{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ITWVLRNUP5NGWSJUPGSYRQGCQV","short_pith_number":"pith:ITWVLRNU","schema_version":"1.0","canonical_sha256":"44ed55c5b47f5a6b493479a588c0c28553c0099b162fbfc169a188236c7ae604","source":{"kind":"arxiv","id":"1805.07137","version":2},"attestation_state":"computed","paper":{"title":"Knowledge Discovery from Layered Neural Networks based on Non-negative Task Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chihiro Watanabe, Kaoru Hiramatsu, Kunio Kashino","submitted_at":"2018-05-18T10:55:21Z","abstract_excerpt":"Interpretability has become an important issue in the machine learning field, along with the success of layered neural networks in various practical tasks. Since a trained layered neural network consists of a complex nonlinear relationship between large number of parameters, we failed to understand how they could achieve input-output mappings with a given data set. In this paper, we propose the non-negative task decomposition method, which applies non-negative matrix factorization to a trained layered neural network. This enables us to decompose the inference mechanism of a trained layered neu"},"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":"1805.07137","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-18T10:55:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"470abf0e15efc831fdc3a022db5fc1a53439616434a6d8917602e85598b87a46","abstract_canon_sha256":"e6ea65481274cdc31de2bfd467c1b56e934e4bb65789204e150fca9b873ac0d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:36.027832Z","signature_b64":"XR2TmgIkZL35m7hTophbTo2TaIgWJ1PIvCtHTzzdLfS2hRVpQBsiUP9fDGduGB8NGgkdBWVm7a0Ycb8oMfxFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44ed55c5b47f5a6b493479a588c0c28553c0099b162fbfc169a188236c7ae604","last_reissued_at":"2026-05-18T00:15:36.026990Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:36.026990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Discovery from Layered Neural Networks based on Non-negative Task Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chihiro Watanabe, Kaoru Hiramatsu, Kunio Kashino","submitted_at":"2018-05-18T10:55:21Z","abstract_excerpt":"Interpretability has become an important issue in the machine learning field, along with the success of layered neural networks in various practical tasks. Since a trained layered neural network consists of a complex nonlinear relationship between large number of parameters, we failed to understand how they could achieve input-output mappings with a given data set. In this paper, we propose the non-negative task decomposition method, which applies non-negative matrix factorization to a trained layered neural network. This enables us to decompose the inference mechanism of a trained layered neu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07137","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":"1805.07137","created_at":"2026-05-18T00:15:36.027123+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.07137v2","created_at":"2026-05-18T00:15:36.027123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07137","created_at":"2026-05-18T00:15:36.027123+00:00"},{"alias_kind":"pith_short_12","alias_value":"ITWVLRNUP5NG","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"ITWVLRNUP5NGWSJU","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"ITWVLRNU","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ITWVLRNUP5NGWSJUPGSYRQGCQV","json":"https://pith.science/pith/ITWVLRNUP5NGWSJUPGSYRQGCQV.json","graph_json":"https://pith.science/api/pith-number/ITWVLRNUP5NGWSJUPGSYRQGCQV/graph.json","events_json":"https://pith.science/api/pith-number/ITWVLRNUP5NGWSJUPGSYRQGCQV/events.json","paper":"https://pith.science/paper/ITWVLRNU"},"agent_actions":{"view_html":"https://pith.science/pith/ITWVLRNUP5NGWSJUPGSYRQGCQV","download_json":"https://pith.science/pith/ITWVLRNUP5NGWSJUPGSYRQGCQV.json","view_paper":"https://pith.science/paper/ITWVLRNU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.07137&json=true","fetch_graph":"https://pith.science/api/pith-number/ITWVLRNUP5NGWSJUPGSYRQGCQV/graph.json","fetch_events":"https://pith.science/api/pith-number/ITWVLRNUP5NGWSJUPGSYRQGCQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ITWVLRNUP5NGWSJUPGSYRQGCQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ITWVLRNUP5NGWSJUPGSYRQGCQV/action/storage_attestation","attest_author":"https://pith.science/pith/ITWVLRNUP5NGWSJUPGSYRQGCQV/action/author_attestation","sign_citation":"https://pith.science/pith/ITWVLRNUP5NGWSJUPGSYRQGCQV/action/citation_signature","submit_replication":"https://pith.science/pith/ITWVLRNUP5NGWSJUPGSYRQGCQV/action/replication_record"}},"created_at":"2026-05-18T00:15:36.027123+00:00","updated_at":"2026-05-18T00:15:36.027123+00:00"}