabrielsson","cross_cats":["math.AT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T03:46:32Z","title":"A Topology Layer for Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12200","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":"sha256:5748e76908eaaf2e4ce208ae40db54987bd067ed4df0d90378b806d9d5953618","target":"record","created_at":"2026-07-05T00:57:49Z","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":"9cd5b2ec18dd1a500ebe759add3be2ec3fd674d4176093cc67f5f8adcd25a4d2","cross_cats_sorted":["math.AT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T03:46:32Z","title_canon_sha256":"0b0c48250c986d16349770b703c1865d80a2564acad58549bfdfa5874d72e65d"},"schema_version":"1.0","source":{"id":"1905.12200","kind":"arxiv","version":2}},"canonical_sha256":"13e2d89bdc39726a91e55ce92c755a2cd21dadb6bfdc06cbad77ddb9294ee792","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13e2d89bdc39726a91e55ce92c755a2cd21dadb6bfdc06cbad77ddb9294ee792","first_computed_at":"2026-07-05T00:57:49.322931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:57:49.322931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U+1IQC6L7Zj8dHQOZP2+NmYJAcXaUsRxq5Wx8ENH8d2NVVQQNRML7St0+1tGe/EWidt0+PRS8qOZqDk10jZiDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:57:49.323479Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.12200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5748e76908eaaf2e4ce208ae40db54987bd067ed4df0d90378b806d9d5953618","sha256:692056572768448608d1a48cd877c76afef605ebb7366ea28c0c4934ccd8885b"],"state_sha256":"bb01d68f80b03a7f4d1cfdbf84d708b24727fe1f3a8703132a76fcfec0d4f0fe"}