{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:E4NWTL32XCAT7AXCRAZADCQEXJ","short_pith_number":"pith:E4NWTL32","schema_version":"1.0","canonical_sha256":"271b69af7ab8813f82e28832018a04ba60ad6413eaff31558c172e13da1af8e6","source":{"kind":"arxiv","id":"1812.04801","version":1},"attestation_state":"computed","paper":{"title":"Can I trust you more? Model-Agnostic Hierarchical Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dongxu Ren, Michael Tsang, Yan Liu, Youbang Sun","submitted_at":"2018-12-12T04:12:29Z","abstract_excerpt":"Interactions such as double negation in sentences and scene interactions in images are common forms of complex dependencies captured by state-of-the-art machine learning models. We propose Mah\\'e, a novel approach to provide Model-agnostic hierarchical \\'explanations of how powerful machine learning models, such as deep neural networks, capture these interactions as either dependent on or free of the context of data instances. Specifically, Mah\\'e provides context-dependent explanations by a novel local interpretation algorithm that effectively captures any-order interactions, and obtains cont"},"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":"1812.04801","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-12T04:12:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"47d58253305a4957cc247944b2ad8439437f8b33d86a19135ac5d45210770d00","abstract_canon_sha256":"8ea276409a48690ff0b3b24310ff49de48e1861e5df82cd26079402b47e2083e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:27.336367Z","signature_b64":"I3dvuSgHTeb2ONiQeWbzkwz0MGxX4yRIYzxLzNqDb+GkaENeEgdexBQfWUIMZGzTi7ryFK8YEW4xDi06tk8pAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"271b69af7ab8813f82e28832018a04ba60ad6413eaff31558c172e13da1af8e6","last_reissued_at":"2026-05-17T23:58:27.335538Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:27.335538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can I trust you more? Model-Agnostic Hierarchical Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dongxu Ren, Michael Tsang, Yan Liu, Youbang Sun","submitted_at":"2018-12-12T04:12:29Z","abstract_excerpt":"Interactions such as double negation in sentences and scene interactions in images are common forms of complex dependencies captured by state-of-the-art machine learning models. We propose Mah\\'e, a novel approach to provide Model-agnostic hierarchical \\'explanations of how powerful machine learning models, such as deep neural networks, capture these interactions as either dependent on or free of the context of data instances. Specifically, Mah\\'e provides context-dependent explanations by a novel local interpretation algorithm that effectively captures any-order interactions, and obtains cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04801","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":""},"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":"1812.04801","created_at":"2026-05-17T23:58:27.335658+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.04801v1","created_at":"2026-05-17T23:58:27.335658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04801","created_at":"2026-05-17T23:58:27.335658+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4NWTL32XCAT","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4NWTL32XCAT7AXC","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4NWTL32","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06661","citing_title":"iLOCO: Distribution-Free Inference for Feature Interactions","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4NWTL32XCAT7AXCRAZADCQEXJ","json":"https://pith.science/pith/E4NWTL32XCAT7AXCRAZADCQEXJ.json","graph_json":"https://pith.science/api/pith-number/E4NWTL32XCAT7AXCRAZADCQEXJ/graph.json","events_json":"https://pith.science/api/pith-number/E4NWTL32XCAT7AXCRAZADCQEXJ/events.json","paper":"https://pith.science/paper/E4NWTL32"},"agent_actions":{"view_html":"https://pith.science/pith/E4NWTL32XCAT7AXCRAZADCQEXJ","download_json":"https://pith.science/pith/E4NWTL32XCAT7AXCRAZADCQEXJ.json","view_paper":"https://pith.science/paper/E4NWTL32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.04801&json=true","fetch_graph":"https://pith.science/api/pith-number/E4NWTL32XCAT7AXCRAZADCQEXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/E4NWTL32XCAT7AXCRAZADCQEXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4NWTL32XCAT7AXCRAZADCQEXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4NWTL32XCAT7AXCRAZADCQEXJ/action/storage_attestation","attest_author":"https://pith.science/pith/E4NWTL32XCAT7AXCRAZADCQEXJ/action/author_attestation","sign_citation":"https://pith.science/pith/E4NWTL32XCAT7AXCRAZADCQEXJ/action/citation_signature","submit_replication":"https://pith.science/pith/E4NWTL32XCAT7AXCRAZADCQEXJ/action/replication_record"}},"created_at":"2026-05-17T23:58:27.335658+00:00","updated_at":"2026-05-17T23:58:27.335658+00:00"}