{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KSPE23SIQ5SKR3XS5LHU6T55X5","short_pith_number":"pith:KSPE23SI","schema_version":"1.0","canonical_sha256":"549e4d6e488764a8eef2eacf4f4fbdbf4db97d0278347a98116b1286ad9a4d16","source":{"kind":"arxiv","id":"2103.15589","version":3},"attestation_state":"computed","paper":{"title":"Backpropagation Through Time For Networks With Long-Term Dependencies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"George Bird, Maxim E. Polivoda","submitted_at":"2021-03-26T15:55:54Z","abstract_excerpt":"Backpropagation through time (BPTT) is a technique of updating tuned parameters within recurrent neural networks (RNNs). Several attempts at creating such an algorithm have been made including: Nth Ordered Approximations and Truncated-BPTT. These methods approximate the backpropagation gradients under the assumption that the RNN only utilises short-term dependencies. This is an acceptable assumption to make for the current state of artificial neural networks. As RNNs become more advanced, a shift towards influence by long-term dependencies is likely. Thus, a new method for backpropagation is r"},"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":"2103.15589","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-26T15:55:54Z","cross_cats_sorted":[],"title_canon_sha256":"fadcbea8498d13b8d0b57b7246ec9409e8b4cc1e30c69ecb702834a67e38a50a","abstract_canon_sha256":"9ebbd1b077cebf3c49f3d35faf74eec8e1365e7607b5dac68ff05781e8c29df3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:39.923109Z","signature_b64":"w8LwjVifUIkGtya7Im8bKpVksHoHMeuBHnSb3Xq+rMH2UCfDh/ieDFV4PrMFRTWFm3+ui9h6mcO1oCsz4RK+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"549e4d6e488764a8eef2eacf4f4fbdbf4db97d0278347a98116b1286ad9a4d16","last_reissued_at":"2026-07-05T11:26:39.922622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:39.922622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Backpropagation Through Time For Networks With Long-Term Dependencies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"George Bird, Maxim E. Polivoda","submitted_at":"2021-03-26T15:55:54Z","abstract_excerpt":"Backpropagation through time (BPTT) is a technique of updating tuned parameters within recurrent neural networks (RNNs). Several attempts at creating such an algorithm have been made including: Nth Ordered Approximations and Truncated-BPTT. These methods approximate the backpropagation gradients under the assumption that the RNN only utilises short-term dependencies. This is an acceptable assumption to make for the current state of artificial neural networks. As RNNs become more advanced, a shift towards influence by long-term dependencies is likely. Thus, a new method for backpropagation is r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15589","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.15589/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2103.15589","created_at":"2026-07-05T11:26:39.922682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.15589v3","created_at":"2026-07-05T11:26:39.922682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15589","created_at":"2026-07-05T11:26:39.922682+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSPE23SIQ5SK","created_at":"2026-07-05T11:26:39.922682+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSPE23SIQ5SKR3XS","created_at":"2026-07-05T11:26:39.922682+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSPE23SI","created_at":"2026-07-05T11:26:39.922682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.08113","citing_title":"Think Deep, Speak Once: Relit, A Recursive Latent Implicit Transformer Framework","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSPE23SIQ5SKR3XS5LHU6T55X5","json":"https://pith.science/pith/KSPE23SIQ5SKR3XS5LHU6T55X5.json","graph_json":"https://pith.science/api/pith-number/KSPE23SIQ5SKR3XS5LHU6T55X5/graph.json","events_json":"https://pith.science/api/pith-number/KSPE23SIQ5SKR3XS5LHU6T55X5/events.json","paper":"https://pith.science/paper/KSPE23SI"},"agent_actions":{"view_html":"https://pith.science/pith/KSPE23SIQ5SKR3XS5LHU6T55X5","download_json":"https://pith.science/pith/KSPE23SIQ5SKR3XS5LHU6T55X5.json","view_paper":"https://pith.science/paper/KSPE23SI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.15589&json=true","fetch_graph":"https://pith.science/api/pith-number/KSPE23SIQ5SKR3XS5LHU6T55X5/graph.json","fetch_events":"https://pith.science/api/pith-number/KSPE23SIQ5SKR3XS5LHU6T55X5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSPE23SIQ5SKR3XS5LHU6T55X5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSPE23SIQ5SKR3XS5LHU6T55X5/action/storage_attestation","attest_author":"https://pith.science/pith/KSPE23SIQ5SKR3XS5LHU6T55X5/action/author_attestation","sign_citation":"https://pith.science/pith/KSPE23SIQ5SKR3XS5LHU6T55X5/action/citation_signature","submit_replication":"https://pith.science/pith/KSPE23SIQ5SKR3XS5LHU6T55X5/action/replication_record"}},"created_at":"2026-07-05T11:26:39.922682+00:00","updated_at":"2026-07-05T11:26:39.922682+00:00"}