{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2M3DKFUUPIZSLDJMF4HSPENJLH","short_pith_number":"pith:2M3DKFUU","schema_version":"1.0","canonical_sha256":"d3363516947a33258d2c2f0f2791a959f9e0d385025d5799e66f8ed2214efaa8","source":{"kind":"arxiv","id":"1811.07490","version":3},"attestation_state":"computed","paper":{"title":"Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyu Zhu, Jianjin Zhang, Jianmin Wang, Mingsheng Long, Philip S Yu, Yunbo Wang","submitted_at":"2018-11-19T04:07:49Z","abstract_excerpt":"Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the accumulation, deformation or dissipation of radar echoes in precipitation forecasting. From Cramer's Decomposition, any non-stationary process can be decomposed into deterministic, time-variant polynomials, plus a zero-mean stochastic term. By applying differencing operations appropriately, we may turn time-variant polynomials into a constant, making the deterministi"},"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":"1811.07490","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T04:07:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6729f94c019cdfb6cadc192d08a945321bf8e64bdd5baf544463e99a49541c12","abstract_canon_sha256":"9936a3c04a31d087a5d8f0e577ced468f2247f566ebd5a6fbfa8fd7f38f875fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:06.387826Z","signature_b64":"rNuas3jX+xXmwZBVwWcYWDFr1Rc/aWss/vU3xqEVoaCK8XLzhqXV19CKgr9VLrzfZYISRNM8aZULG7bGJT9AAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3363516947a33258d2c2f0f2791a959f9e0d385025d5799e66f8ed2214efaa8","last_reissued_at":"2026-05-17T23:48:06.387344Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:06.387344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyu Zhu, Jianjin Zhang, Jianmin Wang, Mingsheng Long, Philip S Yu, Yunbo Wang","submitted_at":"2018-11-19T04:07:49Z","abstract_excerpt":"Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the accumulation, deformation or dissipation of radar echoes in precipitation forecasting. From Cramer's Decomposition, any non-stationary process can be decomposed into deterministic, time-variant polynomials, plus a zero-mean stochastic term. By applying differencing operations appropriately, we may turn time-variant polynomials into a constant, making the deterministi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07490","kind":"arxiv","version":3},"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":"1811.07490","created_at":"2026-05-17T23:48:06.387426+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.07490v3","created_at":"2026-05-17T23:48:06.387426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07490","created_at":"2026-05-17T23:48:06.387426+00:00"},{"alias_kind":"pith_short_12","alias_value":"2M3DKFUUPIZS","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2M3DKFUUPIZSLDJM","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2M3DKFUU","created_at":"2026-05-18T12:32:02.567920+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/2M3DKFUUPIZSLDJMF4HSPENJLH","json":"https://pith.science/pith/2M3DKFUUPIZSLDJMF4HSPENJLH.json","graph_json":"https://pith.science/api/pith-number/2M3DKFUUPIZSLDJMF4HSPENJLH/graph.json","events_json":"https://pith.science/api/pith-number/2M3DKFUUPIZSLDJMF4HSPENJLH/events.json","paper":"https://pith.science/paper/2M3DKFUU"},"agent_actions":{"view_html":"https://pith.science/pith/2M3DKFUUPIZSLDJMF4HSPENJLH","download_json":"https://pith.science/pith/2M3DKFUUPIZSLDJMF4HSPENJLH.json","view_paper":"https://pith.science/paper/2M3DKFUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.07490&json=true","fetch_graph":"https://pith.science/api/pith-number/2M3DKFUUPIZSLDJMF4HSPENJLH/graph.json","fetch_events":"https://pith.science/api/pith-number/2M3DKFUUPIZSLDJMF4HSPENJLH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2M3DKFUUPIZSLDJMF4HSPENJLH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2M3DKFUUPIZSLDJMF4HSPENJLH/action/storage_attestation","attest_author":"https://pith.science/pith/2M3DKFUUPIZSLDJMF4HSPENJLH/action/author_attestation","sign_citation":"https://pith.science/pith/2M3DKFUUPIZSLDJMF4HSPENJLH/action/citation_signature","submit_replication":"https://pith.science/pith/2M3DKFUUPIZSLDJMF4HSPENJLH/action/replication_record"}},"created_at":"2026-05-17T23:48:06.387426+00:00","updated_at":"2026-05-17T23:48:06.387426+00:00"}