{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BMK4PPGYPCGCOPJT5VMSPJWCG4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"38989a55f9fbf52646eec4d963151c3b2a09b25f4ddd4f5714d9321543e35cff","cross_cats_sorted":["math.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-10T09:43:02Z","title_canon_sha256":"4a25bac3b5358d8cc76a7085ca20ba733ccd74614c9737e3a4ac8200e45a5524"},"schema_version":"1.0","source":{"id":"2110.04744","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04744","created_at":"2026-07-05T04:00:03Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04744v2","created_at":"2026-07-05T04:00:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04744","created_at":"2026-07-05T04:00:03Z"},{"alias_kind":"pith_short_12","alias_value":"BMK4PPGYPCGC","created_at":"2026-07-05T04:00:03Z"},{"alias_kind":"pith_short_16","alias_value":"BMK4PPGYPCGCOPJT","created_at":"2026-07-05T04:00:03Z"},{"alias_kind":"pith_short_8","alias_value":"BMK4PPGY","created_at":"2026-07-05T04:00:03Z"}],"graph_snapshots":[{"event_id":"sha256:26deb7d7b1bac160f3fcfb0b1bb6756f4af5500d234bd32855926d9f1cadb127","target":"graph","created_at":"2026-07-05T04:00:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.04744/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel method called Long Expressive Memory (LEM) for learning long-term sequential dependencies. LEM is gradient-based, it can efficiently process sequential tasks with very long-term dependencies, and it is sufficiently expressive to be able to learn complicated input-output maps. To derive LEM, we consider a system of multiscale ordinary differential equations, as well as a suitable time-discretization of this system. For LEM, we derive rigorous bounds to show the mitigation of the exploding and vanishing gradients problem, a well-known challenge for gradient-based recurrent seq","authors_text":"Michael W. Mahoney, N. Benjamin Erichson, Siddhartha Mishra, T. Konstantin Rusch","cross_cats":["math.DS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-10T09:43:02Z","title":"Long Expressive Memory for Sequence Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04744","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fadc8e250905e29157744d4e9bf945f69e51ea5f5bd56f64ce2b8e1c3088c3e9","target":"record","created_at":"2026-07-05T04:00:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"38989a55f9fbf52646eec4d963151c3b2a09b25f4ddd4f5714d9321543e35cff","cross_cats_sorted":["math.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-10T09:43:02Z","title_canon_sha256":"4a25bac3b5358d8cc76a7085ca20ba733ccd74614c9737e3a4ac8200e45a5524"},"schema_version":"1.0","source":{"id":"2110.04744","kind":"arxiv","version":2}},"canonical_sha256":"0b15c7bcd8788c273d33ed5927a6c23728580b4774bf3ac1b9d7169a940d7548","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b15c7bcd8788c273d33ed5927a6c23728580b4774bf3ac1b9d7169a940d7548","first_computed_at":"2026-07-05T04:00:03.467527Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:00:03.467527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZCbcVVaFNsTyMxjW6tbcuU3NB/C+oE2iohfkWzs1qtUK1kbUOmcYWBuLBCLnmBm48JN/aB52naL6u7LvlPFCAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:00:03.468020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04744","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fadc8e250905e29157744d4e9bf945f69e51ea5f5bd56f64ce2b8e1c3088c3e9","sha256:26deb7d7b1bac160f3fcfb0b1bb6756f4af5500d234bd32855926d9f1cadb127"],"state_sha256":"f9ddbf21f79fb505cdbfa0805ba1ddbcf86f145fa02542480128996ca59258f3"}