{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DXBUAJ63CKDWFLR3SEWH3ZO7UO","short_pith_number":"pith:DXBUAJ63","schema_version":"1.0","canonical_sha256":"1dc34027db128762ae3b912c7de5dfa3a01b21ade61f3bb742aa3ff701ef4e20","source":{"kind":"arxiv","id":"2308.12044","version":5},"attestation_state":"computed","paper":{"title":"A multiobjective continuation method to compute the regularization path of deep neural networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Augustina C. Amakor, Konstantin Sonntag, Sebastian Peitz","submitted_at":"2023-08-23T10:08:52Z","abstract_excerpt":"Sparsity is a highly desired feature in deep neural networks (DNNs) since it ensures numerical efficiency, improves the interpretability of models (due to the smaller number of relevant features), and robustness. For linear models, it is well known that there exists a \\emph{regularization path} connecting the sparsest solution in terms of the $\\ell^1$ norm, i.e., zero weights and the non-regularized solution. Very recently, there was a first attempt to extend the concept of regularization paths to DNNs by means of treating the empirical loss and sparsity ($\\ell^1$ norm) as two conflicting crit"},"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":"2308.12044","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-23T10:08:52Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"267f58b2f8021baa52241cca3127d477c168cd5d5f2ec4c0bfe0c3239d640715","abstract_canon_sha256":"0bafdbad7a7abb00f66d0b491a54f01022f9ed3a3954bf6bf62b31a8646100b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:00.748236Z","signature_b64":"1N4ppVmbEGUw3ON4nqA7Ai7UEBg/Qinwntc0fk15h2DmyM3yjb/yhg7pqwQidH/xV5RqnQcDlyeR0TKUukynDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dc34027db128762ae3b912c7de5dfa3a01b21ade61f3bb742aa3ff701ef4e20","last_reissued_at":"2026-07-05T08:02:00.747776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:00.747776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A multiobjective continuation method to compute the regularization path of deep neural networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Augustina C. Amakor, Konstantin Sonntag, Sebastian Peitz","submitted_at":"2023-08-23T10:08:52Z","abstract_excerpt":"Sparsity is a highly desired feature in deep neural networks (DNNs) since it ensures numerical efficiency, improves the interpretability of models (due to the smaller number of relevant features), and robustness. For linear models, it is well known that there exists a \\emph{regularization path} connecting the sparsest solution in terms of the $\\ell^1$ norm, i.e., zero weights and the non-regularized solution. Very recently, there was a first attempt to extend the concept of regularization paths to DNNs by means of treating the empirical loss and sparsity ($\\ell^1$ norm) as two conflicting crit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12044","kind":"arxiv","version":5},"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/2308.12044/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":"2308.12044","created_at":"2026-07-05T08:02:00.747841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.12044v5","created_at":"2026-07-05T08:02:00.747841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12044","created_at":"2026-07-05T08:02:00.747841+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXBUAJ63CKDW","created_at":"2026-07-05T08:02:00.747841+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXBUAJ63CKDWFLR3","created_at":"2026-07-05T08:02:00.747841+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXBUAJ63","created_at":"2026-07-05T08:02:00.747841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01566","citing_title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXBUAJ63CKDWFLR3SEWH3ZO7UO","json":"https://pith.science/pith/DXBUAJ63CKDWFLR3SEWH3ZO7UO.json","graph_json":"https://pith.science/api/pith-number/DXBUAJ63CKDWFLR3SEWH3ZO7UO/graph.json","events_json":"https://pith.science/api/pith-number/DXBUAJ63CKDWFLR3SEWH3ZO7UO/events.json","paper":"https://pith.science/paper/DXBUAJ63"},"agent_actions":{"view_html":"https://pith.science/pith/DXBUAJ63CKDWFLR3SEWH3ZO7UO","download_json":"https://pith.science/pith/DXBUAJ63CKDWFLR3SEWH3ZO7UO.json","view_paper":"https://pith.science/paper/DXBUAJ63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.12044&json=true","fetch_graph":"https://pith.science/api/pith-number/DXBUAJ63CKDWFLR3SEWH3ZO7UO/graph.json","fetch_events":"https://pith.science/api/pith-number/DXBUAJ63CKDWFLR3SEWH3ZO7UO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXBUAJ63CKDWFLR3SEWH3ZO7UO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXBUAJ63CKDWFLR3SEWH3ZO7UO/action/storage_attestation","attest_author":"https://pith.science/pith/DXBUAJ63CKDWFLR3SEWH3ZO7UO/action/author_attestation","sign_citation":"https://pith.science/pith/DXBUAJ63CKDWFLR3SEWH3ZO7UO/action/citation_signature","submit_replication":"https://pith.science/pith/DXBUAJ63CKDWFLR3SEWH3ZO7UO/action/replication_record"}},"created_at":"2026-07-05T08:02:00.747841+00:00","updated_at":"2026-07-05T08:02:00.747841+00:00"}