{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MACWKQ4L6UY44V3LXGLVP2BZ3B","short_pith_number":"pith:MACWKQ4L","schema_version":"1.0","canonical_sha256":"600565438bf531ce576bb99757e839d874dcac9fa9cda202f5710a7ba1cb4f20","source":{"kind":"arxiv","id":"2005.05541","version":2},"attestation_state":"computed","paper":{"title":"Modularizing Deep Learning via Pairwise Learning With Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jose Principe, Shiyu Duan, Shujian Yu","submitted_at":"2020-05-12T04:19:37Z","abstract_excerpt":"By redefining the conventional notions of layers, we present an alternative view on finitely wide, fully trainable deep neural networks as stacked linear models in feature spaces, leading to a kernel machine interpretation. Based on this construction, we then propose a provably optimal modular learning framework for classification that does not require between-module backpropagation. This modular approach brings new insights into the label requirement of deep learning: It leverages only implicit pairwise labels (weak supervision) when learning the hidden modules. When training the output modul"},"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":"2005.05541","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-05-12T04:19:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dce1111322bf533ee5799def7d3ed98c639af192ff5eab31e191c97c55f3c19e","abstract_canon_sha256":"8639c5094b2faa792744d1dbc44dbd84aea9bb9fefdd8f8c0261830b1f97de80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:55:52.725752Z","signature_b64":"C+RfRgwbrFQ4fPR0XsQPJAdz4QkKIRU8fiAoKuGIypldlyXxnowYkYcNSiB08ihJmATrDMmagtl66sSWyjRwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"600565438bf531ce576bb99757e839d874dcac9fa9cda202f5710a7ba1cb4f20","last_reissued_at":"2026-07-05T01:55:52.725270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:55:52.725270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modularizing Deep Learning via Pairwise Learning With Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jose Principe, Shiyu Duan, Shujian Yu","submitted_at":"2020-05-12T04:19:37Z","abstract_excerpt":"By redefining the conventional notions of layers, we present an alternative view on finitely wide, fully trainable deep neural networks as stacked linear models in feature spaces, leading to a kernel machine interpretation. Based on this construction, we then propose a provably optimal modular learning framework for classification that does not require between-module backpropagation. This modular approach brings new insights into the label requirement of deep learning: It leverages only implicit pairwise labels (weak supervision) when learning the hidden modules. When training the output modul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.05541","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/2005.05541/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":"2005.05541","created_at":"2026-07-05T01:55:52.725336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.05541v2","created_at":"2026-07-05T01:55:52.725336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.05541","created_at":"2026-07-05T01:55:52.725336+00:00"},{"alias_kind":"pith_short_12","alias_value":"MACWKQ4L6UY4","created_at":"2026-07-05T01:55:52.725336+00:00"},{"alias_kind":"pith_short_16","alias_value":"MACWKQ4L6UY44V3L","created_at":"2026-07-05T01:55:52.725336+00:00"},{"alias_kind":"pith_short_8","alias_value":"MACWKQ4L","created_at":"2026-07-05T01:55:52.725336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MACWKQ4L6UY44V3LXGLVP2BZ3B","json":"https://pith.science/pith/MACWKQ4L6UY44V3LXGLVP2BZ3B.json","graph_json":"https://pith.science/api/pith-number/MACWKQ4L6UY44V3LXGLVP2BZ3B/graph.json","events_json":"https://pith.science/api/pith-number/MACWKQ4L6UY44V3LXGLVP2BZ3B/events.json","paper":"https://pith.science/paper/MACWKQ4L"},"agent_actions":{"view_html":"https://pith.science/pith/MACWKQ4L6UY44V3LXGLVP2BZ3B","download_json":"https://pith.science/pith/MACWKQ4L6UY44V3LXGLVP2BZ3B.json","view_paper":"https://pith.science/paper/MACWKQ4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.05541&json=true","fetch_graph":"https://pith.science/api/pith-number/MACWKQ4L6UY44V3LXGLVP2BZ3B/graph.json","fetch_events":"https://pith.science/api/pith-number/MACWKQ4L6UY44V3LXGLVP2BZ3B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MACWKQ4L6UY44V3LXGLVP2BZ3B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MACWKQ4L6UY44V3LXGLVP2BZ3B/action/storage_attestation","attest_author":"https://pith.science/pith/MACWKQ4L6UY44V3LXGLVP2BZ3B/action/author_attestation","sign_citation":"https://pith.science/pith/MACWKQ4L6UY44V3LXGLVP2BZ3B/action/citation_signature","submit_replication":"https://pith.science/pith/MACWKQ4L6UY44V3LXGLVP2BZ3B/action/replication_record"}},"created_at":"2026-07-05T01:55:52.725336+00:00","updated_at":"2026-07-05T01:55:52.725336+00:00"}