{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IPXIZ45ZWVATC2PQTN2CAX6MXZ","short_pith_number":"pith:IPXIZ45Z","schema_version":"1.0","canonical_sha256":"43ee8cf3b9b5413169f09b74205fccbe7f941982a66b244a352efda6b3bba84c","source":{"kind":"arxiv","id":"2207.08548","version":6},"attestation_state":"computed","paper":{"title":"GANDALF: Gated Adaptive Network for Deep Automated Learning of Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Harsh Raj, Manu Joseph","submitted_at":"2022-07-18T12:12:24Z","abstract_excerpt":"We propose a novel high-performance, interpretable, and parameter \\& computationally efficient deep learning architecture for tabular data, Gated Adaptive Network for Deep Automated Learning of Features (GANDALF). GANDALF relies on a new tabular processing unit with a gating mechanism and in-built feature selection called Gated Feature Learning Unit (GFLU) as a feature representation learning unit. We demonstrate that GANDALF outperforms or stays at-par with SOTA approaches like XGBoost, SAINT, FT-Transformers, etc. by experiments on multiple established public benchmarks. We have made availab"},"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":"2207.08548","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-18T12:12:24Z","cross_cats_sorted":[],"title_canon_sha256":"741ad817707b7bb750900a89675087c754fff79f99c5c65bcebd5c541f861bc2","abstract_canon_sha256":"00fbc1de0b9810f92c3e804bc7740e53dcfa83e50d323fcaf705adbdaf1027c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:50.617999Z","signature_b64":"ZMaBha0u0wCMdDLcJeankuCcy67NBxWWmXu3M5/hHkQBMqUCiJg1YzX1j49ZBpMazmROJNEPGI82EJT0If8jAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43ee8cf3b9b5413169f09b74205fccbe7f941982a66b244a352efda6b3bba84c","last_reissued_at":"2026-07-05T07:31:50.617353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:50.617353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GANDALF: Gated Adaptive Network for Deep Automated Learning of Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Harsh Raj, Manu Joseph","submitted_at":"2022-07-18T12:12:24Z","abstract_excerpt":"We propose a novel high-performance, interpretable, and parameter \\& computationally efficient deep learning architecture for tabular data, Gated Adaptive Network for Deep Automated Learning of Features (GANDALF). GANDALF relies on a new tabular processing unit with a gating mechanism and in-built feature selection called Gated Feature Learning Unit (GFLU) as a feature representation learning unit. We demonstrate that GANDALF outperforms or stays at-par with SOTA approaches like XGBoost, SAINT, FT-Transformers, etc. by experiments on multiple established public benchmarks. We have made availab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.08548","kind":"arxiv","version":6},"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/2207.08548/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":"2207.08548","created_at":"2026-07-05T07:31:50.617425+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.08548v6","created_at":"2026-07-05T07:31:50.617425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.08548","created_at":"2026-07-05T07:31:50.617425+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPXIZ45ZWVAT","created_at":"2026-07-05T07:31:50.617425+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPXIZ45ZWVATC2PQ","created_at":"2026-07-05T07:31:50.617425+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPXIZ45Z","created_at":"2026-07-05T07:31:50.617425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23453","citing_title":"Class-Dependent Hybrid Data Augmentation for Multiclass Migraine Classification under Severe Class Imbalance","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23453","citing_title":"Class-Dependent Hybrid Data Augmentation for Multiclass Migraine Classification under Severe Class Imbalance","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08796","citing_title":"Evaluating Deep Learning Models for Multiclass Classification of LIGO Gravitational-Wave Glitches","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPXIZ45ZWVATC2PQTN2CAX6MXZ","json":"https://pith.science/pith/IPXIZ45ZWVATC2PQTN2CAX6MXZ.json","graph_json":"https://pith.science/api/pith-number/IPXIZ45ZWVATC2PQTN2CAX6MXZ/graph.json","events_json":"https://pith.science/api/pith-number/IPXIZ45ZWVATC2PQTN2CAX6MXZ/events.json","paper":"https://pith.science/paper/IPXIZ45Z"},"agent_actions":{"view_html":"https://pith.science/pith/IPXIZ45ZWVATC2PQTN2CAX6MXZ","download_json":"https://pith.science/pith/IPXIZ45ZWVATC2PQTN2CAX6MXZ.json","view_paper":"https://pith.science/paper/IPXIZ45Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.08548&json=true","fetch_graph":"https://pith.science/api/pith-number/IPXIZ45ZWVATC2PQTN2CAX6MXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/IPXIZ45ZWVATC2PQTN2CAX6MXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPXIZ45ZWVATC2PQTN2CAX6MXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPXIZ45ZWVATC2PQTN2CAX6MXZ/action/storage_attestation","attest_author":"https://pith.science/pith/IPXIZ45ZWVATC2PQTN2CAX6MXZ/action/author_attestation","sign_citation":"https://pith.science/pith/IPXIZ45ZWVATC2PQTN2CAX6MXZ/action/citation_signature","submit_replication":"https://pith.science/pith/IPXIZ45ZWVATC2PQTN2CAX6MXZ/action/replication_record"}},"created_at":"2026-07-05T07:31:50.617425+00:00","updated_at":"2026-07-05T07:31:50.617425+00:00"}