{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4RSENGKUWYTPPGMYFXPNPDGK3I","short_pith_number":"pith:4RSENGKU","schema_version":"1.0","canonical_sha256":"e464469954b626f799982dded78ccada2cb35739ac420a2d0034422177fc7873","source":{"kind":"arxiv","id":"2011.05804","version":2},"attestation_state":"computed","paper":{"title":"Regularization of Persistent Homology Gradient Computation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bailin Deng, Padraig Corcoran","submitted_at":"2020-11-11T14:16:33Z","abstract_excerpt":"Persistent homology is a method for computing the topological features present in a given data. Recently, there has been much interest in the integration of persistent homology as a computational step in neural networks or deep learning. In order for a given computation to be integrated in such a way, the computation in question must be differentiable. Computing the gradients of persistent homology is an ill-posed inverse problem with infinitely many solutions. Consequently, it is important to perform regularization so that the solution obtained agrees with known priors. In this work we propos"},"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":"2011.05804","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T14:16:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7690e15ad09bf248980b6efecf2b7fd5711815f7f008dd1c9fdc9b08c6472c87","abstract_canon_sha256":"9cf2bc5a9444ba44efd9ac05426b68165d4f4be893ff6680834289476f929584"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:46.446281Z","signature_b64":"PaEuVckFOCYBRvfl1NIQ+QzvRfSq+rdyq7Ijqwbng10qlk6fXEM+uZyafOCKotiCS0pAlNEa0SCRzEwzqEwICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e464469954b626f799982dded78ccada2cb35739ac420a2d0034422177fc7873","last_reissued_at":"2026-07-05T01:51:46.445869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:46.445869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularization of Persistent Homology Gradient Computation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bailin Deng, Padraig Corcoran","submitted_at":"2020-11-11T14:16:33Z","abstract_excerpt":"Persistent homology is a method for computing the topological features present in a given data. Recently, there has been much interest in the integration of persistent homology as a computational step in neural networks or deep learning. In order for a given computation to be integrated in such a way, the computation in question must be differentiable. Computing the gradients of persistent homology is an ill-posed inverse problem with infinitely many solutions. Consequently, it is important to perform regularization so that the solution obtained agrees with known priors. In this work we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05804","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/2011.05804/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":"2011.05804","created_at":"2026-07-05T01:51:46.445931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.05804v2","created_at":"2026-07-05T01:51:46.445931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05804","created_at":"2026-07-05T01:51:46.445931+00:00"},{"alias_kind":"pith_short_12","alias_value":"4RSENGKUWYTP","created_at":"2026-07-05T01:51:46.445931+00:00"},{"alias_kind":"pith_short_16","alias_value":"4RSENGKUWYTPPGMY","created_at":"2026-07-05T01:51:46.445931+00:00"},{"alias_kind":"pith_short_8","alias_value":"4RSENGKU","created_at":"2026-07-05T01:51:46.445931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.03806","citing_title":"Dynamical Persistent Homology via Wasserstein Gradient Flow","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4RSENGKUWYTPPGMYFXPNPDGK3I","json":"https://pith.science/pith/4RSENGKUWYTPPGMYFXPNPDGK3I.json","graph_json":"https://pith.science/api/pith-number/4RSENGKUWYTPPGMYFXPNPDGK3I/graph.json","events_json":"https://pith.science/api/pith-number/4RSENGKUWYTPPGMYFXPNPDGK3I/events.json","paper":"https://pith.science/paper/4RSENGKU"},"agent_actions":{"view_html":"https://pith.science/pith/4RSENGKUWYTPPGMYFXPNPDGK3I","download_json":"https://pith.science/pith/4RSENGKUWYTPPGMYFXPNPDGK3I.json","view_paper":"https://pith.science/paper/4RSENGKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.05804&json=true","fetch_graph":"https://pith.science/api/pith-number/4RSENGKUWYTPPGMYFXPNPDGK3I/graph.json","fetch_events":"https://pith.science/api/pith-number/4RSENGKUWYTPPGMYFXPNPDGK3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4RSENGKUWYTPPGMYFXPNPDGK3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4RSENGKUWYTPPGMYFXPNPDGK3I/action/storage_attestation","attest_author":"https://pith.science/pith/4RSENGKUWYTPPGMYFXPNPDGK3I/action/author_attestation","sign_citation":"https://pith.science/pith/4RSENGKUWYTPPGMYFXPNPDGK3I/action/citation_signature","submit_replication":"https://pith.science/pith/4RSENGKUWYTPPGMYFXPNPDGK3I/action/replication_record"}},"created_at":"2026-07-05T01:51:46.445931+00:00","updated_at":"2026-07-05T01:51:46.445931+00:00"}