{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JGPV76RILKUQLWPQPRDW3EY52Q","short_pith_number":"pith:JGPV76RI","schema_version":"1.0","canonical_sha256":"499f5ffa285aa905d9f07c476d931dd4184c53187f347175e025b3b1422a3294","source":{"kind":"arxiv","id":"1806.07538","version":2},"attestation_state":"computed","paper":{"title":"Towards Robust Interpretability with Self-Explaining Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Alvarez-Melis, Tommi S. Jaakkola","submitted_at":"2018-06-20T03:47:03Z","abstract_excerpt":"Most recent work on interpretability of complex machine learning models has focused on estimating $\\textit{a posteriori}$ explanations for previously trained models around specific predictions. $\\textit{Self-explaining}$ models where interpretability plays a key role already during learning have received much less attention. We propose three desiderata for explanations in general -- explicitness, faithfulness, and stability -- and show that existing methods do not satisfy them. In response, we design self-explaining models in stages, progressively generalizing linear classifiers to complex yet"},"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":"1806.07538","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-20T03:47:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"96b9f2c8f8c8bd678e0f0264f3e1281a857fb669c6f034ca9da5a795e2b6a0c0","abstract_canon_sha256":"576ac83320c98d1cffa25fbdde5f2490cc0dffca11e58d5c0098bd7a39cf827a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:16.912157Z","signature_b64":"ZUFH1+Y6QvVL4KGq0O/IHMARBS4zvi98NMCIqgDFJaQya5XyQbzIyCOznqO87G9sT8NyILpuGDgaYhZcerjmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"499f5ffa285aa905d9f07c476d931dd4184c53187f347175e025b3b1422a3294","last_reissued_at":"2026-05-17T23:59:16.911255Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:16.911255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Robust Interpretability with Self-Explaining Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Alvarez-Melis, Tommi S. Jaakkola","submitted_at":"2018-06-20T03:47:03Z","abstract_excerpt":"Most recent work on interpretability of complex machine learning models has focused on estimating $\\textit{a posteriori}$ explanations for previously trained models around specific predictions. $\\textit{Self-explaining}$ models where interpretability plays a key role already during learning have received much less attention. We propose three desiderata for explanations in general -- explicitness, faithfulness, and stability -- and show that existing methods do not satisfy them. In response, we design self-explaining models in stages, progressively generalizing linear classifiers to complex yet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.07538","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":""},"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":"1806.07538","created_at":"2026-05-17T23:59:16.911332+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.07538v2","created_at":"2026-05-17T23:59:16.911332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.07538","created_at":"2026-05-17T23:59:16.911332+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGPV76RILKUQ","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGPV76RILKUQLWPQ","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGPV76RI","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07166","citing_title":"DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGPV76RILKUQLWPQPRDW3EY52Q","json":"https://pith.science/pith/JGPV76RILKUQLWPQPRDW3EY52Q.json","graph_json":"https://pith.science/api/pith-number/JGPV76RILKUQLWPQPRDW3EY52Q/graph.json","events_json":"https://pith.science/api/pith-number/JGPV76RILKUQLWPQPRDW3EY52Q/events.json","paper":"https://pith.science/paper/JGPV76RI"},"agent_actions":{"view_html":"https://pith.science/pith/JGPV76RILKUQLWPQPRDW3EY52Q","download_json":"https://pith.science/pith/JGPV76RILKUQLWPQPRDW3EY52Q.json","view_paper":"https://pith.science/paper/JGPV76RI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.07538&json=true","fetch_graph":"https://pith.science/api/pith-number/JGPV76RILKUQLWPQPRDW3EY52Q/graph.json","fetch_events":"https://pith.science/api/pith-number/JGPV76RILKUQLWPQPRDW3EY52Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGPV76RILKUQLWPQPRDW3EY52Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGPV76RILKUQLWPQPRDW3EY52Q/action/storage_attestation","attest_author":"https://pith.science/pith/JGPV76RILKUQLWPQPRDW3EY52Q/action/author_attestation","sign_citation":"https://pith.science/pith/JGPV76RILKUQLWPQPRDW3EY52Q/action/citation_signature","submit_replication":"https://pith.science/pith/JGPV76RILKUQLWPQPRDW3EY52Q/action/replication_record"}},"created_at":"2026-05-17T23:59:16.911332+00:00","updated_at":"2026-05-17T23:59:16.911332+00:00"}