{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:F5FBVERELF7XIUNRUAXWNOBCLS","short_pith_number":"pith:F5FBVERE","schema_version":"1.0","canonical_sha256":"2f4a1a9224597f7451b1a02f66b8225ca21e6bb73ae3a3e6bcc15fc79b6f0bc8","source":{"kind":"arxiv","id":"2106.01613","version":3},"attestation_state":"computed","paper":{"title":"NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anna Goldenberg, Chun-Hao Chang, Rich Caruana","submitted_at":"2021-06-03T06:20:18Z","abstract_excerpt":"Deployment of machine learning models in real high-risk settings (e.g. healthcare) often depends not only on the model's accuracy but also on its fairness, robustness, and interpretability. Generalized Additive Models (GAMs) are a class of interpretable models with a long history of use in these high-risk domains, but they lack desirable features of deep learning such as differentiability and scalability. In this work, we propose a neural GAM (NODE-GAM) and neural GA$^2$M (NODE-GA$^2$M) that scale well and perform better than other GAMs on large datasets, while remaining interpretable compared"},"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":"2106.01613","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-03T06:20:18Z","cross_cats_sorted":[],"title_canon_sha256":"20b4210bd232cce586ba0201d43aeef6f60db487df4144560a3a54b1777c6c86","abstract_canon_sha256":"21fada97faecf6ef7a63dff6641b6905d7802010e0bbf170760401ad41253612"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:31.337253Z","signature_b64":"q17UpVJVmxv+DswrTUFkThDKVROAZll1d23apRXHqw27er4fV01HY11QkDvxmCEBNtuytoMNOn8m1c7Bks/LDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f4a1a9224597f7451b1a02f66b8225ca21e6bb73ae3a3e6bcc15fc79b6f0bc8","last_reissued_at":"2026-07-05T04:05:31.336811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:31.336811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anna Goldenberg, Chun-Hao Chang, Rich Caruana","submitted_at":"2021-06-03T06:20:18Z","abstract_excerpt":"Deployment of machine learning models in real high-risk settings (e.g. healthcare) often depends not only on the model's accuracy but also on its fairness, robustness, and interpretability. Generalized Additive Models (GAMs) are a class of interpretable models with a long history of use in these high-risk domains, but they lack desirable features of deep learning such as differentiability and scalability. In this work, we propose a neural GAM (NODE-GAM) and neural GA$^2$M (NODE-GA$^2$M) that scale well and perform better than other GAMs on large datasets, while remaining interpretable compared"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01613","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/2106.01613/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":"2106.01613","created_at":"2026-07-05T04:05:31.336885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.01613v3","created_at":"2026-07-05T04:05:31.336885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01613","created_at":"2026-07-05T04:05:31.336885+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5FBVERELF7X","created_at":"2026-07-05T04:05:31.336885+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5FBVERELF7XIUNR","created_at":"2026-07-05T04:05:31.336885+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5FBVERE","created_at":"2026-07-05T04:05:31.336885+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23575","citing_title":"Solve for the Hyperparameter, Skip the Search: Kolmogorov-Optimal Scaling Laws for Spline Regression","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18422","citing_title":"Generalized Functional ANOVA in Closed-Form: A Unified View of Additive Explanations","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18864","citing_title":"ParamBoost: Gradient Boosted Piecewise Cubic Polynomials","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F5FBVERELF7XIUNRUAXWNOBCLS","json":"https://pith.science/pith/F5FBVERELF7XIUNRUAXWNOBCLS.json","graph_json":"https://pith.science/api/pith-number/F5FBVERELF7XIUNRUAXWNOBCLS/graph.json","events_json":"https://pith.science/api/pith-number/F5FBVERELF7XIUNRUAXWNOBCLS/events.json","paper":"https://pith.science/paper/F5FBVERE"},"agent_actions":{"view_html":"https://pith.science/pith/F5FBVERELF7XIUNRUAXWNOBCLS","download_json":"https://pith.science/pith/F5FBVERELF7XIUNRUAXWNOBCLS.json","view_paper":"https://pith.science/paper/F5FBVERE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.01613&json=true","fetch_graph":"https://pith.science/api/pith-number/F5FBVERELF7XIUNRUAXWNOBCLS/graph.json","fetch_events":"https://pith.science/api/pith-number/F5FBVERELF7XIUNRUAXWNOBCLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5FBVERELF7XIUNRUAXWNOBCLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5FBVERELF7XIUNRUAXWNOBCLS/action/storage_attestation","attest_author":"https://pith.science/pith/F5FBVERELF7XIUNRUAXWNOBCLS/action/author_attestation","sign_citation":"https://pith.science/pith/F5FBVERELF7XIUNRUAXWNOBCLS/action/citation_signature","submit_replication":"https://pith.science/pith/F5FBVERELF7XIUNRUAXWNOBCLS/action/replication_record"}},"created_at":"2026-07-05T04:05:31.336885+00:00","updated_at":"2026-07-05T04:05:31.336885+00:00"}