{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CPRNRG64HFZGVEPFLTUSY5K2FT","short_pith_number":"pith:CPRNRG64","schema_version":"1.0","canonical_sha256":"13e2d89bdc39726a91e55ce92c755a2cd21dadb6bfdc06cbad77ddb9294ee792","source":{"kind":"arxiv","id":"1905.12200","version":2},"attestation_state":"computed","paper":{"title":"A Topology Layer for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anjan Dwaraknath, Bradley J. Nelson, Gunnar Carlsson, Leonidas J. Guibas, Primoz Skraba, Rickard Br\\\"uel-Gabrielsson","submitted_at":"2019-05-29T03:46:32Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1905.12200","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T03:46:32Z","cross_cats_sorted":["math.AT","stat.ML"],"title_canon_sha256":"0b0c48250c986d16349770b703c1865d80a2564acad58549bfdfa5874d72e65d","abstract_canon_sha256":"9cd5b2ec18dd1a500ebe759add3be2ec3fd674d4176093cc67f5f8adcd25a4d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:49.323479Z","signature_b64":"U+1IQC6L7Zj8dHQOZP2+NmYJAcXaUsRxq5Wx8ENH8d2NVVQQNRML7St0+1tGe/EWidt0+PRS8qOZqDk10jZiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13e2d89bdc39726a91e55ce92c755a2cd21dadb6bfdc06cbad77ddb9294ee792","last_reissued_at":"2026-07-05T00:57:49.322931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:49.322931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Topology Layer for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anjan Dwaraknath, Bradley J. Nelson, Gunnar Carlsson, Leonidas J. Guibas, Primoz Skraba, Rickard Br\\\"uel-Gabrielsson","submitted_at":"2019-05-29T03:46:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12200","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/1905.12200/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.12200","created_at":"2026-07-05T00:57:49.322986+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12200v2","created_at":"2026-07-05T00:57:49.322986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12200","created_at":"2026-07-05T00:57:49.322986+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPRNRG64HFZG","created_at":"2026-07-05T00:57:49.322986+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPRNRG64HFZGVEPF","created_at":"2026-07-05T00:57:49.322986+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPRNRG64","created_at":"2026-07-05T00:57:49.322986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.21160","citing_title":"KaLDeX: Kalman Filter based Linear Deformable Cross Attention for Retina Vessel Segmentation","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPRNRG64HFZGVEPFLTUSY5K2FT","json":"https://pith.science/pith/CPRNRG64HFZGVEPFLTUSY5K2FT.json","graph_json":"https://pith.science/api/pith-number/CPRNRG64HFZGVEPFLTUSY5K2FT/graph.json","events_json":"https://pith.science/api/pith-number/CPRNRG64HFZGVEPFLTUSY5K2FT/events.json","paper":"https://pith.science/paper/CPRNRG64"},"agent_actions":{"view_html":"https://pith.science/pith/CPRNRG64HFZGVEPFLTUSY5K2FT","download_json":"https://pith.science/pith/CPRNRG64HFZGVEPFLTUSY5K2FT.json","view_paper":"https://pith.science/paper/CPRNRG64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12200&json=true","fetch_graph":"https://pith.science/api/pith-number/CPRNRG64HFZGVEPFLTUSY5K2FT/graph.json","fetch_events":"https://pith.science/api/pith-number/CPRNRG64HFZGVEPFLTUSY5K2FT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPRNRG64HFZGVEPFLTUSY5K2FT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPRNRG64HFZGVEPFLTUSY5K2FT/action/storage_attestation","attest_author":"https://pith.science/pith/CPRNRG64HFZGVEPFLTUSY5K2FT/action/author_attestation","sign_citation":"https://pith.science/pith/CPRNRG64HFZGVEPFLTUSY5K2FT/action/citation_signature","submit_replication":"https://pith.science/pith/CPRNRG64HFZGVEPFLTUSY5K2FT/action/replication_record"}},"created_at":"2026-07-05T00:57:49.322986+00:00","updated_at":"2026-07-05T00:57:49.322986+00:00"}