{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:W53I6UN65RYENCJDNXFZ23ARRF","short_pith_number":"pith:W53I6UN6","schema_version":"1.0","canonical_sha256":"b7768f51beec704689236dcb9d6c118950e523b067b14d3c436f120f1e336d38","source":{"kind":"arxiv","id":"1812.09764","version":3},"attestation_state":"computed","paper":{"title":"Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bastian Rieck, Christian Bock, Karsten Borgwardt, Matteo Togninalli, Max Horn, Michael Moor, Thomas Gumbsch","submitted_at":"2018-12-23T19:41:02Z","abstract_excerpt":"While many approaches to make neural networks more fathomable have been proposed, they are restricted to interrogating the network with input data. Measures for characterizing and monitoring structural properties, however, have not been developed. In this work, we propose neural persistence, a complexity measure for neural network architectures based on topological data analysis on weighted stratified graphs. To demonstrate the usefulness of our approach, we show that neural persistence reflects best practices developed in the deep learning community such as dropout and batch normalization. Mo"},"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":"1812.09764","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-23T19:41:02Z","cross_cats_sorted":["math.AT","stat.ML"],"title_canon_sha256":"1966589f33c40a0384d3dc0f077ce2950fd02a6f1bde5b476aaf5ab079567933","abstract_canon_sha256":"bf647d7736d85428c3754ee9eb1c5d17f6bff392f56ef03c5cb036b8fd4e7149"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:34.969867Z","signature_b64":"GN76gzoEhRs3tTshlALSUg7vFbPC+AcQ7fKxZym3aCfBiXgUd6PtXkePjlyUaw63c5/vUcolwizAoXL6xkO2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7768f51beec704689236dcb9d6c118950e523b067b14d3c436f120f1e336d38","last_reissued_at":"2026-07-05T00:07:34.969397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:34.969397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bastian Rieck, Christian Bock, Karsten Borgwardt, Matteo Togninalli, Max Horn, Michael Moor, Thomas Gumbsch","submitted_at":"2018-12-23T19:41:02Z","abstract_excerpt":"While many approaches to make neural networks more fathomable have been proposed, they are restricted to interrogating the network with input data. Measures for characterizing and monitoring structural properties, however, have not been developed. In this work, we propose neural persistence, a complexity measure for neural network architectures based on topological data analysis on weighted stratified graphs. To demonstrate the usefulness of our approach, we show that neural persistence reflects best practices developed in the deep learning community such as dropout and batch normalization. Mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09764","kind":"arxiv","version":3},"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/1812.09764/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":"1812.09764","created_at":"2026-07-05T00:07:34.969456+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.09764v3","created_at":"2026-07-05T00:07:34.969456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09764","created_at":"2026-07-05T00:07:34.969456+00:00"},{"alias_kind":"pith_short_12","alias_value":"W53I6UN65RYE","created_at":"2026-07-05T00:07:34.969456+00:00"},{"alias_kind":"pith_short_16","alias_value":"W53I6UN65RYENCJD","created_at":"2026-07-05T00:07:34.969456+00:00"},{"alias_kind":"pith_short_8","alias_value":"W53I6UN6","created_at":"2026-07-05T00:07:34.969456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21688","citing_title":"A Three Axis Evaluation Framework for Mapper Algorithms","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01105","citing_title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13997","citing_title":"HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08870","citing_title":"TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selection","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15265","citing_title":"Motif-based filtrations for persistent homology: A framework for graph isomorphism and property prediction","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W53I6UN65RYENCJDNXFZ23ARRF","json":"https://pith.science/pith/W53I6UN65RYENCJDNXFZ23ARRF.json","graph_json":"https://pith.science/api/pith-number/W53I6UN65RYENCJDNXFZ23ARRF/graph.json","events_json":"https://pith.science/api/pith-number/W53I6UN65RYENCJDNXFZ23ARRF/events.json","paper":"https://pith.science/paper/W53I6UN6"},"agent_actions":{"view_html":"https://pith.science/pith/W53I6UN65RYENCJDNXFZ23ARRF","download_json":"https://pith.science/pith/W53I6UN65RYENCJDNXFZ23ARRF.json","view_paper":"https://pith.science/paper/W53I6UN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.09764&json=true","fetch_graph":"https://pith.science/api/pith-number/W53I6UN65RYENCJDNXFZ23ARRF/graph.json","fetch_events":"https://pith.science/api/pith-number/W53I6UN65RYENCJDNXFZ23ARRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W53I6UN65RYENCJDNXFZ23ARRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W53I6UN65RYENCJDNXFZ23ARRF/action/storage_attestation","attest_author":"https://pith.science/pith/W53I6UN65RYENCJDNXFZ23ARRF/action/author_attestation","sign_citation":"https://pith.science/pith/W53I6UN65RYENCJDNXFZ23ARRF/action/citation_signature","submit_replication":"https://pith.science/pith/W53I6UN65RYENCJDNXFZ23ARRF/action/replication_record"}},"created_at":"2026-07-05T00:07:34.969456+00:00","updated_at":"2026-07-05T00:07:34.969456+00:00"}