{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:AMEWTM5QWBBHKY4BKODPFS25LO","short_pith_number":"pith:AMEWTM5Q","schema_version":"1.0","canonical_sha256":"030969b3b0b0427563815386f2cb5d5ba7ee53c24c407217e9ccdaf9ae679df5","source":{"kind":"arxiv","id":"1712.04145","version":1},"attestation_state":"computed","paper":{"title":"Transportation analysis of denoising autoencoders: a novel method for analyzing deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Noboru Murata, Sho Sonoda","submitted_at":"2017-12-12T06:37:28Z","abstract_excerpt":"The feature map obtained from the denoising autoencoder (DAE) is investigated by determining transportation dynamics of the DAE, which is a cornerstone for deep learning. Despite the rapid development in its application, deep neural networks remain analytically unexplained, because the feature maps are nested and parameters are not faithful. In this paper, we address the problem of the formulation of nested complex of parameters by regarding the feature map as a transport map. Even when a feature map has different dimensions between input and output, we can regard it as a transportation map by"},"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":"1712.04145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-12T06:37:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b3b282addb279b216518f2606b96cbbdba55b8b38d489ffc28d54d2a524c694e","abstract_canon_sha256":"93916083b7d997ff2016082e18f6aee26d7b82870dd1eec74ee033a4bf9ddffa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:08.991399Z","signature_b64":"yE7fL+gMUy+0n8cIMUbXTV+IIO1xdeLyA5uNntJQYUZ99AHqqWKUa2poaoyhDzJo/00DESUb6cIcLwOkCELSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"030969b3b0b0427563815386f2cb5d5ba7ee53c24c407217e9ccdaf9ae679df5","last_reissued_at":"2026-05-18T00:28:08.990730Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:08.990730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transportation analysis of denoising autoencoders: a novel method for analyzing deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Noboru Murata, Sho Sonoda","submitted_at":"2017-12-12T06:37:28Z","abstract_excerpt":"The feature map obtained from the denoising autoencoder (DAE) is investigated by determining transportation dynamics of the DAE, which is a cornerstone for deep learning. Despite the rapid development in its application, deep neural networks remain analytically unexplained, because the feature maps are nested and parameters are not faithful. In this paper, we address the problem of the formulation of nested complex of parameters by regarding the feature map as a transport map. Even when a feature map has different dimensions between input and output, we can regard it as a transportation map by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.04145","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":"1712.04145","created_at":"2026-05-18T00:28:08.990845+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.04145v1","created_at":"2026-05-18T00:28:08.990845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.04145","created_at":"2026-05-18T00:28:08.990845+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMEWTM5QWBBH","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMEWTM5QWBBHKY4B","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMEWTM5Q","created_at":"2026-05-18T12:31:05.417338+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/AMEWTM5QWBBHKY4BKODPFS25LO","json":"https://pith.science/pith/AMEWTM5QWBBHKY4BKODPFS25LO.json","graph_json":"https://pith.science/api/pith-number/AMEWTM5QWBBHKY4BKODPFS25LO/graph.json","events_json":"https://pith.science/api/pith-number/AMEWTM5QWBBHKY4BKODPFS25LO/events.json","paper":"https://pith.science/paper/AMEWTM5Q"},"agent_actions":{"view_html":"https://pith.science/pith/AMEWTM5QWBBHKY4BKODPFS25LO","download_json":"https://pith.science/pith/AMEWTM5QWBBHKY4BKODPFS25LO.json","view_paper":"https://pith.science/paper/AMEWTM5Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.04145&json=true","fetch_graph":"https://pith.science/api/pith-number/AMEWTM5QWBBHKY4BKODPFS25LO/graph.json","fetch_events":"https://pith.science/api/pith-number/AMEWTM5QWBBHKY4BKODPFS25LO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMEWTM5QWBBHKY4BKODPFS25LO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMEWTM5QWBBHKY4BKODPFS25LO/action/storage_attestation","attest_author":"https://pith.science/pith/AMEWTM5QWBBHKY4BKODPFS25LO/action/author_attestation","sign_citation":"https://pith.science/pith/AMEWTM5QWBBHKY4BKODPFS25LO/action/citation_signature","submit_replication":"https://pith.science/pith/AMEWTM5QWBBHKY4BKODPFS25LO/action/replication_record"}},"created_at":"2026-05-18T00:28:08.990845+00:00","updated_at":"2026-05-18T00:28:08.990845+00:00"}