{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DQW66JDHQVYZ4KI7KG2HCMZSL7","short_pith_number":"pith:DQW66JDH","schema_version":"1.0","canonical_sha256":"1c2def246785719e291f51b47133325fffdc68ef8cc86f2042b30470c49dcddc","source":{"kind":"arxiv","id":"1705.04977","version":4},"attestation_state":"computed","paper":{"title":"Detecting Statistical Interactions from Neural Network Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dehua Cheng, Michael Tsang, Yan Liu","submitted_at":"2017-05-14T15:35:29Z","abstract_excerpt":"Interpreting neural networks is a crucial and challenging task in machine learning. In this paper, we develop a novel framework for detecting statistical interactions captured by a feedforward multilayer neural network by directly interpreting its learned weights. Depending on the desired interactions, our method can achieve significantly better or similar interaction detection performance compared to the state-of-the-art without searching an exponential solution space of possible interactions. We obtain this accuracy and efficiency by observing that interactions between input features are cre"},"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":"1705.04977","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-14T15:35:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a5ff0e25d8455eaa38f94b0f650e45d02977a71669a4a0bf7e195b29545ad638","abstract_canon_sha256":"85733efb51babeb0691a8956d5c5606b6dac94dd0ab0f813ee4ea211fe27fd1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:29.246873Z","signature_b64":"eoa1QnKWw9ObFZqzy5dAk04PEpNUI07JP1ShBZuGUFP0gSrjNa3/hliEH+MxF3YJOqHSgN4nTXlOqCNBd7USCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c2def246785719e291f51b47133325fffdc68ef8cc86f2042b30470c49dcddc","last_reissued_at":"2026-05-18T00:22:29.246081Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:29.246081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Statistical Interactions from Neural Network Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dehua Cheng, Michael Tsang, Yan Liu","submitted_at":"2017-05-14T15:35:29Z","abstract_excerpt":"Interpreting neural networks is a crucial and challenging task in machine learning. In this paper, we develop a novel framework for detecting statistical interactions captured by a feedforward multilayer neural network by directly interpreting its learned weights. Depending on the desired interactions, our method can achieve significantly better or similar interaction detection performance compared to the state-of-the-art without searching an exponential solution space of possible interactions. We obtain this accuracy and efficiency by observing that interactions between input features are cre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04977","kind":"arxiv","version":4},"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":"1705.04977","created_at":"2026-05-18T00:22:29.246208+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.04977v4","created_at":"2026-05-18T00:22:29.246208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04977","created_at":"2026-05-18T00:22:29.246208+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQW66JDHQVYZ","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQW66JDHQVYZ4KI7","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQW66JDH","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18498","citing_title":"A scalable estimator of higher-order information in complex dynamical systems","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01484","citing_title":"Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks","ref_index":136,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13332","citing_title":"Selecting Feature Interactions for Generalized Additive Models by Distilling Foundation Models","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQW66JDHQVYZ4KI7KG2HCMZSL7","json":"https://pith.science/pith/DQW66JDHQVYZ4KI7KG2HCMZSL7.json","graph_json":"https://pith.science/api/pith-number/DQW66JDHQVYZ4KI7KG2HCMZSL7/graph.json","events_json":"https://pith.science/api/pith-number/DQW66JDHQVYZ4KI7KG2HCMZSL7/events.json","paper":"https://pith.science/paper/DQW66JDH"},"agent_actions":{"view_html":"https://pith.science/pith/DQW66JDHQVYZ4KI7KG2HCMZSL7","download_json":"https://pith.science/pith/DQW66JDHQVYZ4KI7KG2HCMZSL7.json","view_paper":"https://pith.science/paper/DQW66JDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.04977&json=true","fetch_graph":"https://pith.science/api/pith-number/DQW66JDHQVYZ4KI7KG2HCMZSL7/graph.json","fetch_events":"https://pith.science/api/pith-number/DQW66JDHQVYZ4KI7KG2HCMZSL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQW66JDHQVYZ4KI7KG2HCMZSL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQW66JDHQVYZ4KI7KG2HCMZSL7/action/storage_attestation","attest_author":"https://pith.science/pith/DQW66JDHQVYZ4KI7KG2HCMZSL7/action/author_attestation","sign_citation":"https://pith.science/pith/DQW66JDHQVYZ4KI7KG2HCMZSL7/action/citation_signature","submit_replication":"https://pith.science/pith/DQW66JDHQVYZ4KI7KG2HCMZSL7/action/replication_record"}},"created_at":"2026-05-18T00:22:29.246208+00:00","updated_at":"2026-05-18T00:22:29.246208+00:00"}