{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QRXF5QDR74AWH6OKE3RAZDUFIJ","short_pith_number":"pith:QRXF5QDR","schema_version":"1.0","canonical_sha256":"846e5ec071ff0163f9ca26e20c8e85425f8324a74423d74456f0baf56abf08d7","source":{"kind":"arxiv","id":"2312.05840","version":2},"attestation_state":"computed","paper":{"title":"Topological Data Analysis for Neural Network Analysis: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.AT"],"primary_cat":"cs.LG","authors_text":"Carles Casacuberta, Rub\\'en Ballester, Sergio Escalera","submitted_at":"2023-12-10T09:50:57Z","abstract_excerpt":"This survey provides a comprehensive exploration of applications of Topological Data Analysis (TDA) within neural network analysis. Using TDA tools such as persistent homology and Mapper, we delve into the intricate structures and behaviors of neural networks and their datasets. We discuss different strategies to obtain topological information from data and neural networks by means of TDA. Additionally, we review how topological information can be leveraged to analyze properties of neural networks, such as their generalization capacity or expressivity. We explore practical implications of deep"},"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":"2312.05840","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-10T09:50:57Z","cross_cats_sorted":["math.AT"],"title_canon_sha256":"cb1d6e939dd036c94de80c80d6de4591f4381c1cb4f6a6d92cda8c184c364783","abstract_canon_sha256":"17a3cf7e9b36b506c835711f07aaf626f8747b1db654fc46a4054f256fe3e53b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:54.966831Z","signature_b64":"/LfxD5SQQo7l9pvcCb01G3BCIltq1L5GDNuGhrckbhq2Nxp8gv3c+FtiZzdZC43zOozvdSRB32S7ZjUuMy5FDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"846e5ec071ff0163f9ca26e20c8e85425f8324a74423d74456f0baf56abf08d7","last_reissued_at":"2026-07-05T07:29:54.966430Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:54.966430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topological Data Analysis for Neural Network Analysis: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.AT"],"primary_cat":"cs.LG","authors_text":"Carles Casacuberta, Rub\\'en Ballester, Sergio Escalera","submitted_at":"2023-12-10T09:50:57Z","abstract_excerpt":"This survey provides a comprehensive exploration of applications of Topological Data Analysis (TDA) within neural network analysis. Using TDA tools such as persistent homology and Mapper, we delve into the intricate structures and behaviors of neural networks and their datasets. We discuss different strategies to obtain topological information from data and neural networks by means of TDA. Additionally, we review how topological information can be leveraged to analyze properties of neural networks, such as their generalization capacity or expressivity. We explore practical implications of deep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05840","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/2312.05840/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":"2312.05840","created_at":"2026-07-05T07:29:54.966484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05840v2","created_at":"2026-07-05T07:29:54.966484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05840","created_at":"2026-07-05T07:29:54.966484+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRXF5QDR74AW","created_at":"2026-07-05T07:29:54.966484+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRXF5QDR74AWH6OK","created_at":"2026-07-05T07:29:54.966484+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRXF5QDR","created_at":"2026-07-05T07:29:54.966484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.04941","citing_title":"TOAST: Transformer Optimization using Adaptive and Simple Transformations","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06352","citing_title":"Topological Signatures of Grokking","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07172","citing_title":"Topology-Enhanced Alignment for Large Language Models: Trajectory Topology Loss and Topological Preference Optimization","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QRXF5QDR74AWH6OKE3RAZDUFIJ","json":"https://pith.science/pith/QRXF5QDR74AWH6OKE3RAZDUFIJ.json","graph_json":"https://pith.science/api/pith-number/QRXF5QDR74AWH6OKE3RAZDUFIJ/graph.json","events_json":"https://pith.science/api/pith-number/QRXF5QDR74AWH6OKE3RAZDUFIJ/events.json","paper":"https://pith.science/paper/QRXF5QDR"},"agent_actions":{"view_html":"https://pith.science/pith/QRXF5QDR74AWH6OKE3RAZDUFIJ","download_json":"https://pith.science/pith/QRXF5QDR74AWH6OKE3RAZDUFIJ.json","view_paper":"https://pith.science/paper/QRXF5QDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05840&json=true","fetch_graph":"https://pith.science/api/pith-number/QRXF5QDR74AWH6OKE3RAZDUFIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/QRXF5QDR74AWH6OKE3RAZDUFIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRXF5QDR74AWH6OKE3RAZDUFIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRXF5QDR74AWH6OKE3RAZDUFIJ/action/storage_attestation","attest_author":"https://pith.science/pith/QRXF5QDR74AWH6OKE3RAZDUFIJ/action/author_attestation","sign_citation":"https://pith.science/pith/QRXF5QDR74AWH6OKE3RAZDUFIJ/action/citation_signature","submit_replication":"https://pith.science/pith/QRXF5QDR74AWH6OKE3RAZDUFIJ/action/replication_record"}},"created_at":"2026-07-05T07:29:54.966484+00:00","updated_at":"2026-07-05T07:29:54.966484+00:00"}