{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V27P2FTCJEXCK2YM5SA6QVMYVF","short_pith_number":"pith:V27P2FTC","schema_version":"1.0","canonical_sha256":"aebefd1662492e256b0cec81e85598a94a5550e658769cfa0e4aeea2596aae62","source":{"kind":"arxiv","id":"2404.19710","version":3},"attestation_state":"computed","paper":{"title":"A rank decomposition for the topological classification of neural representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.AT","q-bio.NC"],"primary_cat":"cs.LG","authors_text":"Gaute T. Einevoll, Kosio Beshkov","submitted_at":"2024-04-30T17:01:20Z","abstract_excerpt":"Neural networks can be thought of as applying a transformation to an input dataset. The way in which they change the topology of such a dataset often holds practical significance for many tasks, particularly those demanding non-homeomorphic mappings for optimal solutions, such as classification problems. In this work, we leverage the fact that neural networks are equivalent to continuous piecewise-affine maps, whose rank can be used to pinpoint regions in the input space that undergo non-homeomorphic transformations, leading to alterations in the topological structure of the input dataset. Our"},"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":"2404.19710","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-30T17:01:20Z","cross_cats_sorted":["math.AT","q-bio.NC"],"title_canon_sha256":"d1beb97313b9309eef17f390739f012027cbb43e867f73986fea1603438b3038","abstract_canon_sha256":"6e513326fe29e52acfd24967e5538e2f2ff76f706bc6028d53747d9a59f44bb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:07.788511Z","signature_b64":"bl2Fu5cQyH9QPWOWRCuIsfDaupLh7KZkky7wuyGeT1tCuDuQBgfmDxlXraF5uzkz7ogmU9fu2ot7KnlEFIo4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aebefd1662492e256b0cec81e85598a94a5550e658769cfa0e4aeea2596aae62","last_reissued_at":"2026-07-05T08:27:07.788050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:07.788050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A rank decomposition for the topological classification of neural representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.AT","q-bio.NC"],"primary_cat":"cs.LG","authors_text":"Gaute T. Einevoll, Kosio Beshkov","submitted_at":"2024-04-30T17:01:20Z","abstract_excerpt":"Neural networks can be thought of as applying a transformation to an input dataset. The way in which they change the topology of such a dataset often holds practical significance for many tasks, particularly those demanding non-homeomorphic mappings for optimal solutions, such as classification problems. In this work, we leverage the fact that neural networks are equivalent to continuous piecewise-affine maps, whose rank can be used to pinpoint regions in the input space that undergo non-homeomorphic transformations, leading to alterations in the topological structure of the input dataset. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19710","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/2404.19710/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":"2404.19710","created_at":"2026-07-05T08:27:07.788106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.19710v3","created_at":"2026-07-05T08:27:07.788106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19710","created_at":"2026-07-05T08:27:07.788106+00:00"},{"alias_kind":"pith_short_12","alias_value":"V27P2FTCJEXC","created_at":"2026-07-05T08:27:07.788106+00:00"},{"alias_kind":"pith_short_16","alias_value":"V27P2FTCJEXCK2YM","created_at":"2026-07-05T08:27:07.788106+00:00"},{"alias_kind":"pith_short_8","alias_value":"V27P2FTC","created_at":"2026-07-05T08:27:07.788106+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01360","citing_title":"A Quotient Homology Theory of Representation in Neural Networks","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V27P2FTCJEXCK2YM5SA6QVMYVF","json":"https://pith.science/pith/V27P2FTCJEXCK2YM5SA6QVMYVF.json","graph_json":"https://pith.science/api/pith-number/V27P2FTCJEXCK2YM5SA6QVMYVF/graph.json","events_json":"https://pith.science/api/pith-number/V27P2FTCJEXCK2YM5SA6QVMYVF/events.json","paper":"https://pith.science/paper/V27P2FTC"},"agent_actions":{"view_html":"https://pith.science/pith/V27P2FTCJEXCK2YM5SA6QVMYVF","download_json":"https://pith.science/pith/V27P2FTCJEXCK2YM5SA6QVMYVF.json","view_paper":"https://pith.science/paper/V27P2FTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.19710&json=true","fetch_graph":"https://pith.science/api/pith-number/V27P2FTCJEXCK2YM5SA6QVMYVF/graph.json","fetch_events":"https://pith.science/api/pith-number/V27P2FTCJEXCK2YM5SA6QVMYVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V27P2FTCJEXCK2YM5SA6QVMYVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V27P2FTCJEXCK2YM5SA6QVMYVF/action/storage_attestation","attest_author":"https://pith.science/pith/V27P2FTCJEXCK2YM5SA6QVMYVF/action/author_attestation","sign_citation":"https://pith.science/pith/V27P2FTCJEXCK2YM5SA6QVMYVF/action/citation_signature","submit_replication":"https://pith.science/pith/V27P2FTCJEXCK2YM5SA6QVMYVF/action/replication_record"}},"created_at":"2026-07-05T08:27:07.788106+00:00","updated_at":"2026-07-05T08:27:07.788106+00:00"}