{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X3WO6DHH7LHXUIQGUEHVW7D3KO","short_pith_number":"pith:X3WO6DHH","schema_version":"1.0","canonical_sha256":"beecef0ce7facf7a2206a10f5b7c7b538fc2f2ed66a441ec2ec460b6c4268e45","source":{"kind":"arxiv","id":"2506.17466","version":1},"attestation_state":"computed","paper":{"title":"FedNAMs: Performing Interpretability Analysis in Federated Learning Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amitash Nanda, Debashis Sahoo, Sree Bhargavi Balija","submitted_at":"2025-06-20T20:14:13Z","abstract_excerpt":"Federated learning continues to evolve but faces challenges in interpretability and explainability. To address these challenges, we introduce a novel approach that employs Neural Additive Models (NAMs) within a federated learning framework. This new Federated Neural Additive Models (FedNAMs) approach merges the advantages of NAMs, where individual networks concentrate on specific input features, with the decentralized approach of federated learning, ultimately producing interpretable analysis results. This integration enhances privacy by training on local data across multiple devices, thereby "},"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":"2506.17466","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T20:14:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b215f23f595e4563f02eb57c20ffba4b56fac11f841d55c5c7c65e79a743aafb","abstract_canon_sha256":"ad5898b05a36dcf95acccacfb106c6834c64b3a95eae3b8611f7a46fc61685da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:18.080786Z","signature_b64":"K7SgE/LwCUiqS4b0U+ee8D6ORi//I/VXThgAy86Nsf4DU4zyZsHWr6LWiu9cnr3pt4rmSMKOVQT1SYmDGJi8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"beecef0ce7facf7a2206a10f5b7c7b538fc2f2ed66a441ec2ec460b6c4268e45","last_reissued_at":"2026-07-05T11:25:18.080299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:18.080299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedNAMs: Performing Interpretability Analysis in Federated Learning Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amitash Nanda, Debashis Sahoo, Sree Bhargavi Balija","submitted_at":"2025-06-20T20:14:13Z","abstract_excerpt":"Federated learning continues to evolve but faces challenges in interpretability and explainability. To address these challenges, we introduce a novel approach that employs Neural Additive Models (NAMs) within a federated learning framework. This new Federated Neural Additive Models (FedNAMs) approach merges the advantages of NAMs, where individual networks concentrate on specific input features, with the decentralized approach of federated learning, ultimately producing interpretable analysis results. This integration enhances privacy by training on local data across multiple devices, thereby "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17466","kind":"arxiv","version":1},"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/2506.17466/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":"2506.17466","created_at":"2026-07-05T11:25:18.080363+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17466v1","created_at":"2026-07-05T11:25:18.080363+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17466","created_at":"2026-07-05T11:25:18.080363+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3WO6DHH7LHX","created_at":"2026-07-05T11:25:18.080363+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3WO6DHH7LHXUIQG","created_at":"2026-07-05T11:25:18.080363+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3WO6DHH","created_at":"2026-07-05T11:25:18.080363+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07901","citing_title":"The Trust Fabric: Decentralized Interoperability and Economic Coordination for the Agentic Web","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X3WO6DHH7LHXUIQGUEHVW7D3KO","json":"https://pith.science/pith/X3WO6DHH7LHXUIQGUEHVW7D3KO.json","graph_json":"https://pith.science/api/pith-number/X3WO6DHH7LHXUIQGUEHVW7D3KO/graph.json","events_json":"https://pith.science/api/pith-number/X3WO6DHH7LHXUIQGUEHVW7D3KO/events.json","paper":"https://pith.science/paper/X3WO6DHH"},"agent_actions":{"view_html":"https://pith.science/pith/X3WO6DHH7LHXUIQGUEHVW7D3KO","download_json":"https://pith.science/pith/X3WO6DHH7LHXUIQGUEHVW7D3KO.json","view_paper":"https://pith.science/paper/X3WO6DHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17466&json=true","fetch_graph":"https://pith.science/api/pith-number/X3WO6DHH7LHXUIQGUEHVW7D3KO/graph.json","fetch_events":"https://pith.science/api/pith-number/X3WO6DHH7LHXUIQGUEHVW7D3KO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3WO6DHH7LHXUIQGUEHVW7D3KO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3WO6DHH7LHXUIQGUEHVW7D3KO/action/storage_attestation","attest_author":"https://pith.science/pith/X3WO6DHH7LHXUIQGUEHVW7D3KO/action/author_attestation","sign_citation":"https://pith.science/pith/X3WO6DHH7LHXUIQGUEHVW7D3KO/action/citation_signature","submit_replication":"https://pith.science/pith/X3WO6DHH7LHXUIQGUEHVW7D3KO/action/replication_record"}},"created_at":"2026-07-05T11:25:18.080363+00:00","updated_at":"2026-07-05T11:25:18.080363+00:00"}